CN108765362B - Vehicle detection method and device - Google Patents
- ️Tue Apr 11 2023
CN108765362B - Vehicle detection method and device - Google Patents
Vehicle detection method and device Download PDFInfo
-
Publication number
- CN108765362B CN108765362B CN201710261393.5A CN201710261393A CN108765362B CN 108765362 B CN108765362 B CN 108765362B CN 201710261393 A CN201710261393 A CN 201710261393A CN 108765362 B CN108765362 B CN 108765362B Authority
- CN
- China Prior art keywords
- detection
- vehicle
- detection point
- point
- detected Prior art date
- 2017-04-20 Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 462
- 230000006378 damage Effects 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims description 13
- 230000000007 visual effect Effects 0.000 claims description 3
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle detection method and a device, wherein the vehicle detection method comprises the following steps: acquiring an explicit detection result of an explicit detection point in the vehicle to be detected according to the image of the vehicle to be detected; acquiring historical detection results of the dominant detection points and the target detection points in the known vehicle; and generating a detection result of the target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result. According to the vehicle detection method, the detection result of the recessive detection point serving as the target detection point in the vehicle to be detected is determined according to the real and effective detection result of the known vehicle and the dominant detection result of the dominant detection point in the vehicle to be detected, when the recessive detection point is subjected to unobvious damage, the damage condition can be accurately detected, the risk of missing the unobvious damage part is avoided, the detection accuracy is greatly improved, and the applicability is better.
Description
Technical Field
The invention relates to the technical field of vehicle detection, in particular to a vehicle detection method and device.
Background
In the second-hand vehicle industry, vehicle detection is a very important link, and the technical condition or the working capacity of a vehicle can be determined through the vehicle detection, and the damage of the vehicle can be determined at certain positions, so that an accurate vehicle detection report can be provided for a client. Particularly, with the development of the internet second-hand car industry, most of the second-hand car industry provides a network transaction platform for customers, so that the customers can know various performance indexes of the vehicles through vehicle detection reports provided by the network transaction platform without checking the vehicles on site. Therefore, the accuracy and comprehensiveness of vehicle inspection reports is critical to both the used-vehicle industry and to customers transacting via a used-vehicle transaction platform.
In the prior art, most of the used-hand vehicles need to be detected by detectors through experience, the technical conditions and the working capacity of the vehicles are checked, and detection results are given according to various technical indexes of the vehicles. Due to the fact that detection experiences of detection personnel are different, authenticity and effectiveness of detection results are generally low, especially for parts, with normal surfaces and actually hidden damage, of a vehicle, most of detection personnel cannot completely detect the parts through experiences, and therefore detection omission occurs, and the detection results are distorted.
Therefore, the conventional vehicle detection method has low detection accuracy and is easy to cause a phenomenon of distortion of a detection result.
Disclosure of Invention
The invention provides a vehicle detection method and device, and aims to solve the problems that the existing vehicle detection method is low in detection accuracy and easy to generate detection result distortion.
In a first aspect, the present invention provides a vehicle detection method, comprising: acquiring an explicit detection result of an explicit detection point in the vehicle to be detected according to the image of the vehicle to be detected; acquiring historical detection results of the dominant detection point and the target detection point in the known vehicle; and generating a detection result of a target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result.
Further, the process of obtaining the historical detection result associated with the dominant detection point and the target detection point in the known vehicle specifically includes: and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise the classification probability of each dominant detection point, the classification probability of the target detection point and the conditional probability of each dominant detection point and the target detection point.
Further, the process of generating the detection result of the target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result specifically includes: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a naive Bayes algorithm according to the explicit detection result and the historical detection result corresponding to each target detection point.
Further, the process of obtaining the historical detection result associated with the dominant detection point and the target detection point in the known vehicle specifically includes: and acquiring a historical detection result associated with each target detection point and the explicit detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each explicit detection point in the known vehicle influences the detection result of the target detection point.
Further, the process of generating the detection result of the target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result specifically includes: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point.
Further, after the detection result of the target detection point in the vehicle to be detected is generated, the vehicle detection method further comprises the following steps: and displaying a reminding mark at the position of the target detection point with damage in the image of the vehicle to be detected.
In a second aspect, the present invention also provides a vehicle detection apparatus, including: the dominant detection result acquisition module is used for acquiring a dominant detection result of a dominant detection point in the vehicle to be detected according to the image of the vehicle to be detected; the historical detection result acquisition module is used for acquiring the historical detection result associated with the dominant detection point and the target detection point in the known vehicle; and the target detection result generation module is used for generating a detection result of a target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result.
Further, the historical detection result obtaining module is specifically configured to: and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise the classification probability of each dominant detection point, the classification probability of the target detection point and the conditional probability of each dominant detection point and the target detection point.
Further, the target detection result generation module is specifically configured to: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a naive Bayesian algorithm according to the dominant detection result and the historical detection result corresponding to each target detection point.
Further, the historical detection result obtaining module is specifically configured to: and acquiring a historical detection result associated with each target detection point and the explicit detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each explicit detection point in the known vehicle influences the detection result of the target detection point.
Further, the target detection result generation module is specifically configured to: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point.
Further, the vehicle detection device further includes: and the display reminding module is used for displaying a reminding mark at the position of the target detection point with a damaged detection result in the image of the vehicle to be detected.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects: the invention provides a vehicle detection method and device. According to the vehicle detection method, the detection result of the recessive detection point serving as the target detection point in the vehicle to be detected is determined according to the real and effective detection result of the known vehicle and the dominant detection result of the dominant detection point in the vehicle to be detected, when the recessive detection point is subjected to unobvious damage, the damage condition can be accurately detected, the risk of missing the unobvious damage part is avoided, the detection accuracy is greatly improved, and the applicability is better.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a schematic flow chart of a vehicle detection method according to an embodiment of the present invention;
FIG. 2 is a schematic view of a vehicle to be inspected according to an embodiment of the present invention;
fig. 3 is a block diagram of a vehicle detection device according to an embodiment of the present invention.
Detailed Description
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a vehicle detection method according to an embodiment of the present invention. As can be seen from fig. 1, the vehicle detection method includes:
101, acquiring an explicit detection result of an explicit detection point in a vehicle to be detected according to an image of the vehicle to be detected.
The vehicle to be detected refers to a vehicle to be detected at present, and any vehicle needing to be detected can be used as the vehicle to be detected. The image of the vehicle to be inspected refers to a three-dimensional stereoscopic image of the vehicle to be inspected from which each part of the surface of the vehicle to be inspected can be directly observed.
Before a vehicle to be detected is detected, all parts of any vehicle (including the vehicle to be detected) are divided into a plurality of detection points, each detection point comprises at least one part of all the parts, and all parts of any vehicle comprise each part of the surface of the vehicle which can be directly observed in an image of the vehicle (a three-dimensional stereo image of the vehicle) and parts which cannot be directly observed in the image of the vehicle. The explicit detection point refers to a detection point in the vehicle, and a common technician in vehicle detection can directly obtain a detection result through visual observation. Herein, the detection result of the dominant detection point of the vehicle to be detected is defined as the dominant detection result.
Before detecting the vehicle to be detected, the image of the vehicle to be detected needs to be acquired. The method for acquiring the image of the vehicle to be detected includes various methods, for example, the entity of the vehicle to be detected can be shot, the shot image of the vehicle to be detected is input to the detection system, and the detection system can acquire the image of the vehicle to be detected. The detection system may also synthesize an image of the vehicle to be detected by inputting therein planar images of a plurality of angles of the vehicle to be detected.
After the image of the vehicle to be detected is obtained, the realization mode of obtaining the dominant detection result of the dominant detection point in the vehicle to be detected according to the image of the vehicle to be detected is as follows: a technician for vehicle detection observes an image of a vehicle to be detected, determines an explicit detection result of explicit detection points in the vehicle to be detected from the image, inputs the explicit detection result of each explicit detection point to a storage position corresponding to the corresponding explicit detection point in a detection system, and the detection system calls the storage data in each storage position to obtain the explicit detection result of each explicit detection point of the vehicle to be detected.
It should be noted that, in this document, a detection result of any detection point of any vehicle (including the vehicle to be detected) includes damage or no damage. The overt test also includes the presence or absence of lesions.
And 102, acquiring historical detection results of the dominant detection point and the target detection point in the known vehicle.
In all the detection points of any vehicle (including the vehicle to be detected), besides the explicit detection point, the vehicle detection system also comprises a plurality of implicit detection points, namely, the detection points of the detection result cannot be observed by a common technician for vehicle detection through direct observation. Herein, the hidden detection point involved in the current vehicle detection is defined as a target detection point. One or more target detection points may be provided.
The known vehicle refers to a vehicle in which detection results of respective detection points (including an explicit detection point and a implicit detection point) have been determined. Implementations for obtaining historical detection results associated with an explicit detection point and a target detection point in a known vehicle include a variety of approaches, such as:
the first implementation mode is as follows: and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise the classification probability of each dominant detection point, the classification probability of the target detection point and the conditional probability of each dominant detection point and the target detection point.
Wherein the historical detection data comprises: the detection result of each detection point (including all explicit detection points and all implicit detection points) of each known vehicle comprises damage or no damage; the classification probability of each detection point in all the known vehicles comprises the probability that the number of the damaged vehicles at the detection point occupies the total number of all the known vehicles and the probability that the number of the undamaged vehicles at the detection point occupies the total number of all the known vehicles; and each dominant detection point in the plurality of dominant detection points associated with each target detection point in all known vehicles has a conditional probability with the target detection point, wherein the conditional probability comprises the probability that each dominant detection point has damage under the condition that the target detection point has damage and the probability that each dominant detection point has damage under the condition that the target detection point is not damaged.
The multiple dominant detection points associated with each target detection point refer to dominant detection points that affect the technical performance of the target detection point, and are usually set manually according to the detection experience of a detection expert.
The second implementation manner is as follows: and acquiring a historical detection result associated with each target detection point and the explicit detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each explicit detection point in the known vehicle influences the detection result of the target detection point. The historical detection result can be set manually through expert experience.
And 103, generating a detection result of the target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result.
In
step102, if a first implementation manner is adopted to obtain a historical detection result of the dominant detection point in the known vehicle associated with the target detection point, in step 103, a process of generating a detection result of the target detection point in the vehicle to be detected according to the dominant detection result and the historical detection result specifically includes: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a naive Bayes algorithm according to the explicit detection result and the historical detection result corresponding to each target detection point. Examples are as follows:
referring to fig. 2, fig. 2 is a schematic diagram of a vehicle to be detected according to an embodiment of the present invention. In fig. 2, the vehicles to be detected have three detection points in total, including: a column A, a column B and a front framework; wherein, the A column is a target detection point, and the B column and the front framework are two dominant detection points associated with the A column of the target detection point. If the obtained explicit detection results of the dominant detection point B column and the front skeleton of the vehicle to be detected are damaged, the detection result of the target detection point A column can be calculated by adopting the following naive Bayes formula (1) and naive Bayes formula (2).
P [ column A has damage (column B has damage, anterior skeleton has damage) ]
= P [ (pillar damaged, anterior skeleton damaged) | A pillar damaged ]. P (pillar damaged/A)/P (pillar damaged, anterior skeleton damaged)
= [ P (B pillar damaged | a pillar damaged) × P (a pillar damaged)/[ P (B pillar damaged) × P (front skeleton damaged) ] (1)
P [ non-injury to column A (injury to column B and injury to anterior skeleton) ]
= P [ (pillar damaged, anterior skeleton damaged) | A pillar not damaged ]. P (pillar not damaged)/P (pillar damaged, anterior skeleton damaged)
= [ P (B pillar damaged | a pillar damage) × P (a pillar damage) ]/[ P (B pillar damaged) × P (front skeleton damaged) ] (2)
In the above formula (1) and formula (2), P (the B column is damaged, | a column is damaged) and P (the B column is damaged, | a column is not damaged) represent conditional probabilities of the dominant checkpoint B column and the target checkpoint a column in the known vehicle; p (the front framework has damage | A column has damage) and P (the front framework has damage | A column has no damage) represent conditional probabilities of the dominant checkpoint front framework and the target checkpoint A column in the known vehicle; p (damaged column A) and P (undamaged column A) represent the classification probability of the column A at the target detection point in the known vehicle; p (B-pillars are damaged) represents the classification probability of the dominant detection point B-pillar in the aforementioned known vehicle; p (damaged front skeleton) represents the classification probability of the dominant detection point front skeleton in the aforementioned known vehicle. These probability data in equations (1) and (2) may be extracted from the stored historical detection data.
It should be noted that the vehicle to be detected in fig. 2 may be replaced by any vehicle that needs to be detected. In addition, if the obtained explicit detection results of the two explicit detection points associated with other target detection points in the vehicle to be detected are all damaged, the detection results of the target detection points can be calculated by adopting the formula (1) and the formula (2). During specific calculation, the correlation probabilities of the target detection point A column and the two dominant detection points related to the A column in the formula (1) and the formula (2) are replaced by the correlation probabilities of the target detection point and the two dominant detection points related to the target detection point correspondingly.
In
step102, if a second implementation manner is adopted to obtain a historical detection result of the dominant detection point in the known vehicle associated with the target detection point, in step 103, a process of generating a detection result of the target detection point in the vehicle to be detected according to the dominant detection result and the historical detection result specifically includes: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point. Wherein the preset pattern may be set to take a maximum value. Examples are as follows:
for the vehicle to be detected in fig. 2, the probability that the detection results obtained from the dominant detection point B pillar and the front skeleton in the known vehicle affect the detection result of the target detection point a pillar is as follows:
damage to column B, with a probability of 0.4 for column A;
the anterior skeleton is damaged, and the probability of the A column is 0.3;
if the dominant detection result of the B column in the vehicle to be detected is obtained to be damaged and the dominant detection result of the front framework is obtained to be non-damaged, the probability that the A column in the vehicle to be detected is damaged is 0.4 according to a preset paradigm; if the dominant detection result of the B column in the vehicle to be detected is obtained to be a damaged state and the dominant detection result of the front framework is obtained to be a damaged state, the probability that the A column in the vehicle to be detected is damaged is 0.4 according to a preset paradigm; if the dominant detection result of the B column in the vehicle to be detected is not damaged and the dominant detection result of the front framework is damaged, the probability that the A column in the vehicle to be detected is damaged is 0.3 according to a preset paradigm; and if the obtained explicit detection result of the B column in the vehicle to be detected is not damaged and the explicit detection result of the front framework is not damaged, the probability that the A column in the vehicle to be detected is damaged is 0 according to a preset paradigm.
Further, after the detection result of each target detection point in the vehicle to be detected is generated, the vehicle detection method further comprises the following steps: and displaying a reminding mark at the position of the target detection point with damage in the image of the vehicle to be detected. The reminding mark can be set at will, for example, a highlight mark, a flashing mark, a color mark and the like can be set.
According to the vehicle detection method provided by the embodiment of the invention, the detection result of the recessive detection point serving as the target detection point in the vehicle to be detected is determined according to the real and effective detection result of the known vehicle and the dominant detection result of the dominant detection point in the vehicle to be detected, and when the recessive detection point is subjected to unobvious damage, the damage condition can be accurately detected, so that the risk of omitting the unobvious damaged part is avoided, the detection accuracy is greatly improved, and the applicability is better.
Corresponding to the vehicle detection method, the invention also provides a vehicle detection device.
Referring to fig. 3, fig. 3 is a block diagram illustrating a structure of a vehicle detecting device according to an embodiment of the present invention. As can be seen from fig. 3, the vehicle detection device includes: an explicit detection
result obtaining module301, configured to obtain an explicit detection result of an explicit detection point in a vehicle to be detected according to an image of the vehicle to be detected; a historical detection
result obtaining module302, configured to obtain a historical detection result obtained by associating the explicit detection point with a target detection point in a known vehicle; and a target detection
result generation module303, configured to generate a detection result of a target detection point in the vehicle to be detected according to the explicit detection result and the historical detection result.
Further, the historical detection
result obtaining module302 is specifically configured to: and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise the classification probability of each dominant detection point, the classification probability of the target detection point and the conditional probability of each dominant detection point and the target detection point.
Further, the target detection
result generating module303 is specifically configured to: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a naive Bayesian algorithm according to the dominant detection result and the historical detection result corresponding to each target detection point.
Further, the historical detection
result obtaining module302 is specifically configured to: and acquiring a historical detection result associated with each target detection point and the dominant detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each dominant detection point in the known vehicle influences the detection result of the target detection point.
Further, the target detection
result generating module303 is specifically configured to: and calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point.
Further, the vehicle detection device further includes: and the
display reminding module304 is used for displaying a reminding mark at the position of the target detection point with the damaged detection result in the image of the vehicle to be detected.
By adopting the vehicle detection device provided by the embodiment of the invention, each step in the vehicle detection method can be implemented, the detection result of the target detection point in the vehicle to be detected is generated, namely the detection result of the hidden detection point is generated, when the hidden detection point is subjected to unobvious damage, the damage condition can be accurately detected, the risk of omitting the unobvious damaged part is avoided, the detection accuracy is greatly improved, and the applicability is better.
In specific implementation, the invention further provides a computer storage medium, wherein the computer storage medium may store a program, and the program may include some or all of the steps in the embodiments of the vehicle detection method provided by the invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a Random Access Memory (RAM).
Those skilled in the art will readily appreciate that the techniques of the embodiments of the present invention may be implemented as software plus a required general purpose hardware platform. Based on such understanding, the technical solutions in the embodiments of the present invention may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The same and similar parts in the various embodiments in this specification may be referred to each other. In particular, as for the embodiment of the vehicle detection device, since it is basically similar to the embodiment of the method, the description is simple, and the relevant points can be referred to the description of the embodiment of the method.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention.
Claims (4)
1. A vehicle detection method, characterized by comprising:
acquiring an explicit detection result of an explicit detection point in the vehicle to be detected according to the image of the vehicle to be detected;
the image is a three-dimensional image for observing each part of the surface of the vehicle to be detected, the image comprises a plurality of detection points divided by parts, and the detection points comprise dominant detection points and target detection points;
the dominant detection point refers to a detection point which can be directly obtained by a common technician for vehicle detection through visual observation in a vehicle to be detected;
acquiring a historical detection result associated with each target detection point and an explicit detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each explicit detection point in the known vehicle influences the detection result of the target detection point;
calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point; the preset normal form is set to be a maximum value;
and displaying a reminding mark at the position of the target detection point with damage in the image of the vehicle to be detected.
2. The vehicle detection method according to claim 1, wherein the process of obtaining historical detection results associated with the dominant detection point and the target detection point in the known vehicle specifically includes:
and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise classification probability of each dominant detection point, classification probability of the target detection point and conditional probability of each dominant detection point and the target detection point.
3. A vehicle detecting apparatus, characterized by comprising:
the dominant detection result acquisition module is used for acquiring a dominant detection result of a dominant detection point in the vehicle to be detected according to the image of the vehicle to be detected;
the image is a three-dimensional image for observing each part of the surface of the vehicle to be detected, the image comprises a plurality of detection points divided by parts, and the detection points consist of dominant detection points and target detection points;
the dominant detection point refers to a detection point which can be directly obtained by a common technician for vehicle detection through visual observation in a vehicle to be detected;
the historical detection result acquisition module is used for acquiring a historical detection result associated with each target detection point and an explicit detection point in the known vehicle, wherein the historical detection result is the probability that the detection result of each explicit detection point in the known vehicle influences the detection result of the target detection point;
the target detection result generation module is used for calculating the detection result of the target detection point in the vehicle to be detected by adopting a preset paradigm according to the explicit detection result and the historical detection result corresponding to each target detection point; the preset normal form is set to be a maximum value;
and the display reminding module is used for displaying a reminding mark at the position of the target detection point with a damaged detection result in the image of the vehicle to be detected.
4. The vehicle detection apparatus of claim 3, wherein the historical detection result acquisition module is specifically configured to:
and calling historical detection results of each target detection point and two dominant detection points associated with the target detection point from stored historical detection data of the known vehicle, wherein the historical detection results comprise classification probability of each dominant detection point, classification probability of the target detection point and conditional probability of each dominant detection point and the target detection point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710261393.5A CN108765362B (en) | 2017-04-20 | 2017-04-20 | Vehicle detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710261393.5A CN108765362B (en) | 2017-04-20 | 2017-04-20 | Vehicle detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108765362A CN108765362A (en) | 2018-11-06 |
| CN108765362B true CN108765362B (en) | 2023-04-11 |
Family
ID=63980019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710261393.5A Active CN108765362B (en) | 2017-04-20 | 2017-04-20 | Vehicle detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765362B (en) |
Families Citing this family (2)
* Cited by examiner, † Cited by third party| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334611A (en) * | 2019-06-18 | 2019-10-15 | 中国平安财产保险股份有限公司 | Component detection method and device, server, storage medium |
| CN114500038B (en) * | 2022-01-24 | 2024-12-03 | 深信服科技股份有限公司 | Network security detection method, device, electronic device and readable storage medium |
Citations (3)
* Cited by examiner, † Cited by third party| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001066977A1 (en) * | 2000-03-10 | 2001-09-13 | Tcm Corporation | Drivingly traveling device for industrial vehicle and brake device of the drivingly traveling device |
| JP2013161434A (en) * | 2012-02-08 | 2013-08-19 | Toyota Motor Corp | Periphery monitoring device for vehicle |
| CN104240505A (en) * | 2014-09-11 | 2014-12-24 | 胡又宏 | Method for analyzing road traffic video image information |
Family Cites Families (2)
* Cited by examiner, † Cited by third party| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6303090B2 (en) * | 2014-03-24 | 2018-04-04 | アルパイン株式会社 | Image processing apparatus and image processing program |
| WO2015184619A1 (en) * | 2014-06-05 | 2015-12-10 | 深圳市推想大数据信息技术有限公司 | Method and apparatus for estimating recessive character distribution of users |
-
2017
- 2017-04-20 CN CN201710261393.5A patent/CN108765362B/en active Active
Patent Citations (3)
* Cited by examiner, † Cited by third party| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001066977A1 (en) * | 2000-03-10 | 2001-09-13 | Tcm Corporation | Drivingly traveling device for industrial vehicle and brake device of the drivingly traveling device |
| JP2013161434A (en) * | 2012-02-08 | 2013-08-19 | Toyota Motor Corp | Periphery monitoring device for vehicle |
| CN104240505A (en) * | 2014-09-11 | 2014-12-24 | 胡又宏 | Method for analyzing road traffic video image information |
Non-Patent Citations (1)
* Cited by examiner, † Cited by third party| Title |
|---|
| K.A. Hogda etal..High-resolution satellite images for detecting vegetation damage caused by terrain vehicles in northern Norway.《2004 IEEE International Geoscience and Remote Sensing Symposium》.2004,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108765362A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10013757B2 (en) | 2018-07-03 | Classification apparatus for pathologic diagnosis of medical image, and pathologic diagnosis system using the same |
| US6275559B1 (en) | 2001-08-14 | Method and system for diagnosing faults in imaging scanners |
| Chard et al. | 2010 | Reducing the impact of white matter lesions on automated measures of brain gray and white matter volumes |
| US9286547B2 (en) | 2016-03-15 | Quality control and assurance of images |
| EP3489898A1 (en) | 2019-05-29 | Method and apparatus for estimating disparity |
| CN116664551B (en) | 2023-10-31 | Display screen detection method, device, equipment and storage medium based on machine vision |
| WO2013018814A1 (en) | 2013-02-07 | Ophthalmic diagnosis support apparatus and ophthalmic diagnosis support method |
| US20230049804A1 (en) | 2023-02-16 | Crack estimation device, failure diagnosis device, crack estimation method, and failure diagnosis method for rotating machine |
| WO2019111339A1 (en) | 2019-06-13 | Learning device, inspection system, learning method, inspection method, and program |
| WO2013177189A1 (en) | 2013-11-28 | Predictive modeling relating molecular imaging modalities |
| CN108765362B (en) | 2023-04-11 | Vehicle detection method and device |
| DE102015220884A1 (en) | 2016-04-28 | Image processing device |
| US20190285710A1 (en) | 2019-09-19 | Mpi method and system for visually representing mpi image data |
| CN110017998A (en) | 2019-07-16 | Vehicle checking method, device and equipment |
| CN112183555A (en) | 2021-01-05 | Method and system for detecting welding quality, electronic device and storage medium |
| CN112365489A (en) | 2021-02-12 | Ultrasonic image blood vessel bifurcation detection method |
| TWI223214B (en) | 2004-11-01 | A method for relating images in an image processing system |
| Martin et al. | 2017 | Characterization of identification errors and uses in localization of poor modal correlation |
| US8306311B2 (en) | 2012-11-06 | Method and system for automated ball-grid array void quantification |
| JP7600909B2 (en) | 2024-12-17 | Anomaly detection system and anomaly detection method |
| CN113516386B (en) | 2022-03-15 | Parking space detection performance evaluation method and device, electronic equipment and storage medium |
| CN106910163B (en) | 2022-06-21 | Data restoration device and method for original CT projection data and CT imaging system |
| CN113537407A (en) | 2021-10-22 | Image data evaluation processing method and device based on machine learning |
| Lakshmanan et al. | 2013 | Affine based image registration applied to MRI brain |
| US20160231261A1 (en) | 2016-08-11 | Induction Thermography Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 2018-11-06 | PB01 | Publication | |
| 2018-11-06 | PB01 | Publication | |
| 2018-11-30 | SE01 | Entry into force of request for substantive examination | |
| 2018-11-30 | SE01 | Entry into force of request for substantive examination | |
| 2020-04-28 | EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20181106 Assignee: Beijing May 8th clapping Information Technology Co.,Ltd. Assignor: YOUXIN SHUXIANG (BEIJING) INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2020990000156 Denomination of invention: Detecting method and device for vehicle License type: Common License Record date: 20200402 |
| 2020-04-28 | EE01 | Entry into force of recordation of patent licensing contract | |
| 2023-04-11 | GR01 | Patent grant | |
| 2023-04-11 | GR01 | Patent grant |