CN112434368A - Image acquisition method, device and storage medium - Google Patents
Image acquisition method, device and storage medium Download PDFInfo
- Publication number
- CN112434368A CN112434368A CN202011122659.6A CN202011122659A CN112434368A CN 112434368 A CN112434368 A CN 112434368A CN 202011122659 A CN202011122659 A CN 202011122659A CN 112434368 A CN112434368 A CN 112434368A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- accident
- dimensional
- model
- image
- Prior art date
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 206010039203 Road traffic accident Diseases 0.000 claims abstract description 81
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000003190 augmentative effect Effects 0.000 claims description 6
- 238000012797 qualification Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
Abstract
The embodiment of the invention discloses an image acquisition method, an image acquisition device and a storage medium, wherein the method comprises the following steps: firstly, acquiring a scene image of a traffic accident; determining the accident type and constructing or associating a three-dimensional vehicle model of the accident vehicle according to the field image and/or the user input; and then, acquiring a three-dimensional virtual vehicle contour map according to the accident type and the associated three-dimensional vehicle model, and displaying the virtual vehicle contour map so as to guide a user to take a picture according to the virtual vehicle contour map and acquire a evidence obtaining result consistent with the virtual vehicle contour map. Because the virtual vehicle profile map that obtains according to accident type and three-dimensional vehicle model is three-dimensional, can laminate the outward appearance of accident vehicle more accurately, the guide to the user angle of shooing is also more accurate, and the qualification rate of the result of collecting evidence like this is higher, and the suitability is better. On the other hand, the user also finds the suitable shooting angle more easily, and the success rate of shooting the picture is higher, has also promoted user's use experience.
Description
Technical Field
The present invention relates to the field of image acquisition, and in particular, to an image acquisition method, an image acquisition apparatus, and a storage medium.
Background
With the rapid development of economy in recent decades, automobiles have become one of the most common transportation means for people to go out, but at the same time, the number of traffic accidents is increased. The accidents of collision or scratch on the road are not rare, and traffic jam paralysis caused by untimely handling of the traffic accidents also happens occasionally. Therefore, the traffic management department has a policy to encourage the accident parties to obtain evidence and negotiate and solve the accident by themselves so as to accelerate the processing of the traffic accident.
However, when the two parties of the accident perform self-evidence collection, the experience of handling the traffic accident is insufficient and the shooting level is limited, so that the angle and the position of the shooting target vehicle are deviated, the evidence collection result is not ideal, and the attribution of accident responsibility cannot be clearly judged, thereby causing unnecessary disputes.
Although some urban road traffic accident collecting and analyzing tools based on mobile phone application are available at present, the functions of the tools are limited to simple photographing guidance and photo verification for users by using a planar image processing technology. Under the circumstance, due to the limitation of the plane image processing technology, the guidance is often not accurate enough, so that a user needs to repeatedly try and take pictures for many times to obtain photos meeting the requirements, the use is complicated, and the further popularization and application are difficult to obtain.
Therefore, how to overcome the defects of the existing scheme and accurately guide the user to carry out on-site evidence collection of the traffic accident still remains a technical problem to be solved in the intelligent traffic management application.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide an image capturing method and apparatus, and a storage medium.
According to a first aspect of an embodiment of the present invention, an image acquisition method is applied to forensics of a traffic accident scene, and the method includes: collecting a scene image of a traffic accident; determining an accident type according to the live image and/or user input; acquiring a three-dimensional vehicle model of an accident vehicle of the traffic accident according to the scene image; acquiring a three-dimensional virtual vehicle contour map according to the accident type and the three-dimensional vehicle model of the accident vehicle; displaying the virtual vehicle outline so as to guide a user to take a picture according to the virtual vehicle outline; and obtaining a evidence obtaining result consistent with the virtual vehicle contour map.
According to an embodiment of the present invention, determining the accident type according to the live image and/or the user input includes: identifying the traffic accident type according to the field image to obtain a pre-judged accident type; and displaying the pre-judged accident type for the user to confirm, if the user confirms, determining the pre-judged accident type as the accident type, if the user denies, displaying all the accident types for the user to select, and determining the accident type according to the user selection.
According to an embodiment of the present invention, identifying a traffic accident type according to a scene image to obtain a pre-determined accident type includes: constructing a three-dimensional field model according to the field image; extracting accident characteristics of the traffic accident from the three-dimensional field model by utilizing an Augmented Reality (AR) identification technology; and identifying the traffic accident type according to the accident characteristics to obtain a pre-judged accident type.
According to an embodiment of the present invention, a three-dimensional vehicle model of an accident vehicle of a traffic accident is obtained from a live image, including: vehicle identification is carried out according to the scene image to obtain the brand and the model of an accident vehicle of the traffic accident; and acquiring a three-dimensional vehicle model corresponding to the brand and the model from a pre-established three-dimensional vehicle model database according to the brand and the model of the accident vehicle.
According to an embodiment of the present invention, the method further includes: and if the three-dimensional vehicle model corresponding to the brand and the model does not exist in the pre-established three-dimensional vehicle model database, reconstructing the three-dimensional model to obtain the three-dimensional vehicle model of the accident vehicle of the traffic accident.
According to one embodiment of the present invention, the three-dimensional vehicle model of the accident vehicle is obtained by dividing the size of the accident vehicle into 1: 1, and (b).
According to one embodiment of the present invention, obtaining a forensics result consistent with a virtual vehicle contour map comprises: when the image of the accident vehicle is superposed with the virtual vehicle outline map, automatic photographing is carried out to obtain a evidence obtaining result consistent with the virtual vehicle outline map.
According to an embodiment of the present invention, the method further includes: and when the image of the accident vehicle is not overlapped with the virtual vehicle outline drawing, giving a user operation prompt.
According to an embodiment of the present invention, after obtaining the evidence result that is coincident with the virtual vehicle contour map, the method further comprises: and determining the damaged position of the accident vehicle caused by the traffic accident according to the evidence obtaining result.
According to an embodiment of the present invention, the forensic result includes a forensic result in a three-dimensional image format.
According to an embodiment of the present invention, after obtaining the evidence result that is coincident with the virtual vehicle contour map, the method further comprises: calculating the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road according to the evidence obtaining result; and adding the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road to the evidence obtaining result.
According to a second aspect of the embodiments of the present invention, an apparatus for image acquisition, the apparatus comprising: the image acquisition module is used for acquiring a scene image of a traffic accident; the accident type determining module is used for determining the accident type according to the field image and/or the user input; the three-dimensional vehicle model acquisition module is used for acquiring a three-dimensional vehicle model of an accident vehicle of the traffic accident according to the scene image; the vehicle contour map acquisition module is used for acquiring a three-dimensional virtual vehicle contour map according to the accident type and the three-dimensional vehicle model of the accident vehicle; the vehicle outline map display module is used for displaying the virtual vehicle outline map so as to guide a user to take a picture according to the virtual vehicle outline map; and the evidence obtaining module is used for obtaining evidence obtaining results consistent with the virtual vehicle contour map.
According to an embodiment of the present invention, an accident type determining module includes: the pre-judged accident type obtaining submodule is used for identifying the traffic accident type according to the field image to obtain the pre-judged accident type; and the accident type determining submodule is used for displaying the pre-judged accident type for the user to confirm, determining the pre-judged accident type as the accident type if the user confirms, displaying all the accident types for the user to select if the user denies, and determining the accident type according to the user selection.
According to an embodiment of the present invention, the pre-determined accident type obtaining sub-module includes: the three-dimensional field model building unit is used for building a three-dimensional field model according to the field image; the accident feature extraction unit is used for extracting accident features of the traffic accident from the three-dimensional field model by utilizing an AR (augmented reality) identification technology; and the pre-judging accident type obtaining unit is used for identifying the traffic accident type according to the accident characteristics to obtain the pre-judging accident type.
According to one embodiment of the present invention, a three-dimensional vehicle model obtaining module includes: the brand and model acquisition submodule is used for carrying out vehicle identification according to the field image to obtain the brand and model of an accident vehicle of the traffic accident; and the three-dimensional vehicle model acquisition submodule is used for acquiring a three-dimensional vehicle model corresponding to the brand and the model from a pre-established three-dimensional vehicle model database according to the brand and the model of the accident vehicle.
According to an embodiment of the present invention, the three-dimensional vehicle model obtaining module further includes: and the three-dimensional vehicle model reconstruction submodule is used for reconstructing a three-dimensional model to obtain a three-dimensional vehicle model of the accident vehicle of the traffic accident if the three-dimensional vehicle model corresponding to the brand and the model does not exist in the pre-established three-dimensional vehicle model database.
According to an embodiment of the present invention, the three-dimensional vehicle model reconstruction submodule is specifically configured to, according to a size ratio 1 of the accident vehicle: 1, constructing a three-dimensional vehicle model of the accident vehicle.
According to an embodiment of the present invention, the forensics result obtaining module includes: and the automatic photographing sub-module is used for automatically photographing to obtain a evidence obtaining result consistent with the virtual vehicle outline map when the image of the accident vehicle is superposed with the virtual vehicle outline map.
According to an embodiment of the present invention, the forensics result obtaining module further includes: and the user operation prompting submodule is used for giving a user operation prompt when the image of the accident vehicle is not coincident with the virtual vehicle outline drawing.
According to an embodiment of the present invention, the apparatus further includes: and the vehicle damaged position determining module is used for determining the damaged position of the accident vehicle caused by the traffic accident according to the evidence obtaining result.
According to an embodiment of the present invention, the apparatus further includes: the calculation module is used for calculating the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road according to the evidence obtaining result; and the additional information adding module is used for adding the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road on the evidence obtaining result.
According to a third aspect of embodiments of the present invention, a storage medium has stored thereon program instructions for executing the above-mentioned image acquisition method when executed.
The embodiment of the invention provides an image acquisition method, an image acquisition device and a storage medium, wherein the method comprises the following steps: firstly, acquiring a scene image of a traffic accident; determining the accident type and constructing or associating a three-dimensional vehicle model of the accident vehicle according to the field image and/or the user input; and then, acquiring a three-dimensional virtual vehicle contour map according to the accident type and the associated three-dimensional vehicle model, and displaying the virtual vehicle contour map so as to guide a user to take a picture according to the virtual vehicle contour map and acquire a evidence obtaining result consistent with the virtual vehicle contour map. Because the virtual vehicle profile map that obtains according to accident type and three-dimensional vehicle model is three-dimensional, can laminate the outward appearance of accident vehicle more accurately, the guide to the user angle of shooing is also more accurate, and the qualification rate of the result of collecting evidence like this is higher, and the suitability is better. On the other hand, the user also finds the suitable shooting angle more easily, and the success rate of shooting the picture is higher, has also further promoted user's use and has experienced.
It is to be understood that the present invention need not achieve all of the above-described advantages, but that certain embodiments may achieve certain technical effects, and that other embodiments of the present invention may achieve other advantages not mentioned above.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a schematic flow chart illustrating an implementation of an image acquisition method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an implementation process for determining evidence-taking emphasis by analyzing accident types according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a comparison between a contour map of a virtual vehicle and a real image of an accident vehicle according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a specific implementation of generating a three-dimensional vehicle model according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an image capturing device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
According to a first aspect of an embodiment of the present invention, an image capturing method is applied to forensics of a traffic accident scene, as shown in fig. 1, the method includes: operation 110, collecting a scene image of a traffic accident; an operation 120 of determining an accident type based on the live image and/or user input; an operation 130 of acquiring a three-dimensional vehicle model of an accident vehicle of the traffic accident from the live image; an operation 140 of obtaining a three-dimensional virtual vehicle contour map according to the accident type and the three-dimensional vehicle model of the accident vehicle; an operation 150 of displaying the virtual vehicle contour map to guide the user to take a photograph according to the virtual vehicle contour map; at operation 160, a forensics result is obtained that is consistent with the virtual vehicle profile.
In operation 110, the device for collecting the live image of the traffic accident includes a mobile terminal device such as a mobile phone, a tablet computer, and AR glasses. In order to ensure that the quality of the shot image can meet the evidence obtaining requirement, the hardware of the acquisition equipment can be detected before the image is acquired, for example, the detection of the use authority and the detection of the resolution of a camera are carried out.
In operation 120, the accident type mainly refers to a type classified according to an accident occurrence scenario, a vehicle collision location, and a damage degree, for example: rear-end collision/car backing, overtaking/parallel line rubbing, crossroad accidents, up-down slope accidents, emergency obstacle avoidance, retrograde motion and other accidents. Different traffic accident types have different requirements on the evidence obtaining range and the shooting angle. Fig. 2 shows some examples of different requirements of the application of the embodiment of the present invention on the evidence-taking emphasis for different accident types. For example, if the accident type is "rear-end/reverse rolling", the first forensic emphasis is to capture an image of the "45 ° front" of the accident vehicle, and the second forensic emphasis is to capture an image of the "45 ° rear" of the accident vehicle.
Therefore, prior to forensics, the type of traffic accident is first determined. Therefore, the evidence obtaining range and the shooting angle can be accurately determined, and the user is guided to obtain evidence in a more targeted manner.
The determination of the traffic accident type can be automatically identified according to the site image, can be actively input by the user, and can be combined with the site image, the site image is automatically identified to give a prejudgment result, and the traffic accident type is finally determined through the user confirmation.
The traffic accident type is automatically identified according to the field image, the traffic accident type is mainly identified through an artificial intelligent image identification technology and a classification algorithm, and an implementer can adopt any suitable implementation method and implementation mode according to implementation conditions.
In operation 130, the three-dimensional vehicle model mainly refers to a three-dimensional representation suitable for computer processing, which is obtained by acquiring information such as a geometric structure and a shape feature of the accident vehicle according to the scene image and reconstructing the three-dimensional model for the accident vehicle. It should be noted that, the three-dimensional vehicle model is an accurate model of the traffic accident vehicle, and therefore, the three-dimensional vehicle model is more closely attached to the appearance of the traffic accident vehicle, so that more accurate guidance can be performed when the user is guided to take a picture.
In operation 140, a three-dimensional virtual vehicle contour map is obtained by determining a forensic range according to the accident type, and an optimal position and angle of the accident vehicle in the finder frame at the time of forensic, and then assigning the optimal position and angle to the three-dimensional vehicle model so that the three-dimensional vehicle model is displayed at the set position and angle. An outline view of a virtual vehicle as shown in phantom in fig. 3, as shown in an application of an embodiment of the present invention. The outline map is the position and angle of the vehicle that the user can use to reference when taking a picture. It should be noted that the outline shown by the dotted line in fig. 3 is only an effect diagram, and in practical applications, the outline of the virtual vehicle will be more detailed and clear.
When the evidence obtaining range is determined according to the accident type and the optimal position and angle of the accident vehicle in the view-finding frame during evidence obtaining, the evidence obtaining key points and the evidence obtaining range corresponding to the accident type and the optimal position and angle of the accident vehicle in the view-finding frame during evidence obtaining of each evidence obtaining key point can be inquired and obtained from a pre-established database. The database is generally established according to the evidence obtaining requirements, the field knowledge related to traffic management and automobile manufacturing and expert experience in the traffic accident handling related regulations, and stores the related information such as the vehicle position and angle which are more suitable when different traffic accidents are obtained. The relevant information such as the vehicle position and the angle can be the key points of the evidence obtaining and other evidence obtaining shown in fig. 2.
In general, it is easier to calculate detailed information such as a distance between accident vehicles, a braking speed, a braking distance, and a damage situation by using a result of forensics obtained by photographing at the photographing position and angle stored in the database. And the information is very helpful for processing responsibility and identifying disputes and settlement disputes.
Because the outline of the virtual vehicle is obtained based on the three-dimensional vehicle model of the accident vehicle and is highly attached to the image of the real accident vehicle entering the viewing frame during actual shooting, as shown in fig. 3(b), the outline of the virtual vehicle shown by the dotted line can be basically overlapped with the outline of the real accident vehicle shown by the solid line, so that the shooting guidance is more accurate.
In operation 150, the virtual vehicle contour map is typically displayed in a display screen of the viewfinder content, for example, a cell phone screen. The user can see the objects and the virtual vehicle outline map in the shooting view range from the display screen at the same time, so that the shot accident vehicle outline can be superposed with the virtual vehicle outline by changing the shooting distance and the shooting angle, and the aim of accurate guidance is fulfilled.
For example, in the case shown in fig. 3(a), when the contour of the accident vehicle in the finder frame shown by the solid line deviates from the virtual vehicle contour shown by the broken line, the user can be prompted to further change the photographing distance and the photographing angle; when the user changes the shooting distance and the shooting angle to the situation shown in fig. 3(b), that is, the contour of the accident vehicle in the viewing frame shown by the solid line substantially coincides with the contour of the virtual vehicle shown by the dotted line, the user can be prompted to take a picture to obtain evidence or the system can automatically take a picture to obtain evidence.
In operation 160, the captured emergency vehicle contour substantially coincides with the virtual vehicle contour in accordance with the virtual vehicle contour map, thereby obtaining an emergency vehicle image with determined position and angle.
As is well known, the process of forensics is often not completed by taking a picture at one time, and multiple angles and positions are required for taking pictures. Therefore, the process of giving the virtual vehicle profile to guide the user to take a photograph is also repeated as necessary.
For example, fig. 2 shows a specific process of performing forensics by an application according to an embodiment of the present invention. As shown in fig. 2, after analyzing the accident type, a first forensics point (e.g., "front 45 ° angle") may be obtained according to a specific accident type (e.g., "rear-end/reverse rolling"), at which a virtual vehicle profile may be generated to guide the user to perform (front 45 ° angle) photographing to obtain a first forensics result; after the first forensic point is captured, the second forensic point (e.g., "rear 45 ° angle") may be captured, and a new virtual vehicle contour may be generated to guide the user to capture the second forensic result, and so on, until all the first forensic points are processed.
In the embodiment of the present invention, the forensics result includes not only the above-mentioned image of the accident vehicle, but also other information that is acquired during the shooting process and plays a key role in forensics and responsibility determination, such as: license plate number, vehicle spacing, vehicle location in the road, vehicle damage location, weather and road conditions, time of evidence collection, and the like.
Typically, the forensics results are automatically saved in the user's collection device. In some application scenarios, the user may be required to actively send the forensics result to the cloud server or automatically send the forensics result to the cloud server for the third party to check according to needs. When the evidence is sent to the cloud server, the evidence obtaining result can be associated with the vehicle information or the driver information, so that a third party can obtain the corresponding evidence obtaining result according to the vehicle information or the driver information when checking.
In conclusion, the virtual vehicle contour map obtained according to the accident type and the three-dimensional vehicle model can be attached to the appearance of the accident vehicle more accurately, the guiding of the shooting angle of the user is more accurate, the qualification rate of the collected evidence obtaining result is higher, and the applicability is better. On the other hand, the user also finds the suitable shooting angle more easily, and the success rate of shooting the picture is higher, has also further promoted user's use and has experienced.
According to an embodiment of the present invention, determining the accident type according to the live image and/or the user input includes: identifying the traffic accident type according to the field image to obtain a pre-judged accident type; and displaying the pre-judged accident type for the user to confirm, if the user confirms, determining the pre-judged accident type as the accident type, if the user denies, displaying all the accident types for the user to select, and determining the accident type according to the user selection.
In the embodiment, the traffic accident type is firstly identified through the site image to obtain the pre-judged accident type, so that the time for a user to search the traffic accident type can be saved, the operation is more convenient, and the user experience is better. In order to avoid the deviation caused by inaccurate identification of the traffic accident type, the verification is further carried out in a confirmation mode, and if the identification is wrong, the user can also select the proper traffic accident type by himself, so that the convenience of operation and the accuracy of the identification result of the traffic accident type are both considered.
According to an embodiment of the present invention, identifying a traffic accident type according to a scene image to obtain a pre-determined accident type includes: constructing a three-dimensional field model according to the field image; extracting accident characteristics of the traffic accident from the three-dimensional field model by utilizing an AR (augmented reality) identification technology; and identifying the traffic accident type according to the accident characteristics to obtain a pre-judged accident type.
The method comprises the steps of constructing a three-dimensional field model according to a field image, performing three-dimensional reconstruction on accident vehicles and key reference objects in the field image, such as roads, traffic signs, barriers, traffic lights and the like, and further acquiring accurate information such as three-dimensional structures, positions, distances and the like.
Wherein, utilizing AR recognition technology to extract traffic accident characteristics includes: and (3) extracting the characteristics and the similarity of the accident vehicle and the key reference object in the three-dimensional field model in the aspects of shape, structure, statistics, texture, environment, height, size and the like, the position relation of the accident vehicle and the key reference object and the like by utilizing an AR (augmented reality) identification technology. Through the extraction of the features, the type of the traffic accident can be more fully analyzed, and a more accurate accident type analysis result is obtained to serve as the accident type to be judged in advance.
According to an embodiment of the present invention, a three-dimensional vehicle model of an accident vehicle of a traffic accident is obtained from a live image, including: vehicle identification is carried out according to the scene image to obtain the brand and the model of an accident vehicle of the traffic accident; and acquiring a three-dimensional vehicle model corresponding to the brand and the model from a pre-established three-dimensional vehicle model database according to the brand and the model of the accident vehicle.
The vehicle identification from the live images includes: the vehicle exists as a three-dimensional object of the real world, and the brand and the model of the vehicle are identified according to the analysis of the similarity by reconstructing a three-dimensional model of the vehicle.
The similarity (image similarity) of the object images related to the object images is recognized, including the similarity in terms of shape, structure, statistics, texture, environment, height, size, and the like. In addition, the computer can be used for analyzing the spatial information and the spectral information of different objects in the object image, selecting the characteristics, dividing the characteristic space into subspaces which do not overlap with each other, and classifying each pixel in the object image into the subspaces.
Preferably, the information stored in the three-dimensional vehicle model database further includes the composition of contour outline, color and size of the individual vehicle. Therefore, the computer can be used for deeply learning the modular feature points, and the combination of all parts is identified by a classification method, so that a more accurate vehicle identification result is finally obtained.
Preferably, the information stored in the three-dimensional vehicle model database further includes the make-up of various components of the vehicle. In this manner, automatic identification of vehicles and components can be performed by mathematical methods and computer techniques, such as image processing and computer vision.
Since vehicles of the same make and model are substantially identical in appearance shape and size, the same three-dimensional vehicle model can be shared without repeated modeling. Therefore, by establishing the three-dimensional vehicle model database corresponding to the brand and the model of the vehicle in advance and acquiring the three-dimensional vehicle model from the database when obtaining evidence, the repeated modeling process can be omitted, the resource and time cost can be greatly reduced, and the speed of acquiring the three-dimensional vehicle model is higher.
According to an embodiment of the present invention, the method further includes: and if the three-dimensional vehicle model corresponding to the brand and the model does not exist in the pre-established three-dimensional vehicle model database, reconstructing the three-dimensional model to obtain the three-dimensional vehicle model of the accident vehicle of the traffic accident.
Since a vehicle manufacturer releases a new product or information recorded in a database before is not complete, a three-dimensional vehicle model corresponding to a brand and a model may not be found in a pre-established three-dimensional vehicle model database. At this time, three-dimensional reconstruction can still be performed according to the picture taken by the user, and a new vehicle model is generated and stored in the database. Therefore, even if the user cannot find the corresponding vehicle model when shooting for the first time, the established three-dimensional vehicle model can be directly used without reconstruction when obtaining evidence again.
Any suitable implementation method and implementation mode may be used when performing three-dimensional reconstruction according to a picture taken by a user, which is not limited in this embodiment of the present invention.
Fig. 4 shows a three-dimensional reconstruction process applied in a specific embodiment of the present invention, which mainly includes:
4030, extracting the feature points of the accident vehicle;
4040, performing concentric multi-angle splicing to obtain a 3D data file;
and 4070, rendering the adjusted 3D data file to obtain a three-dimensional vehicle model.
During modeling, any one of a 3D model reconstruction algorithm based on a Boosting architecture and Haar characteristics, a 3D model reconstruction algorithm based on machine learning-deep learning, a 3D model reconstruction algorithm based on machine learning-SVM or Bayes learning, a 3D model reconstruction algorithm based on geometric shape analysis and a vehicle characteristic point model reconstruction algorithm based on texture can be used.
When the point cloud is manually edited, the 3D model can be displayed, and point cloud data in the model can be visually edited. And editing the point cloud comprises: selecting a part of point cloud; deleting the point cloud; canceling the previous operation, and restoring to the state of any one step before the operation.
In the embodiment, because the three-dimensional vehicle model database can be enriched continuously according to the images provided by the user, correspondingly, the probability that the user cannot find the corresponding model is smaller and smaller, and the use experience of the user is further improved continuously.
According to one embodiment of the present invention, the three-dimensional vehicle model of the accident vehicle is obtained by dividing the size of the accident vehicle into 1: 1, and (b).
In the present embodiment, a size ratio of 1: the method has the advantages that 1, the three-dimensional vehicle model is built, the accident scene can be restored more truly, more tiny detailed characteristics such as structural characteristics of tiny components such as rearview mirrors and exhaust pipes and damage caused by traffic accidents can be captured more easily, in addition, when the information such as the area of a damaged position and the distance between vehicles is calculated in an auxiliary mode, extra proportion conversion is not needed, calculation resources are saved, calculation complexity is simplified, and processing time is shortened.
According to one embodiment of the present invention, obtaining a forensics result consistent with a virtual vehicle contour map comprises: when the image of the accident vehicle is superposed with the virtual vehicle outline map, automatic photographing is carried out to obtain a evidence obtaining result consistent with the virtual vehicle outline map.
In the embodiment, when the image of the accident vehicle is overlapped with the virtual vehicle outline map, a user does not need to manually shoot, and the shooting command or the program interface of the acquisition equipment can be used for realizing automatic shooting, so that the operation is more convenient and faster, and the use experience is better.
According to an embodiment of the present invention, the method further includes: and when the image of the accident vehicle is not overlapped with the virtual vehicle outline drawing, giving a user operation prompt.
The operation prompt here is a prompt message for guiding the user to change the shooting distance and angle so that the image of the accident vehicle and the virtual vehicle contour map coincide with each other as soon as possible, and further shortening the time for obtaining evidence, and for example, the rotation direction of the shooting angle may be indicated by up, down, left, and right arrows, and the adjustment of the shooting distance forward or backward may be indicated by a front-stretched arrow or a candidate-stretched arrow. This action prompt may also be in voice or text form.
According to an embodiment of the present invention, after obtaining the evidence result that is coincident with the virtual vehicle contour map, the method further comprises: and determining the damaged position of the accident vehicle caused by the traffic accident according to the evidence obtaining result.
In the embodiment, not only can some photos reflecting the basic conditions of the traffic accident, such as the direct position relationship of the accident vehicle, the position relationship between the vehicle and the road reference object, and the like be shot, but also the analysis and comparison of the shape, the structure, the texture, and the like can be further carried out according to the shot photos, the position of the damaged automobile is determined, then the damage which is irrelevant to the accident is further eliminated according to the accident type and the position relationship of the accident vehicle, so that the damage which is directly relevant to the accident is obtained, and more accurate information is provided for accident claim settlement.
According to an embodiment of the present invention, the forensic result includes a forensic result in a three-dimensional image format.
Since the forensics process of the embodiment of the invention is carried out based on the three-dimensional vehicle model, the forensics result in the three-dimensional image format can be easily generated on the basis of the three-dimensional vehicle model, so that scene reappearance can be carried out when necessary, or more accurate evidence information which cannot be provided by some two-dimensional images can be provided, such as the distance between vehicles, the distance between the vehicles and a traffic reference object, the surface area or the volume of a damaged part and the like.
In addition, in the specific implementation process, more related information of the damaged part can be obtained by preliminarily positioning the damaged part related to the accident and prompting the user to take a picture of the part to obtain a detailed picture.
According to an embodiment of the present invention, after obtaining the evidence result that is coincident with the virtual vehicle contour map, the method further comprises: calculating the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road according to the evidence obtaining result; and adding the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road to the evidence obtaining result.
If the evidence obtaining result comprises the evidence obtaining result in the three-dimensional image format, the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road can be further calculated and added into the evidence obtaining result. Thus, the evidence obtaining result is displayed on the display screen, and meanwhile, the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road and the like can be displayed and marked.
According to a second aspect of the embodiments of the present invention, an apparatus for image acquisition, as shown in fig. 5, the apparatus 50 includes: the image acquisition module 501 is used for acquiring field images of traffic accidents; an incident type determination module 502 for determining an incident type based on the live image and/or user input; a three-dimensional vehicle model obtaining module 503, configured to obtain a three-dimensional vehicle model of an accident vehicle of the traffic accident according to the scene image; a vehicle contour map obtaining module 504, configured to obtain a three-dimensional virtual vehicle contour map according to the accident type and a three-dimensional vehicle model of the accident vehicle; a vehicle profile display module 505, configured to display a virtual vehicle profile to guide a user to take a photograph according to the virtual vehicle profile; and a forensics result obtaining module 506, configured to obtain forensics results consistent with the virtual vehicle contour map.
According to an embodiment of the present invention, the accident type determining module 502 includes: the pre-judged accident type obtaining submodule is used for identifying the traffic accident type according to the field image to obtain the pre-judged accident type; and the accident type determining submodule is used for displaying the pre-judged accident type for the user to confirm, determining the pre-judged accident type as the accident type if the user confirms, displaying all the accident types for the user to select if the user denies, and determining the accident type according to the user selection.
According to an embodiment of the present invention, the pre-determined accident type obtaining sub-module includes: the three-dimensional field model building unit is used for building a three-dimensional field model according to the field image; the accident feature extraction unit is used for extracting accident features of the traffic accident from the three-dimensional field model by utilizing an augmented reality AR identification technology; and the pre-judging accident type obtaining unit is used for identifying the traffic accident type according to the accident characteristics to obtain the pre-judging accident type.
According to an embodiment of the present invention, the three-dimensional vehicle model obtaining module 503 includes: the brand and model acquisition submodule is used for carrying out vehicle identification according to the field image to obtain the brand and model of an accident vehicle of the traffic accident; and the three-dimensional vehicle model acquisition submodule is used for acquiring a three-dimensional vehicle model corresponding to the brand and the model from a pre-established three-dimensional vehicle model database according to the brand and the model of the accident vehicle.
According to an embodiment of the present invention, the three-dimensional vehicle model obtaining module 503 further includes: and the three-dimensional vehicle model reconstruction submodule is used for reconstructing a three-dimensional model to obtain a three-dimensional vehicle model of the accident vehicle of the traffic accident if the three-dimensional vehicle model corresponding to the brand and the model does not exist in the pre-established three-dimensional vehicle model database.
According to an embodiment of the present invention, the three-dimensional vehicle model reconstruction submodule is specifically configured to, according to a size ratio 1 of the accident vehicle: 1, constructing a three-dimensional vehicle model of the accident vehicle.
According to an embodiment of the present invention, the forensics result obtaining module 506 includes: and the automatic photographing sub-module is used for automatically photographing to obtain a evidence obtaining result consistent with the virtual vehicle outline map when the image of the accident vehicle is superposed with the virtual vehicle outline map.
According to an embodiment of the present invention, the forensics result obtaining module 506 further includes: and the user operation prompting submodule is used for giving a user operation prompt when the image of the accident vehicle is not coincident with the virtual vehicle outline drawing.
According to an embodiment of the present invention, the apparatus 50 further includes: and the vehicle damaged position determining module is used for determining the damaged position of the accident vehicle caused by the traffic accident according to the evidence obtaining result.
According to an embodiment of the present invention, the apparatus 50 further includes: the calculation module is used for calculating the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road according to the evidence obtaining result; and the additional information adding module is used for adding the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road on the evidence obtaining result.
According to a third aspect of embodiments of the present invention, a storage medium has stored thereon program instructions for executing the above-mentioned image acquisition method when executed.
Here, it should be noted that: the above description of the embodiment of the image capturing apparatus and the above description of the embodiment of the computer storage medium are similar to the description of the foregoing method embodiments, and have similar beneficial effects to the foregoing method embodiments, and therefore are not repeated herein. For the technical details of the embodiments of the image capturing device and the computer storage medium of the present invention that have not been disclosed yet, please refer to the description of the foregoing method embodiments of the present invention for understanding, and therefore, for brevity, will not be repeated.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another device, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media capable of storing program codes, such as a removable storage medium, a Read Only Memory (ROM), a magnetic disk, and an optical disk.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage medium, a ROM, a magnetic disk, an optical disk, or the like, which can store the program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (13)
1. An image acquisition method is applied to evidence collection of a traffic accident scene, and is characterized by comprising the following steps:
collecting a scene image of a traffic accident;
determining the accident type according to the scene image;
acquiring a three-dimensional vehicle model of an accident vehicle of the traffic accident according to the scene image;
acquiring a three-dimensional virtual vehicle contour map according to the accident type and the three-dimensional vehicle model of the accident vehicle;
displaying the virtual vehicle outline so as to guide a user to take a picture according to the virtual vehicle outline;
obtaining a forensics result consistent with the virtual vehicle profile.
2. The method of claim 1, wherein determining a type of incident from the live image comprises:
identifying the type of the traffic accident according to the site image to obtain a pre-judged accident type;
and displaying the pre-judged accident type for a user to confirm, if the user confirms, determining the pre-judged accident type as the accident type, if the user denies, displaying all the accident types for the user to select, and determining the accident type according to the user selection.
3. The method of claim 2, wherein the identifying the type of the traffic accident according to the scene image to obtain a pre-determined accident type comprises:
constructing a three-dimensional field model according to the field image;
extracting accident features of the traffic accident from the three-dimensional field model by using an Augmented Reality (AR) recognition technology;
and identifying the traffic accident type according to the accident characteristics to obtain a pre-judged accident type.
4. The method of claim 1, wherein the obtaining a three-dimensional vehicle model of an accident vehicle of the traffic accident from the live images comprises:
carrying out vehicle identification according to the site image to obtain the brand and the model of an accident vehicle of the traffic accident;
and acquiring a three-dimensional vehicle model corresponding to the brand and the model from a pre-established three-dimensional vehicle model database according to the brand and the model of the accident vehicle.
5. The method of claim 4, further comprising:
and if the three-dimensional vehicle model corresponding to the brand and the model does not exist in the pre-established three-dimensional vehicle model database, reconstructing the three-dimensional model to obtain the three-dimensional vehicle model of the accident vehicle of the traffic accident.
6. The method of claim 1, 4 or 5, wherein the three-dimensional vehicle model of the accident vehicle is a three-dimensional vehicle model of the accident vehicle in a 1: 1, and (b).
7. The method of claim 1, wherein said obtaining a forensic result consistent with the virtual vehicle contour map comprises:
and when the image of the accident vehicle is superposed with the virtual vehicle outline drawing, automatically taking a picture to obtain a forensics result consistent with the virtual vehicle outline drawing.
8. The method of claim 7, further comprising:
and when the image of the accident vehicle is not coincident with the virtual vehicle outline drawing, giving a user operation prompt.
9. The method of claim 1, wherein after the obtaining a forensic result that coincides with the virtual vehicle profile, the method further comprises:
and determining the damaged position of the accident vehicle caused by the traffic accident according to the evidence obtaining result.
10. The method of claim 1, 7, 8, or 9, wherein the forensic result comprises a forensic result in a three-dimensional image format.
11. The method of claim 10, wherein after the obtaining a forensic result that coincides with the virtual vehicle profile, the method further comprises:
calculating the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road according to the evidence obtaining result;
and adding the vehicle distance of the accident vehicle and/or the angle between the accident vehicle and the road to the evidence obtaining result.
12. An image acquisition device is applied to evidence collection of a traffic accident scene, and is characterized by comprising:
the image acquisition module is used for acquiring a scene image of a traffic accident;
the accident type determining module is used for determining the accident type according to the scene image;
the three-dimensional vehicle model acquisition module is used for acquiring a three-dimensional vehicle model of an accident vehicle of the traffic accident according to the field image;
the vehicle contour map acquisition module is used for acquiring a three-dimensional virtual vehicle contour map according to the accident type and the three-dimensional vehicle model of the accident vehicle;
the vehicle outline map display module is used for displaying the virtual vehicle outline map so as to guide a user to take a picture according to the virtual vehicle outline map;
and the evidence obtaining module is used for obtaining evidence obtaining results consistent with the virtual vehicle contour map.
13. A storage medium on which program instructions are stored, characterized in that the program instructions are adapted to perform the image acquisition method as claimed in claim 1 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011122659.6A CN112434368A (en) | 2020-10-20 | 2020-10-20 | Image acquisition method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011122659.6A CN112434368A (en) | 2020-10-20 | 2020-10-20 | Image acquisition method, device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112434368A true CN112434368A (en) | 2021-03-02 |
Family
ID=74695712
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011122659.6A Pending CN112434368A (en) | 2020-10-20 | 2020-10-20 | Image acquisition method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112434368A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114088041A (en) * | 2021-10-18 | 2022-02-25 | 北京魔鬼鱼科技有限公司 | Vehicle three-dimensional scanning imaging method and system |
CN114637438A (en) * | 2022-03-23 | 2022-06-17 | 支付宝(杭州)信息技术有限公司 | AR-based vehicle accident handling method and device |
CN114928695A (en) * | 2022-04-29 | 2022-08-19 | 北京淘车科技有限公司 | Vehicle image acquisition method and device, medium and terminal |
WO2023035960A1 (en) * | 2021-09-07 | 2023-03-16 | 北京字跳网络技术有限公司 | Photographing guiding method and apparatus, and electronic device and storage medium |
CN117312598A (en) * | 2023-11-27 | 2023-12-29 | 广东利通科技投资有限公司 | Evidence obtaining method, device, computer equipment and storage medium for fee evasion auditing |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046731A (en) * | 2015-06-25 | 2015-11-11 | 西安理工大学 | Accident site virtual multi-attention-perspective conversion three-dimensional dynamic reproducing method |
CN105206059A (en) * | 2015-10-28 | 2015-12-30 | 重庆邮电大学 | Traffic accident scene evidence collection guiding system and method thereof |
CN108665373A (en) * | 2018-05-08 | 2018-10-16 | 阿里巴巴集团控股有限公司 | A kind of interaction processing method of car damage identification, device, processing equipment and client |
CN110245552A (en) * | 2019-04-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Interaction processing method, device, equipment and the client of vehicle damage image taking |
CN110809088A (en) * | 2019-10-25 | 2020-02-18 | 广东以诺通讯有限公司 | Traffic accident photographing method and system based on mobile phone app |
WO2020177480A1 (en) * | 2019-03-07 | 2020-09-10 | 阿里巴巴集团控股有限公司 | Vehicle accident identification method and apparatus, and electronic device |
-
2020
- 2020-10-20 CN CN202011122659.6A patent/CN112434368A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105046731A (en) * | 2015-06-25 | 2015-11-11 | 西安理工大学 | Accident site virtual multi-attention-perspective conversion three-dimensional dynamic reproducing method |
CN105206059A (en) * | 2015-10-28 | 2015-12-30 | 重庆邮电大学 | Traffic accident scene evidence collection guiding system and method thereof |
CN108665373A (en) * | 2018-05-08 | 2018-10-16 | 阿里巴巴集团控股有限公司 | A kind of interaction processing method of car damage identification, device, processing equipment and client |
WO2020177480A1 (en) * | 2019-03-07 | 2020-09-10 | 阿里巴巴集团控股有限公司 | Vehicle accident identification method and apparatus, and electronic device |
CN110245552A (en) * | 2019-04-29 | 2019-09-17 | 阿里巴巴集团控股有限公司 | Interaction processing method, device, equipment and the client of vehicle damage image taking |
CN110809088A (en) * | 2019-10-25 | 2020-02-18 | 广东以诺通讯有限公司 | Traffic accident photographing method and system based on mobile phone app |
Non-Patent Citations (1)
Title |
---|
胡雪瑾;: "车祸再现中三维车辆模型准确检索方法研究", 计算机仿真, no. 09 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023035960A1 (en) * | 2021-09-07 | 2023-03-16 | 北京字跳网络技术有限公司 | Photographing guiding method and apparatus, and electronic device and storage medium |
CN114088041A (en) * | 2021-10-18 | 2022-02-25 | 北京魔鬼鱼科技有限公司 | Vehicle three-dimensional scanning imaging method and system |
CN114637438A (en) * | 2022-03-23 | 2022-06-17 | 支付宝(杭州)信息技术有限公司 | AR-based vehicle accident handling method and device |
CN114637438B (en) * | 2022-03-23 | 2024-05-07 | 支付宝(杭州)信息技术有限公司 | AR-based vehicle accident handling method and device |
CN114928695A (en) * | 2022-04-29 | 2022-08-19 | 北京淘车科技有限公司 | Vehicle image acquisition method and device, medium and terminal |
CN117312598A (en) * | 2023-11-27 | 2023-12-29 | 广东利通科技投资有限公司 | Evidence obtaining method, device, computer equipment and storage medium for fee evasion auditing |
CN117312598B (en) * | 2023-11-27 | 2024-04-09 | 广东利通科技投资有限公司 | Evidence obtaining method, device, computer equipment and storage medium for fee evasion auditing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112434368A (en) | Image acquisition method, device and storage medium | |
KR102270499B1 (en) | Image-based vehicle damage determination method and device, and electronic device | |
US11030698B2 (en) | Server for real-time accident documentation and claim submission | |
CN105206059B (en) | A kind of scene of a traffic accident evidence collection instructs system and method | |
JP6546271B2 (en) | Image processing apparatus, object detection apparatus, and image processing method | |
KR20190069457A (en) | IMAGE BASED VEHICLES LOSS EVALUATION METHOD, DEVICE AND SYSTEM, | |
CN110136091B (en) | Image processing method and related product | |
US9336630B2 (en) | Method and apparatus for providing augmented reality | |
KR101900778B1 (en) | A car accident handling system based on mobile devices | |
CN111837158A (en) | Image processing method and device, shooting device and movable platform | |
JP2020518165A (en) | Platform for managing and validating content such as video images, pictures, etc. generated by different devices | |
CN114913506A (en) | 3D target detection method and device based on multi-view fusion | |
CN115115611B (en) | Vehicle damage identification method and device, electronic equipment and storage medium | |
CN113055823A (en) | Method and device for sharing bicycle based on roadside parking management | |
CN115810134A (en) | Image acquisition quality inspection method, system and device for preventing car insurance from cheating | |
CN108986249B (en) | Vehicle remote damage assessment method and system based on panoramic all-around image | |
CN108419044B (en) | Vehicle accountability determination method, terminal and computer readable storage medium | |
JP4057571B2 (en) | Image analysis system and image analysis method | |
CN115565155A (en) | Training method of neural network model, generation method of vehicle view and vehicle | |
CN112818743B (en) | Image recognition method and device, electronic equipment and computer storage medium | |
CN111756988A (en) | Driving shooting recording method, vehicle-mounted device and vehicle | |
CN114971991A (en) | Data processing method, device, equipment and medium | |
CN112184605A (en) | Method, equipment and system for enhancing vehicle driving visual field | |
US20160337636A1 (en) | System and method for event reconstruction | |
CN116434016B (en) | Image information enhancement method, model training method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |