CN112734908B - Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system - Google Patents
Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system Download PDFInfo
- Publication number
- CN112734908B CN112734908B CN202011635384.6A CN202011635384A CN112734908B CN 112734908 B CN112734908 B CN 112734908B CN 202011635384 A CN202011635384 A CN 202011635384A CN 112734908 B CN112734908 B CN 112734908B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- dimensional reconstruction
- image
- chassis
- data
- 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.)
- Active
Links
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- 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
Abstract
The invention provides an automobile chassis three-dimensional reconstruction system for a running vehicle and a working method thereof. The system comprises an under-vehicle imaging subsystem and a data acquisition processing subsystem which are connected through a data cable; the vehicle bottom imaging subsystem is arranged on the ground or buried below the ground and is used for shooting vehicles passing above, and comprises an image acquisition unit and a light supplementing light source; the image acquisition unit is used for acquiring an image of the chassis of the automobile; the light supplementing light source is used for uniformly illuminating within the view field range of the image acquisition unit; and the data acquisition processing subsystem is used for controlling the vehicle bottom imaging subsystem, acquiring image data, storing the data and executing a three-dimensional reconstruction algorithm to complete the three-dimensional reconstruction of the vehicle bottom. The technical scheme of the invention solves the problems that objects are shielded under the structure of the vehicle bottom and cannot be easily observed in the prior art, and the technical problems of low efficiency and poor reliability in the prior art that only two-dimensional views of the vehicle bottom are shot and foreign matter detection is carried out.
Description
Technical Field
The invention relates to the technical field of three-dimensional reconstruction of automobile chassis, in particular to an automobile chassis three-dimensional reconstruction system for a running vehicle and a working method of the automobile chassis three-dimensional reconstruction system.
Background
In recent years, safety accidents caused by dangerous articles and contraband articles carried by vehicles are more and more, and life and public property safety of passengers are threatened. In order to maintain the safety and stability of society, safety inspection is required to be carried out on vehicles passing through a partial area so as to prevent illegal objects from being hidden on the vehicles by lawbreakers. Modern vehicles pay attention to functionality and driving safety, the vehicle body structure is more and more complex, and the difficulty is increased for safety inspection. In particular, automobile chassis contains more and more parts, and the sight of inspectors is difficult to observe, and the automobile chassis belongs to the position where the safety inspection of the automobile needs to be focused. In the prior art, two methods are generally adopted, namely, an inspector utilizes a reflector to inspect by means of human eyes; secondly, scanning the vehicle bottom by using a linear array camera to generate a two-dimensional image of the vehicle bottom, thereby completing foreign matter detection of the vehicle bottom. The simple two-dimensional image recognition method only relies on plane image detection, so that information shielded by the automobile chassis structure is difficult to detect, and the detection accuracy is not high; in order to detect the automobile chassis more accurately, research on the automobile chassis foreign matter detection technology based on three-dimensional images has become more and more important and urgent.
Disclosure of Invention
According to the technical problems that the object is shielded under the structure of the vehicle bottom and cannot be easily observed, and the prior art only shoots a two-dimensional view of the vehicle bottom and detects the foreign matters, the efficiency is low and the reliability is poor, the three-dimensional reconstruction system of the chassis of the vehicle facing the running vehicle and the working method thereof are provided. The invention firstly utilizes the high-speed area array camera to collect the two-dimensional image of the automobile chassis, and then utilizes the three-dimensional reconstruction algorithm to process the two-dimensional image to obtain the three-dimensional view of the automobile chassis. The vehicle bottom image can be viewed at multiple angles according to the three-dimensional view of the vehicle chassis, so that the problems of single view angle, image distortion and the like in the result image scanned by the linear array camera are solved, and foreign matters hidden behind the vehicle bottom structure are not hidden.
The invention adopts the following technical means:
a three-dimensional reconstruction system of an automobile chassis facing a running vehicle comprises an automobile bottom imaging subsystem and a data acquisition processing subsystem which are connected through a data cable; wherein:
the vehicle bottom imaging subsystem is arranged on the ground or buried below the ground and is used for shooting vehicles passing above, and comprises an image acquisition unit and a light supplementing light source; the image acquisition unit is used for acquiring an image of the chassis of the automobile; the light supplementing light source is used for uniformly illuminating within the view field range of the image acquisition unit;
the data acquisition processing subsystem is used for controlling the vehicle bottom imaging subsystem, acquiring image data, storing the data and executing a three-dimensional reconstruction algorithm to complete vehicle bottom three-dimensional reconstruction.
Further, the image acquisition unit comprises a plurality of high-speed area array cameras, the high-speed area array cameras are arranged on the same straight line, the arrangement direction is along the width direction of the automobile chassis, and the automobile width is completely covered.
Further, the light supplementing light source is a high-brightness light source, and the light emitting part of the light supplementing light source extends along the width direction of the automobile chassis.
Further, the data acquisition processing subsystem comprises one of a PC computer, an industrial personal computer, a graphic workstation or a special embedded computer, and is internally provided with a high-speed computing card.
Further, the data acquisition processing subsystem is internally provided with a corresponding data acquisition card.
Further, the three-dimensional reconstruction algorithm executed by the data acquisition processing subsystem specifically includes:
step 1, inputting a group of automobile chassis image data sets acquired by the automobile bottom imaging subsystem;
step 2, extracting features, namely extracting features of each image in the automobile chassis image dataset to obtain feature points;
step 3, feature matching is carried out on feature points of adjacent images in the automobile chassis image dataset to obtain a complete matching point set;
step 4, estimating the relative pose between cameras based on the initial matching of the feature points;
step 5, optimizing the feature points and the camera parameters which are initially matched to obtain optimal space coordinates and camera parameters;
step 6, point cloud fusion, namely calculating the point cloud of the matched characteristic points according to the characteristic point matching result, and fusing the point cloud according to the pose of the camera;
and 7, dense three-dimensional reconstruction, namely carrying out three-dimensional correction on two adjacent image pairs according to the camera parameters obtained in the step 5, extracting characteristic points of the images, carrying out polar constraint matching on the three-dimensional matched images, and fusing dense point clouds according to the relative pose between the cameras estimated in the step 4 to obtain a reconstructed vehicle bottom three-dimensional model.
Further, the step 5 specifically includes:
step 51, adopting a beam method to adjust the difference to remove the error matching points;
step 52, taking the three-dimensional coordinates of the feature points in the step 2 and the relative pose between the cameras estimated in the step 4 as unknown parameters, and taking the pixel coordinates of the feature points in the step 2 as observation data;
and step 53, performing adjustment operation based on the step 52 to obtain optimal space coordinates and camera parameters.
The invention also provides a working method of the vehicle chassis three-dimensional reconstruction system facing the running vehicle, which comprises the following steps:
s1, preparing a system, namely arranging the vehicle bottom imaging subsystem at a specific entrance and exit so that the center of a vehicle passes right above the vehicle bottom imaging subsystem, and when the vehicle runs into the visible range of the vehicle bottom imaging subsystem, starting a light supplementing light source, and starting to acquire a vehicle bottom image at the highest acquisition frame rate by an image acquisition unit;
s2, image acquisition, namely starting from the head of the vehicle, synchronously acquiring images by the image acquisition unit according to a certain frame rate, ensuring that the vehicle passes through a specific entrance at a certain speed, and synchronously acquiring clear chassis images of the vehicle at a high frame rate by the image acquisition unit through a uniform and enough-brightness light supplementing light source;
s3, closing the system, namely closing a light supplementing light source in the vehicle bottom imaging subsystem after the vehicle integrally passes, and enabling the image acquisition unit to enter a waiting or closing state;
s4, data processing is carried out, image data acquired by the image acquisition unit are transmitted to the data acquisition processing subsystem, and a three-dimensional reconstruction algorithm is executed to complete data processing, so that three-dimensional reconstruction of the automobile chassis is realized.
Further, in step S2, the plurality of high-speed area cameras in the image acquisition unit are synchronized in an external triggering or internal triggering manner during acquisition, so that each high-speed area camera performs image acquisition at the same time point, and the frame rate of each high-speed area camera is required to ensure that the overlapping rate of two adjacent acquired images is not lower than 50%.
Compared with the prior art, the invention has the following advantages:
1. the three-dimensional reconstruction system for the automobile chassis facing the running automobile, provided by the invention, acquires the two-dimensional image of the automobile chassis by using the high-speed area array camera, and then processes the two-dimensional image by using the three-dimensional reconstruction algorithm to obtain the three-dimensional view of the automobile chassis. The vehicle bottom image can be viewed at multiple angles according to the three-dimensional view of the vehicle chassis, so that the problems of single view angle, image distortion and the like in the result image scanned by the linear array camera are solved, and foreign matters hidden behind the vehicle bottom structure are not hidden.
2. The three-dimensional reconstruction system of the chassis of the automobile facing the running vehicle solves the problem that objects can not be easily observed due to shielding under the structure of the chassis, and has the advantages of high efficiency, good reliability and the like.
Based on the reasons, the invention can be widely popularized in the fields of three-dimensional reconstruction of the automobile chassis and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic structural diagram of a three-dimensional reconstruction system for an automobile chassis according to the present invention.
Fig. 2 is a schematic diagram of the position arrangement of a plurality of high-speed area array cameras in an image acquisition unit according to an embodiment of the present invention.
FIG. 3 is a flow chart of the operation of the three-dimensional reconstruction system of the chassis of the automobile of the present invention.
Fig. 4 is a flow chart of the three-dimensional reconstruction algorithm of the present invention.
Fig. 5 is a schematic diagram of a naming process of an image of a vehicle bottom in an image dataset of a vehicle chassis according to an embodiment of the present invention.
Fig. 6 is a three-dimensional reconstruction result (front view angle) of an automobile chassis obtained by the three-dimensional reconstruction system of an automobile chassis of the present invention.
Fig. 7 shows a three-dimensional reconstruction result (inclination angle) of an automobile chassis obtained by the three-dimensional reconstruction system of an automobile chassis of the present invention.
In the figure: 1. an underbody imaging subsystem; 2. a data acquisition processing subsystem; 3. an image acquisition unit; 4. a light supplementing light source; A. b, C, M, N each represent five high-speed area cameras arranged in the width direction of the vehicle bottom.
Detailed Description
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of 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 some embodiments of the present invention, not all embodiments. The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise. Meanwhile, it should be clear that the dimensions of the respective parts shown in the drawings are not drawn in actual scale for convenience of description. Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
In the description of the present invention, it should be understood that the azimuth or positional relationships indicated by the azimuth terms such as "front, rear, upper, lower, left, right", "lateral, vertical, horizontal", and "top, bottom", etc., are generally based on the azimuth or positional relationships shown in the drawings, merely to facilitate description of the present invention and simplify the description, and these azimuth terms do not indicate and imply that the apparatus or elements referred to must have a specific azimuth or be constructed and operated in a specific azimuth, and thus should not be construed as limiting the scope of protection of the present invention: the orientation word "inner and outer" refers to inner and outer relative to the contour of the respective component itself.
Spatially relative terms, such as "above … …," "above … …," "upper surface at … …," "above," and the like, may be used herein for ease of description to describe one device or feature's spatial location relative to another device or feature as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "above" or "over" other devices or structures would then be oriented "below" or "beneath" the other devices or structures. Thus, the exemplary term "above … …" may include both orientations of "above … …" and "below … …". The device may also be positioned in other different ways (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
In addition, the terms "first", "second", etc. are used to define the components, and are only for convenience of distinguishing the corresponding components, and the terms have no special meaning unless otherwise stated, and therefore should not be construed as limiting the scope of the present invention.
As shown in fig. 1, the invention provides an automobile chassis three-dimensional reconstruction system facing a running vehicle, which comprises an automobile bottom imaging subsystem 1 and a data acquisition processing subsystem 2 which are connected through a data cable; wherein: the vehicle bottom imaging subsystem 1 is arranged on the ground or buried in a range of 50cm below the ground and is used for shooting vehicles passing above, and comprises an image acquisition unit 3 and a light supplementing light source 4; the image acquisition unit 3 is used for acquiring an image of the chassis of the automobile; the light supplementing light source 4 is used for uniformly illuminating within the view field range of the image acquisition unit 3; the data acquisition processing subsystem 2 is used for controlling the vehicle bottom imaging subsystem 1, acquiring image data, storing the data and executing a three-dimensional reconstruction algorithm to complete the three-dimensional reconstruction of the vehicle bottom.
In specific implementation, as shown in fig. 2, the image acquisition unit includes a plurality of high-speed area array cameras, and the high-speed area array cameras are arranged on the same straight line, and the arrangement direction extends along the width direction of the chassis of the automobile to completely cover the width of the automobile. In this embodiment, the image acquisition unit includes 5 high-speed area array cameras, where the field angles of the high-speed area array cameras A, B, C are not less than 70 °, the space between the high-speed area array cameras A, B, C is 40cm-60cm, and the field overlapping ratio between two adjacent cameras can reach more than 55%. The three cameras are arranged in a straight line, and the arrangement direction is perpendicular to the running direction of the vehicle. In order to ensure that a plurality of cameras can synchronously acquire the automobile chassis of a vehicle moving at a high speed, an external triggering mode is adopted to synchronously and hard trigger the three cameras. Preferably, two high-speed cameras M and N which are obliquely arranged are added on the basis of three high-speed area array cameras A, B, C to increase parallax, the cameras M and N are respectively arranged on two sides of the camera B, the distance between the cameras M and N is about 7-10cm, and the inclination angles of the two oblique cameras are 15-30 degrees. The additional cameras need to be triggered in synchronization with the high speed area camera A, B, C.
In specific implementation, as a preferred embodiment of the present invention, the data acquisition processing subsystem 2 includes one of a PC computer, an industrial personal computer, a graphics workstation, or a dedicated embedded computer, and is internally configured with a high-speed computing card. In this embodiment, the data acquisition processing subsystem 2 is an industrial personal computer, and is used for controlling the vehicle bottom imaging subsystem 1, image data acquisition, data storage and executing a three-dimensional reconstruction algorithm, and the industrial personal computer is connected with the vehicle bottom imaging subsystem 1 through a data line. The data acquisition processing subsystem 2 is internally provided with a corresponding data acquisition card.
In specific implementation, as a preferred embodiment of the present invention, the present invention further provides a working method of an automobile chassis three-dimensional reconstruction system for a traveling vehicle, as shown in fig. 3, including:
s1, preparing a system, namely arranging an under-vehicle imaging subsystem 1 at a specific entrance and exit so that the center of a vehicle passes right above the under-vehicle imaging subsystem 1, starting a light supplementing light source 4 when the vehicle runs into the visible range of the under-vehicle imaging subsystem 1, and starting to acquire an under-vehicle image by an image acquisition unit 3 at the highest acquisition frame rate;
s2, image acquisition, namely starting from the head of the vehicle, synchronously acquiring images by the image acquisition unit 3 according to a certain frame rate, ensuring that the vehicle passes through a specific entrance and exit at a speed not higher than 60km/h, and synchronously acquiring clear chassis images of the vehicle at a high frame rate by the image acquisition unit 3 through the uniform and enough-brightness light supplementing light source 4; the plurality of high-speed area array cameras in the image acquisition unit 3 are synchronized in an external triggering or internal triggering mode during acquisition, so that the image acquisition of each high-speed area array camera at the same time point is ensured, and the frame rate of each high-speed area array camera is ensured to ensure that the overlapping rate of two adjacent acquired images is not lower than 50%.
S3, closing the system, after the whole vehicle passes through, closing the light supplementing light source 4 in the vehicle bottom imaging subsystem 1, and enabling the image acquisition unit 3 to enter a waiting or closing state;
s4, data processing is carried out, image data acquired by the image acquisition unit 3 are transmitted to the data acquisition processing subsystem 2, and a three-dimensional reconstruction algorithm is executed to complete data processing, so that three-dimensional reconstruction of the automobile chassis is realized.
In specific implementation, as a preferred embodiment of the present invention, the three-dimensional reconstruction algorithm executed by the data acquisition processing subsystem 2, as shown in fig. 4, specifically includes:
step 1, inputting a group of automobile chassis image data sets acquired by an automobile chassis imaging subsystem 1; as shown in fig. 5, in the naming process of the bottom images in the dataset, for convenience of description later, naming rules of the dataset (including n bottom images) are 001,002 … …,00n, and after the vehicle head enters the field of view of the cameras, the images collected by the camera A, N, B, M, C are sequentially named as 001,002, 003, 004, 005 as a first group of bottom images according to the field of view overlapping rate relation between the cameras. As the vehicle moves, the images captured by the camera A, N, B, M, C are sequentially designated 010, 009, 008, 007, 006, and so on in the second set of drawings. Each group comprises five vehicle bottom images, m groups are total, each group of images is traversed in an arch shape, the images are named from 001 to 00i until i=n, and the whole data set has n (n=m×5) images;
step 2, extracting features, namely extracting features of each image in the automobile chassis image data set by adopting a SIFT operator to obtain feature points;
step 3, feature matching is carried out on feature points of adjacent images in the automobile chassis image dataset to obtain a complete matching point set;
step 4, estimating the relative pose between cameras based on the initial matching of the feature points; in the data set of the whole vehicle bottom image, the image 001 and the image 002 are selected first, and a group of basic point clouds are obtained according to the characteristic points which can be matched between the two images. And solving the pose coordinates and the rotation angles of the camera A and the camera N, namely the relative pose among the cameras, through a plurality of feature points with known three-dimensional coordinates and pixel coordinates of the feature points in the images 001 and 002. For the subsequent image 003, calculating matching points of the image 002 and the image 003, wherein part of the matching points are also matching points with known space coordinates between the image 001 and the image 002, and meanwhile, the relative transformation matrix of the camera B relative to the camera N can be estimated because the pixel coordinates of the points in the image 003 are known, so that the relative pose between the camera B and the camera N is estimated preliminarily;
step 5, optimizing the feature points and the camera parameters which are initially matched to obtain optimal space coordinates and camera parameters; the step 5 specifically includes:
step 51, adopting a beam method to adjust the difference to remove the error matching points;
step 52, taking the three-dimensional coordinates of the feature points in the step 2 and the relative pose between the cameras estimated in the step 4 as unknown parameters, and taking the pixel coordinates of the feature points in the step 2 as observation data;
and step 53, performing adjustment operation based on the step 52 to obtain optimal space coordinates and camera parameters.
Step 6, point cloud fusion, namely calculating the point cloud of the matched characteristic points according to the characteristic point matching result, and fusing the point cloud according to the pose of the camera; in this embodiment, after three-dimensional coordinates of the matchable points in the space in the image 002 and the image 003 are calculated and a new point cloud is obtained, the newly obtained three-dimensional point cloud is fused with the previous three-dimensional point cloud according to the relative pose between the camera B and the camera N, and only points that match between the image 002 and the image 003 but do not match between the image 001 and the image 002 are added. The pose of the camera M is estimated by the input image 004, the pose of the camera C is estimated by the input image 005, then the pose of the corresponding camera is estimated by continuously inputting the image 00i until i=n, and the pose estimation of the corresponding cameras of all the images in the data set is completed. The iteration is circulated until the addition of the images of the vehicle bottom image dataset is finished, and the whole vehicle bottom point cloud is obtained;
and 7, dense three-dimensional reconstruction, namely carrying out three-dimensional correction on two adjacent image pairs according to the camera parameters obtained in the step 5, extracting characteristic points of the images, carrying out polar constraint matching on the three-dimensional matched images, and fusing dense point clouds according to the relative pose between the cameras estimated in the step 4 to obtain a reconstructed vehicle bottom three-dimensional model. The output result can be point cloud, triangle split map, texture map and the like.
As shown in fig. 6 and 7, the three-dimensional model of the vehicle chassis obtained by using the three-dimensional reconstruction system of the vehicle chassis in the invention is shown.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. The three-dimensional reconstruction system of the chassis of the automobile facing the running vehicle is characterized by comprising an imaging subsystem of the chassis and a data acquisition and processing subsystem which are connected through a data cable; wherein:
the vehicle bottom imaging subsystem is arranged on the ground or buried below the ground and is used for shooting vehicles passing above, and comprises an image acquisition unit and a light supplementing light source; the image acquisition unit is used for acquiring an image of the chassis of the automobile; the light supplementing light source is used for uniformly illuminating within the view field range of the image acquisition unit;
the data acquisition processing subsystem is used for controlling the vehicle bottom imaging subsystem, acquiring image data, storing the data and executing a three-dimensional reconstruction algorithm to complete vehicle bottom three-dimensional reconstruction; the three-dimensional reconstruction algorithm executed by the data acquisition and processing subsystem specifically comprises the following steps:
step 1, inputting a group of automobile chassis image data sets acquired by the automobile bottom imaging subsystem;
step 2, extracting features, namely extracting features of each image in the automobile chassis image dataset to obtain feature points;
step 3, feature matching is carried out on feature points of adjacent images in the automobile chassis image dataset to obtain a complete matching point set;
step 4, estimating the relative pose between cameras based on the initial matching of the feature points;
step 5, optimizing the feature points and the camera parameters which are initially matched to obtain optimal space coordinates and camera parameters;
step 6, point cloud fusion, namely calculating the point cloud of the matched characteristic points according to the characteristic point matching result, and fusing the point cloud according to the pose of the camera;
and 7, dense three-dimensional reconstruction, namely carrying out three-dimensional correction on two adjacent image pairs according to the camera parameters obtained in the step 5, extracting characteristic points of the images, carrying out polar constraint matching on the three-dimensional matched images, and fusing dense point clouds according to the relative pose between the cameras estimated in the step 4 to obtain a reconstructed vehicle bottom three-dimensional model.
2. The three-dimensional reconstruction system for an automobile chassis facing a traveling vehicle according to claim 1, wherein the image acquisition unit comprises a plurality of high-speed area array cameras, the high-speed area array cameras are arranged on the same straight line, and the arrangement direction extends along the width direction of the automobile chassis to completely cover the width of the automobile.
3. The three-dimensional reconstruction system for an automobile chassis facing a traveling vehicle according to claim 1, wherein the light-supplementing light source is a high-brightness light source, and the light-emitting portion thereof extends in a direction of an automobile chassis width.
4. The vehicle chassis three-dimensional reconstruction system for a traveling vehicle according to claim 1, wherein the data acquisition processing subsystem comprises one of a PC computer, an industrial personal computer, a graphics workstation, or a dedicated embedded computer, and a high-speed computing card is internally configured.
5. The vehicle chassis three-dimensional reconstruction system for a traveling vehicle according to claim 4, wherein the data acquisition processing subsystem is internally provided with a corresponding data acquisition card.
6. The three-dimensional reconstruction system for chassis of vehicles according to claim 1, wherein said step 5 specifically comprises:
step 51, adopting a beam method to adjust the difference to remove the error matching points;
step 52, taking the three-dimensional coordinates of the feature points in the step 2 and the relative pose between the cameras estimated in the step 4 as unknown parameters, and taking the pixel coordinates of the feature points in the step 2 as observation data;
and step 53, performing adjustment operation based on the step 52 to obtain optimal space coordinates and camera parameters.
7. A method of operation of a three-dimensional reconstruction system for a chassis of a vehicle for travelling according to any one of the preceding claims 1-6, comprising:
s1, preparing a system, namely arranging the vehicle bottom imaging subsystem at a specific entrance and exit so that the center of a vehicle passes right above the vehicle bottom imaging subsystem, and when the vehicle runs into the visible range of the vehicle bottom imaging subsystem, starting a light supplementing light source, and starting to acquire a vehicle bottom image at the highest acquisition frame rate by an image acquisition unit;
s2, image acquisition, namely starting from the head of the vehicle, synchronously acquiring images by the image acquisition unit according to a certain frame rate, ensuring that the vehicle passes through a specific entrance at a certain speed, and synchronously acquiring clear chassis images of the vehicle at a high frame rate by the image acquisition unit through a uniform and enough-brightness light supplementing light source;
s3, closing the system, namely closing a light supplementing light source in the vehicle bottom imaging subsystem after the vehicle integrally passes, and enabling the image acquisition unit to enter a waiting or closing state;
s4, data processing is carried out, image data acquired by the image acquisition unit are transmitted to the data acquisition processing subsystem, and a three-dimensional reconstruction algorithm is executed to complete data processing, so that three-dimensional reconstruction of the automobile chassis is realized.
8. The working method of the three-dimensional reconstruction system of the chassis of the automobile facing the driving vehicle according to claim 7, wherein in the step S2, a plurality of high-speed area array cameras in the image acquisition unit are synchronized in an external triggering or internal triggering manner during acquisition, so that each high-speed area array camera performs image acquisition at the same time point, and the frame rate of each high-speed area array camera is required to ensure that the overlapping rate of two adjacent acquired images is not lower than 50%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011635384.6A CN112734908B (en) | 2020-12-31 | 2020-12-31 | Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011635384.6A CN112734908B (en) | 2020-12-31 | 2020-12-31 | Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734908A CN112734908A (en) | 2021-04-30 |
| CN112734908B true CN112734908B (en) | 2023-09-01 |
Family
ID=75609912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011635384.6A Active CN112734908B (en) | 2020-12-31 | 2020-12-31 | Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734908B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724368B (en) * | 2021-07-23 | 2023-02-07 | 北京百度网讯科技有限公司 | Image acquisition system, three-dimensional reconstruction method, device, equipment and storage medium |
| CN117593592B (en) * | 2024-01-18 | 2024-04-16 | 山东华时数字技术有限公司 | Intelligent scanning and identifying system and method for foreign matters at bottom of vehicle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565873A (en) * | 2012-01-14 | 2012-07-11 | 张森 | Safety check system for three-dimensional vehicle chassis |
| CN108257161A (en) * | 2018-01-16 | 2018-07-06 | 重庆邮电大学 | Vehicle environmental three-dimensionalreconstruction and movement estimation system and method based on polyphaser |
| EP3364336A1 (en) * | 2017-02-20 | 2018-08-22 | Continental Automotive GmbH | A method and apparatus for estimating a range of a moving object |
-
2020
- 2020-12-31 CN CN202011635384.6A patent/CN112734908B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102565873A (en) * | 2012-01-14 | 2012-07-11 | 张森 | Safety check system for three-dimensional vehicle chassis |
| EP3364336A1 (en) * | 2017-02-20 | 2018-08-22 | Continental Automotive GmbH | A method and apparatus for estimating a range of a moving object |
| CN108257161A (en) * | 2018-01-16 | 2018-07-06 | 重庆邮电大学 | Vehicle environmental three-dimensionalreconstruction and movement estimation system and method based on polyphaser |
Non-Patent Citations (1)
| Title |
|---|
| 多目立体视觉三维重建系统的设计;章秀华;白浩玉;李毅;;武汉工程大学学报(03);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734908A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111337941B (en) | Dynamic obstacle tracking method based on sparse laser radar data | |
| CN110163904A (en) | Object marking method, control method for movement, device, equipment and storage medium | |
| CN107392964B (en) | The indoor SLAM method combined based on indoor characteristic point and structure lines | |
| CN110531376B (en) | Obstacle detection and tracking method for port unmanned vehicle | |
| CN104541302B (en) | Distance prompt Object Segmentation System and method | |
| CN101941438B (en) | Intelligent detection control device and method of safe interval | |
| CN108764187A (en) | Extract method, apparatus, equipment, storage medium and the acquisition entity of lane line | |
| CN112734908B (en) | Automobile chassis three-dimensional reconstruction system for running vehicle and working method of automobile chassis three-dimensional reconstruction system | |
| CN104506800B (en) | The alert camera scene synthesis of the multi-direction electricity of one kind and comprehensive monitoring and controlling method and device | |
| CN103578117A (en) | Method for determining poses of camera relative to environment | |
| CN111369617B (en) | 3D target detection method of monocular view based on convolutional neural network | |
| CN105300403A (en) | Vehicle mileage calculation method based on double-eye vision | |
| CN103716687A (en) | Method and system for using fingerprints to track moving objects in video | |
| CN112883790A (en) | 3D object detection method based on monocular camera | |
| US20220258875A1 (en) | Feature detection for automated air-to-air refueling (a3r) | |
| CN107688174A (en) | A kind of image distance-finding method, system, storage medium and vehicle-mounted visually-perceptible equipment | |
| Zhang et al. | Deep learning based object distance measurement method for binocular stereo vision blind area | |
| CN113537047A (en) | Obstacle detection method, obstacle detection device, vehicle and storage medium | |
| Huang et al. | Measuring the absolute distance of a front vehicle from an in-car camera based on monocular vision and instance segmentation | |
| CN116978009A (en) | Dynamic object filtering method based on 4D millimeter wave radar | |
| CN106709432B (en) | Human head detection counting method based on binocular stereo vision | |
| CN114820474A (en) | Train wheel defect detection method based on three-dimensional information | |
| CN112991433B (en) | Truck overall dimension measuring method based on binocular depth perception and vehicle position | |
| CN102565873A (en) | Safety check system for three-dimensional vehicle chassis | |
| Petrovai et al. | Obstacle detection using stereovision for Android-based mobile devices |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |