CN112614050A - Device and method for acquiring vehicle bottom road surface image of motor vehicle - Google Patents
Device and method for acquiring vehicle bottom road surface image of motor vehicle Download PDFInfo
- Publication number
- CN112614050A CN112614050A CN202011378746.8A CN202011378746A CN112614050A CN 112614050 A CN112614050 A CN 112614050A CN 202011378746 A CN202011378746 A CN 202011378746A CN 112614050 A CN112614050 A CN 112614050A
- Authority
- CN
- China
- Prior art keywords
- image frame
- original image
- frame
- motor vehicle
- offset
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The embodiment of the invention provides a device and a method for acquiring an image of a bottom road surface of a motor vehicle, wherein the device comprises: the initialization module is used for extracting original image frames of the motor vehicle under an overlooking visual angle frame by frame from a panoramic video image transmitted by a camera device of the motor vehicle; the wheel speed pulse monitoring module is used for monitoring and outputting real-time wheel speed pulses of wheels of the motor vehicle; the pulse variation calculating module is used for determining a reference image frame and then calculating to obtain the actual wheel speed pulse variation of the wheel relative to the reference image frame in the original image frame; the offset calculation module is used for calculating a target angle offset and a target position offset of the original image frame relative to the reference image frame; and the image splicing module is used for determining an image frame to be intercepted from the reference image frame, then determining a pavement image to be spliced, and splicing and covering the pavement image to be intercepted to the corresponding position in the original image frame. The embodiment can still accurately acquire the road surface image of the bottom of the motor vehicle when the visibility is poor.
Description
Technical Field
The embodiment of the invention relates to the technical field of auxiliary driving of motor vehicles, in particular to a device and a method for acquiring a vehicle bottom road surface image of a motor vehicle.
Background
Generally, in current motor vehicle safety driving, for convenience of customers knows 360 degrees images around the motor vehicle in real time, install 360 degrees panorama image systems on the motor vehicle usually, wherein, still present the whole virtual transparent form of motor vehicle in order to improve user's impression in the display screen, promoted holistic science and technology sense on the one hand, on the other hand, also convenience of customers looks over the road surface image of motor vehicle bottom to combine the road surface image of bottom to select safe driving route.
However, the vehicle bottom road surface of the motor vehicle is positioned in the view blind area of the 360-degree panoramic image system of the motor vehicle and can not be directly shot, however, in the top view of the vehicle, an image of the road surface around the vehicle body is captured, therefore, the existing vehicle underbody road surface image usually first acquires the previous frame of the current frame (from the second frame, the first frame usually does not display the underbody road surface image or displays as the black image) in the top view of the vehicle, then calculating the angle offset and the position offset of the motor vehicle based on the image detection principle, finally intercepting the image of the corresponding position (part of the road surface around the motor vehicle body) from the previous frame image according to the angle offset and the position offset for splicing the vehicle bottom road surface images in the current frame, circulating in sequence, namely, the road surface image (the previous frame of the current frame) before the vehicle moves is adopted to patch the road surface image (the current frame) covered by the chassis after the vehicle moves. The existing method for imaging the underbody pavement of the motor vehicle needs to select corresponding areas from a current frame and a previous frame respectively, detect and identify the images and then determine the angle offset and the position offset of the images and the previous frame. However, when the vehicle is in an environment with poor visibility (for example, at night), the light reflection phenomenon is severe, the quality of the image obtained by the panoramic image system is poor, the detection and identification effects of the image are also poor, and the accuracy of the angle offset and the position offset which are correspondingly calculated at the moment is reduced, so that an accurate road surface image of the bottom of the vehicle cannot be obtained.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a device for acquiring the road surface image of the bottom of the motor vehicle, which can still accurately acquire the road surface image of the bottom of the motor vehicle when the visibility is poor.
The embodiment of the invention further aims to solve the technical problem of providing a device for acquiring the road surface image at the bottom of the motor vehicle, which can still accurately acquire the road surface image at the bottom of the motor vehicle when the visibility is poor.
In order to solve the above technical problem, an embodiment of the present invention provides the following technical solutions: an image acquisition device for a bottom road surface of a motor vehicle comprises:
the initialization module is connected with a camera device of the motor vehicle and used for extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device;
the wheel speed pulse monitoring module is connected with the wheels of the motor vehicle and used for monitoring and outputting real-time wheel speed pulses of the wheels when the visibility of the surrounding environment of the motor vehicle is lower than a preset threshold value;
a pulse variation calculating module, connected to the wheel speed pulse monitoring module and the initializing module, for processing the original image frames frame by frame from a predetermined nth frame original image frame, and calculating to obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse by taking the adjacent previous N-1 frames of the current original image frame as reference image frames, where N is an integer greater than 2;
the offset calculation module is connected with the pulse variation calculation module and used for calculating the target angle offset and the target position offset of the current original image frame relative to the automobile body in each reference image frame according to the actual wheel speed pulse variation by adopting the Ackerman steering geometry principle; and
and the image splicing module is connected with the offset determining module and used for determining image frames to be intercepted from the reference image frames according to the target angle offsets and the target position offsets, calculating road images to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frames to be intercepted, and splicing and covering the road images to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
Further, the offset calculation module includes:
the wheel moving distance calculating unit is used for calculating the actual moving distance of the current original image frame relative to the wheels in each reference image frame according to the preset moving distance of the pre-stored wheels under the single wheel speed pulse and the variation of each actual wheel speed pulse;
the angle offset calculation unit is used for calculating the target angle offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to each actual moving distance by adopting an Ackerman steering geometry principle; and
and the position offset calculating unit is used for calculating the target position offset of the current original image frame relative to the vehicle body in each reference image frame according to each target angle offset and the actual moving distance by adopting an Ackerman steering geometry principle.
Further, the image stitching module comprises:
a pre-storing unit for pre-storing a reference angle offset and a reference position offset;
an intercepted object determining unit, configured to calculate corresponding differences between the reference angle offset and the reference position offset and between the target angle offset and the target position offset, and determine a reference image frame, in which the difference between the target angle offset and the reference angle offset is minimum and the difference between the target position offset and the reference position offset is minimum, as an image frame to be intercepted;
the calculation and interception unit is used for calculating and intercepting the road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
and the splicing unit is used for splicing the road surface image to be intercepted and covering the road surface image to the corresponding position of the motor vehicle body in the current original image frame.
Further, the pulse variation calculating module is further configured to process the second frame to the N-1 th frame of the original image frame by frame, use all original image frames before the current original image frame as reference image frames, and calculate and obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to the wheels in each reference image frame according to the real-time wheel speed pulse.
Further, the apparatus further comprises:
and the wheel speed pulse recording module is connected between the wheel speed pulse monitoring module and the pulse variable quantity calculating module and is used for recording wheel speed pulses corresponding to wheels in the current original image frame.
On the other hand, in order to solve the above further technical problem, an embodiment of the present invention provides the following technical solutions: a method for acquiring an image of a bottom road surface of a motor vehicle comprises the following steps:
extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device of the motor vehicle;
monitoring and outputting real-time wheel speed pulses of each wheel of the motor vehicle when the visibility of the surrounding environment of the motor vehicle is lower than a preset threshold value;
processing original image frames frame by frame from a preset Nth original image frame, and calculating actual wheel speed pulse variable quantity of wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse by taking an adjacent previous N-1 original image frame of the current original image frame as a reference image frame, wherein N is an integer greater than 2;
calculating the target angle offset and the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to the actual wheel speed pulse variable quantity by adopting an Ackerman steering geometry principle; and
and determining image frames to be intercepted from the reference image frames according to the target angle offset and the target position offset, calculating road surface images to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frames to be intercepted, and splicing and covering the road surface images to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
Further, the calculating the target angle offset and the target position offset of the current original image frame relative to the vehicle body in each reference image frame according to the actual wheel speed pulse variation by using the ackermann steering geometry principle specifically includes: calculating the actual moving distance of the current original image frame relative to each wheel in each reference image frame according to the preset moving distance of the wheel under the single wheel speed pulse and the actual wheel speed pulse variable quantity which are prestored;
calculating the target angle offset of the current original image frame relative to the vehicle body in each reference image frame according to each actual moving distance by adopting an Ackerman steering geometry principle; and
and calculating the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to each target angle offset and the actual moving distance by adopting an Ackerman steering geometry principle.
Further, the determining, according to each of the target angle offset and the target position offset, an image frame to be intercepted from each reference image frame, calculating, from the image frame to be intercepted, a road image to be spliced that matches the position of the vehicle body in the current original image frame, and splicing and covering the road image to be intercepted to the corresponding position of the vehicle body in the current original image frame specifically includes:
pre-storing a reference angle offset and a reference position offset;
respectively calculating corresponding difference values of the reference angle offset and the reference position offset as well as the target angle offset and the target position offset, and determining the reference image frame with the minimum difference value of the target angle offset and the reference angle offset and the minimum difference value of the target position offset and the reference position offset as an image frame to be intercepted;
calculating and intercepting a road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
and splicing and covering the road surface image to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
Further, the method further comprises:
and processing the original image frames from the second frame to the (N-1) th frame one by one, taking all original image frames before the current original image frame as reference image frames, and calculating to obtain the actual wheel speed pulse variable quantity of the wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse.
Further, the method further comprises:
and recording wheel speed pulses corresponding to wheels in the current original image frame.
After the technical scheme is adopted, the embodiment of the invention at least has the following beneficial effects: the embodiment of the invention obtains the actual wheel speed pulse variable quantity of the current original image frame relative to the wheels of each reference image frame by calculating according to the real-time wheel speed pulse, further calculates the target angle offset quantity and the target position offset quantity of the current original image frame relative to the vehicle body in each reference image frame according to the actual wheel speed pulse variable quantity by adopting the Ackerman steering geometry principle, calculates the road image to be spliced matched with the vehicle body position in the current original image frame from the image frame to be spliced after determining the image frame to be intercepted from each reference image frame, splices and covers the road image to be intercepted to the corresponding position of the vehicle body in the current original image frame, and avoids detecting and identifying the image to determine the angle offset quantity and the position offset quantity when the visibility of the surrounding environment of the vehicle is low, can effectively acquire the road surface image at the bottom of the motor vehicle.
Drawings
Fig. 1 is a schematic structural block diagram of an alternative embodiment of the vehicle bottom road surface image acquisition device of the motor vehicle of the present invention.
Fig. 2 is a schematic structural block diagram of an offset calculation module according to an alternative embodiment of the vehicle bottom road surface image acquisition device of the motor vehicle of the present invention.
Fig. 3 is a schematic structural block diagram of an image stitching module in an alternative embodiment of the vehicle bottom road surface image acquisition device of the motor vehicle of the present invention.
Fig. 4 is a schematic structural block diagram of another alternative embodiment of the vehicle bottom road surface image acquisition device of the motor vehicle of the present invention.
FIG. 5 is a flowchart illustrating steps of an alternative embodiment of a method for obtaining an image of a bottom surface of a motor vehicle according to the present invention.
Fig. 6 is a detailed flowchart of step S4 in an alternative embodiment of the method for acquiring an image of a bottom road surface of a motor vehicle according to the present invention.
Fig. 7 is a detailed flowchart of step S5 in an alternative embodiment of the method for acquiring an image of a bottom road surface of a motor vehicle according to the present invention.
Detailed Description
The present application will now be described in further detail with reference to the accompanying drawings and specific examples. It should be understood that the following illustrative embodiments and description are only intended to explain the present invention, and are not intended to limit the present invention, and features of the embodiments and examples in the present application may be combined with each other without conflict.
As shown in fig. 1, an alternative embodiment of the present invention provides an image acquiring apparatus 1 for a bottom road surface of a motor vehicle, including: the initialization module 10 is connected with the camera device 3 of the motor vehicle and used for extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device 3;
the wheel speed pulse monitoring module 12 is connected with the wheels 5 of the motor vehicle and is used for monitoring and outputting real-time wheel speed pulses of the wheels 5 when the visibility of the surrounding environment of the motor vehicle is lower than a preset threshold value;
a pulse variation calculating module 14, connected to the wheel speed pulse monitoring module 12 and the initializing module 10, for processing the original image frames frame by frame from a predetermined nth frame original image frame, and calculating to obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse by using the adjacent previous N-1 frames original image frame of the current original image frame as a reference image frame, where N is an integer greater than 2;
an offset calculation module 16, connected to the pulse variation calculation module 14, configured to calculate, according to the actual wheel speed pulse variation, a target angle offset and a target position offset of the current original image frame with respect to the vehicle body in each reference image frame by using an ackerman steering geometry principle; and
and the image splicing module 18 is connected with the offset determining module 16 and is used for determining image frames to be intercepted from the reference image frames according to the target angle offsets and the target position offsets, calculating road images to be spliced matched with the positions of the motor vehicle bodies in the current original image frames from the image frames to be intercepted, and splicing and covering the road images to be intercepted to the corresponding positions of the motor vehicle bodies in the current original image frames.
The embodiment of the invention obtains the actual wheel speed pulse variable quantity of the current original image frame relative to the wheels 5 of each reference image frame by calculating according to the real-time wheel speed pulse, further calculates the target angle offset quantity and the target position offset quantity of the current original image frame relative to the vehicle body in each reference image frame according to the actual wheel speed pulse variable quantity by adopting the Ackerman steering geometry principle, calculates the road image to be spliced matched with the vehicle body position in the current original image frame from the image frame to be spliced after determining the image frame to be intercepted from each reference image frame, splices and covers the road image to be intercepted to the corresponding position of the vehicle body in the current original image frame, and avoids detecting and identifying the image to determine the angle offset quantity and the position offset quantity when the visibility of the surrounding environment of the vehicle is low, can effectively acquire the road surface image at the bottom of the motor vehicle. In particular implementation, it can be understood that, starting from the original image frame of the nth frame, the adjacent previous N-1 frames of the current original image frame are saved as reference image frames, starting from the 1 st frame of the video stream of the panoramic video image, for example: when N is equal to 4, that is, starting from the 4 th frame of the video stream, the 4 th frame is the current original image frame, the original image frame corresponding to the first 3 frames (the 1 st, 2 nd, 3 rd frames of the video stream) of the 4 th frame is taken as the reference image frame, and then the 10 th frame of the video stream is entered, the 10 th frame is the current original image frame, and the original image frame corresponding to the first 3 frames (the 2 nd, 3 rd, 4 th frames of the video stream) of the 10 th frame is taken as the reference image frame, which are sequentially executed, therefore, in the specific design, N may be a set value calculated and measured in advance through a large number of experiments.
In an alternative embodiment of the present invention, as shown in fig. 2, the offset calculation module 16 includes:
a wheel movement distance calculating unit 161 for calculating the actual movement distance of the current original image frame with respect to each wheel 5 in each reference image frame according to the pre-stored predetermined movement distance of the wheel 5 under a single wheel speed pulse and each actual wheel speed pulse variation;
the angle offset calculating unit 163 is used for calculating the target angle offset of the current original image frame relative to the vehicle body in each reference image frame according to each actual moving distance by adopting the ackermann steering geometry principle; and
and a position offset calculation unit 165, configured to calculate, according to each target angle offset and the actual moving distance, a target position offset of the current original image frame with respect to the vehicle body in each reference image frame by using an ackermann steering geometry principle.
In this embodiment, the wheel movement distance calculating unit 161 first calculates the actual movement distance of the current original image frame relative to the wheel 5 in each reference image frame, the angle offset calculating unit 163 calculates the corresponding target angle offset according to each actual movement distance, and the position offset calculating unit 165 calculates the target position offset according to the target angle offset and the actual movement distance.
In the embodiment, the predetermined moving distance d of the wheel 5 under a single wheel speed pulse can be pre-stored, and in the embodiment, for the convenience of calculation, the Δ f of the rear left wheel and the rear right wheel of the motor vehicle are generally calculated respectivelyLeft side ofAnd Δ fRight sideThus, the actual distance D of movement of the current raw image frame of the rear left and right wheels relative to the wheel 5 in the respective reference image frameLeft side of＝△fLeft side ofD and DRight side＝△fRight sideD, and according to the Ackerman steering geometry principle, the target angle offset theta of the current original image frame relative to the automobile body in each reference image frame is equal to (D)Left side of-DRight side)/DWorkshop，DWorkshopRepresenting the axial spacing of the rear left wheel and the rear right wheel of the motor vehicle; at this time, the amount of positional deviation of the vehicle body in the x-axis direction can be calculated
Amount of positional deviation in the y-axis direction
In yet another alternative embodiment of the present invention, as shown in fig. 3, the image stitching module 18 includes:
a pre-storing unit 181 for pre-storing a reference angle offset and a reference position offset;
an intercepted object determining unit 183 configured to calculate corresponding differences between the reference angle offset and the reference position offset and between the target angle offset and the target position offset, and determine a reference image frame in which the difference between the target angle offset and the reference angle offset is the smallest and the difference between the target position offset and the reference position offset is the smallest as an image frame to be intercepted;
the calculating and intercepting unit 185 is configured to calculate and intercept the road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
and the splicing unit 187 is used for splicing and covering the road surface image to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
In this embodiment, after the image frames to be captured are determined from the respective reference image frames by the captured object determining unit 183, the calculating and capturing unit 185 calculates and captures the road surface images to be spliced from the road surface images to be captured according to the target angle offset and the target position offset of the image frames to be captured, and finally the splicing unit 187 splices and covers the road surface images to be captured to the corresponding positions of the vehicle body in the current original image frames, so that the image obtaining efficiency is high, the spliced vehicle bottom road surface images can be effectively obtained, and the reference angle offset and the reference position offset are respectively pre-stored and compared with the target angle offset and the target position offset, because when the vehicle speed of the vehicle is slow, the target angle offset and the target position offset of two consecutive original image frames may be small, if the original image frame from the previous frame at this time is taken as the image frame to be captured, therefore, the reference image frame with the minimum difference between the target angle offset and the reference angle offset and the minimum difference between the target position offset and the reference position offset can be determined as the image frame to be intercepted, the reference angle offset and the reference position offset can be preset, the image frame with the minimum difference between the reference offset and each reference image frame can be selected as the image frame to be intercepted, and the effective vehicle bottom road surface image can be intercepted.
In another alternative embodiment of the present invention, as shown in fig. 4, the pulse variation calculating module 14 is further configured to process the second frame to the N-1 th frame of original image frames frame by frame, use all original image frames before the current original image frame as reference image frames, and calculate and obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to the wheels in the respective reference image frames according to the real-time wheel speed pulses. In the embodiment, the second frame original image frame is processed to the (N-1) th frame original image frame by frame, and all the previous frame original image frames of the current original image frame are used as the reference image frames, so that all the frames before the N-th frame original image frame can effectively form the vehicle bottom road surface pattern, and the image is more smooth when being displayed. As in the above example, when N is 4, N-1 is 3, but when the video stream of the panoramic video image is in the 2 nd to 3 rd frames, since there is no adjacent previous 3 frames (the 2 nd frame has only 1 reference image frame, and the 3 rd frame has 2 reference image frames) as the reference image frames, in this case, the previous frames of the current original image frame are all used as the reference image frames, so as to ensure that the vehicle bottom road surface image can still be obtained when the 2 nd to 3 rd frames of the video stream of the panoramic video image are in the same frame.
In yet another alternative embodiment of the present invention, as shown in fig. 4, the apparatus further comprises:
and the wheel speed pulse recording module 19 is connected between the wheel speed pulse monitoring module 12 and the pulse variation calculating module 14, and is used for recording the wheel speed pulse corresponding to the wheel 5 in the current original image frame. In the embodiment, the wheel speed pulse recording module 19 records the wheel speed pulse corresponding to the wheel 5 in the current original image frame, so that repeated wheel speed pulses corresponding to the wheel 5 in each original image frame do not need to be repeated for multiple times, and the data calculation amount is reduced.
On the other hand, as shown in fig. 5, an embodiment of the present invention provides a method for acquiring an image of a bottom road surface of a motor vehicle, including the following steps:
s1: extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device 3 of the motor vehicle;
s2: monitoring and outputting wheel speed pulses of the individual wheels 5 of the motor vehicle when the visibility of the surroundings of the motor vehicle is below a predetermined threshold value;
s3: processing original image frames frame by frame from a preset Nth original image frame, and calculating actual wheel speed pulse variation of wheels 5 in the current original image frame relative to each wheel 5 in each reference image frame according to the real-time wheel speed pulse by taking an adjacent previous N-1 original image frame of the current original image frame as a reference image frame, wherein N is an integer greater than 2;
s4: calculating the target angle offset and the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to the actual wheel speed pulse variable quantity by adopting an Ackerman steering geometry principle; and
s5: and determining image frames to be intercepted from the reference image frames according to the target angle offset and the target position offset, calculating road surface images to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frames to be intercepted, and splicing and covering the road surface images to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
The embodiment of the invention obtains the actual wheel speed pulse variable quantity of the current original image frame relative to the wheels 5 of each reference image frame through the method according to the real-time wheel speed pulse calculation, further calculates the target angle offset quantity and the target position offset quantity of the current original image frame relative to the vehicle body in each reference image frame according to the actual wheel speed pulse variable quantity by adopting the Ackerman steering geometry principle, calculates the road surface image to be spliced matched with the vehicle body position in the current original image frame from the image frame to be spliced after determining the image frame to be intercepted from each reference image frame, splices and covers the road surface image to be intercepted to the corresponding position of the vehicle body in the current original image frame, and avoids detecting and identifying the image to determine the angle offset quantity and the position offset quantity when the visibility of the surrounding environment of the vehicle is low, can effectively acquire the road surface image at the bottom of the motor vehicle.
In another alternative embodiment of the present invention, as shown in fig. 6, the step S4 specifically includes:
s41: calculating the actual moving distance of the current original image frame relative to each wheel 5 in each reference image frame according to the pre-stored preset moving distance of the wheel 5 under a single wheel speed pulse and each actual wheel speed pulse variable quantity;
s42: calculating the target angle offset of the current original image frame relative to the vehicle body in each reference image frame according to each actual moving distance by adopting an Ackerman steering geometry principle; and
s43: and calculating the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to each target angle offset and the actual moving distance by adopting an Ackerman steering geometry principle.
According to the method, the actual moving distance of the current original image frame relative to the wheel 5 in each reference image frame is calculated, the corresponding target angle offset can be calculated according to each actual moving distance, and the target position offset can be calculated according to the target angle offset and the actual moving distance.
In yet another alternative embodiment of the present invention, as shown in fig. 7, the step S5 specifically includes:
s51: pre-storing a reference angle offset and a reference position offset;
s52: respectively calculating corresponding difference values of the reference angle offset and the reference position offset as well as the target angle offset and the target position offset, and determining the reference image frame with the minimum difference value of the target angle offset and the reference angle offset and the minimum difference value of the target position offset and the reference position offset as an image frame to be intercepted;
s53: calculating and intercepting a road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
s54: and splicing and covering the road surface image to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
In this embodiment, by the above method, after determining the image frames to be captured from the reference image frames, further calculating and capturing the road images to be spliced from the road images to be captured according to the target angle offset and the target position offset of the image frames to be captured, and finally splicing and covering the road images to be captured to the corresponding positions of the vehicle body in the current original image frames, the image acquisition efficiency is high, the spliced vehicle bottom road images can be effectively obtained, and the reference angle offset and the reference position offset are respectively pre-stored and compared with the target angle offset and the target position offset, because when the vehicle speed of the vehicle is slow, the target angle offset and the target position offset of two consecutive original image frames may be very small, if the original image frame of the previous frame is taken as the image frame to be captured, therefore, the reference image frame with the minimum difference between the target angle offset and the reference angle offset and the minimum difference between the target position offset and the reference position offset can be determined as the image frame to be intercepted, the reference angle offset and the reference position offset can be preset, the image frame with the minimum difference between the reference offset and each reference image frame can be selected as the image frame to be intercepted, and the effective vehicle bottom road surface image can be intercepted.
In another optional embodiment of the invention, the method further comprises:
the second frame to the (N-1) th frame of original image frame are processed frame by frame, all original image frames before the current original image frame are used as reference image frames, then the actual wheel speed pulse variation of the wheels 5 in the current original image frame relative to the wheels 5 in each reference image frame is obtained through calculation according to the real-time wheel speed pulse, the second frame of original image frame is processed frame by frame to the (N-1) th frame of original image frame, and all previous frame of original image frames of the current original image frame are used as reference image frames, so that all frames before the N frame of original image frame can effectively form a vehicle bottom road surface pattern, and the images are more smooth in display.
In an optional embodiment of the invention, the method further comprises:
and recording the wheel speed pulse corresponding to the wheel 5 in the current original image frame. The embodiment also records the wheel speed pulse corresponding to the wheel 5 in the current original image frame, so that repeated wheel speed pulses corresponding to the wheel 5 in each original image frame do not need to be repeated for multiple times, and the data calculation amount is reduced.
The functions described in the embodiments of the present invention may be stored in a storage medium readable by a computing device if they are implemented in the form of software functional modules or units and sold or used as independent products. Based on such understanding, part of the contribution of the embodiments of the present invention to the prior art or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device, a network device, or the like) to execute all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. The utility model provides a motor vehicle bottom road surface image acquisition device which characterized in that, the device includes:
the initialization module is connected with a camera device of the motor vehicle and used for extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device;
the wheel speed pulse monitoring module is connected with the wheels of the motor vehicle and used for monitoring and outputting real-time wheel speed pulses of the wheels when the visibility of the surrounding environment of the motor vehicle is lower than a preset threshold value;
a pulse variation calculating module, connected to the wheel speed pulse monitoring module and the initializing module, for processing the original image frames frame by frame from a predetermined nth frame original image frame, and calculating to obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse by taking the adjacent previous N-1 frames of the current original image frame as reference image frames, where N is a positive integer greater than 2;
the offset calculation module is connected with the pulse variation calculation module and used for calculating the target angle offset and the target position offset of the current original image frame relative to the automobile body in each reference image frame according to the actual wheel speed pulse variation by adopting the Ackerman steering geometry principle; and
and the image splicing module is connected with the offset determining module and used for determining image frames to be intercepted from the reference image frames according to the target angle offsets and the target position offsets, calculating road images to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frames to be intercepted, and splicing and covering the road images to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
2. The device for acquiring the image of the bottom road surface of the motor vehicle as claimed in claim 1, wherein the offset calculation module comprises:
the wheel moving distance calculating unit is used for calculating the actual moving distance of the current original image frame relative to the wheels in each reference image frame according to the preset moving distance of the pre-stored wheels under the single wheel speed pulse and the variation of each actual wheel speed pulse;
the angle offset calculation unit is used for calculating the target angle offset of the current original image frame relative to the vehicle body in each reference image frame according to each actual moving distance by adopting an Ackerman steering geometry principle; and
and the position offset calculating unit is used for calculating the target position offset of the current original image frame relative to the vehicle body in each reference image frame according to each target angle offset and the actual moving distance by adopting an Ackerman steering geometry principle.
3. The device for acquiring the image of the underbody pavement of the motor vehicle as claimed in claim 1, wherein the image stitching module comprises: a pre-storing unit for pre-storing a reference angle offset and a reference position offset;
an intercepted object determining unit, configured to calculate corresponding differences between the reference angle offset and the reference position offset and between the target angle offset and the target position offset, and determine a reference image frame, in which the difference between the target angle offset and the reference angle offset is minimum and the difference between the target position offset and the reference position offset is minimum, as an image frame to be intercepted;
the calculation and interception unit is used for calculating and intercepting the road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
and the splicing unit is used for splicing the road surface image to be intercepted and covering the road surface image to the corresponding position of the motor vehicle body in the current original image frame.
4. The apparatus of claim 1, wherein the pulse variation calculating module is further configured to process the second frame to the N-1 th frame of original image frames frame by frame, and use all original image frames before the current original image frame as reference image frames, and then calculate and obtain actual wheel speed pulse variations of the wheels in the current original image frame relative to the wheels in the respective reference image frames according to the real-time wheel speed pulses.
5. The device for acquiring an image of the underbody of a motor vehicle as claimed in claim 4, further comprising:
and the wheel speed pulse recording module is connected between the wheel speed pulse monitoring module and the pulse variable quantity calculating module and is used for recording wheel speed pulses corresponding to wheels in the current original image frame.
6. The method for acquiring the vehicle bottom road surface image of the motor vehicle is characterized by comprising the following steps of:
extracting the original image frames of the motor vehicle under the overlooking visual angle frame by frame from the panoramic video image collected and transmitted by the camera device of the motor vehicle;
processing original image frames frame by frame from a preset Nth original image frame, and calculating actual wheel speed pulse variation of wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse by taking an adjacent previous N-1 original image frame of the current original image frame as a reference image frame, wherein N is a positive integer greater than 2;
calculating the target angle offset and the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to the actual wheel speed pulse variable quantity by adopting an Ackerman steering geometry principle; and
and determining image frames to be intercepted from the reference image frames according to the target angle offset and the target position offset, calculating road images to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frames to be intercepted, and splicing and covering the road images to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
7. The method for acquiring the vehicle bottom road surface image of the motor vehicle as claimed in claim 6, wherein the step of calculating the target angle offset and the target position offset of the current original image frame relative to the vehicle body in each reference image frame according to the actual wheel speed pulse variation by using the ackermann steering geometry specifically comprises:
calculating the actual moving distance of the current original image frame relative to each wheel in each reference image frame according to the preset moving distance of the wheel under the single wheel speed pulse and the actual wheel speed pulse variable quantity which are prestored;
calculating the target angle offset of the current original image frame relative to the vehicle body in each reference image frame according to each actual moving distance by adopting an Ackerman steering geometry principle; and
and calculating the target position offset of the current original image frame relative to the vehicle body of the motor vehicle in each reference image frame according to each target angle offset and the actual moving distance by adopting an Ackerman steering geometry principle.
8. The method for obtaining the vehicle bottom road surface image of the motor vehicle as claimed in claim 6, wherein the determining an image frame to be intercepted from each reference image frame according to each target angle offset and target position offset, calculating a road surface image to be spliced matched with the position of the motor vehicle body in the current original image frame from the image frame to be intercepted, and splicing and covering the road surface image to be intercepted to the corresponding position of the motor vehicle body in the current original image frame specifically comprises:
pre-storing a reference angle offset and a reference position offset;
respectively calculating corresponding difference values of the reference angle offset and the reference position offset as well as the target angle offset and the target position offset, and determining the reference image frame with the minimum difference value of the target angle offset and the reference angle offset and the minimum difference value of the target position offset and the reference position offset as an image frame to be intercepted;
calculating and intercepting a road surface image to be spliced from the road surface image to be intercepted according to the target angle offset and the target position offset of the image frame to be intercepted; and
and splicing and covering the road surface image to be intercepted to the corresponding position of the motor vehicle body in the current original image frame.
9. The method for acquiring the image of the underbody pavement of the motor vehicle as claimed in claim 6, comprising:
and processing the original image frames from the second frame to the (N-1) th frame one by one, taking all original image frames before the current original image frame as reference image frames, and calculating to obtain the actual wheel speed pulse variable quantity of the wheels in the current original image frame relative to each wheel in each reference image frame according to the real-time wheel speed pulse.
10. The method for acquiring the image of the underbody pavement of the motor vehicle as set forth in claim 9, further comprising:
and recording wheel speed pulses corresponding to wheels in the current original image frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011378746.8A CN112614050B (en) | 2020-12-01 | 2020-12-01 | Device and method for acquiring road surface image of motor vehicle bottom |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011378746.8A CN112614050B (en) | 2020-12-01 | 2020-12-01 | Device and method for acquiring road surface image of motor vehicle bottom |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112614050A true CN112614050A (en) | 2021-04-06 |
| CN112614050B CN112614050B (en) | 2024-03-22 |
Family
ID=75228304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011378746.8A Active CN112614050B (en) | 2020-12-01 | 2020-12-01 | Device and method for acquiring road surface image of motor vehicle bottom |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614050B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274342A (en) * | 2017-05-22 | 2017-10-20 | 纵目科技（上海）股份有限公司 | A kind of underbody blind area fill method and system, storage medium, terminal device |
| KR101795652B1 (en) * | 2017-04-12 | 2017-11-09 | 주식회사 누리플랜 | Device for Measuring Visibility for Fog Guardian Device |
| CN108068696A (en) * | 2016-11-17 | 2018-05-25 | 比亚迪股份有限公司 | The display methods and display device of full-view image |
| CN109168071A (en) * | 2018-09-21 | 2019-01-08 | 西安万像电子科技有限公司 | Image processing method and device |
| CN109532714A (en) * | 2017-09-21 | 2019-03-29 | 比亚迪股份有限公司 | Obtain the method and system and vehicle of vehicle base map picture |
| CN110490172A (en) * | 2019-08-27 | 2019-11-22 | 北京茵沃汽车科技有限公司 | Information merges parking stall position compensation method, the system, device, medium parked |
| CN111160070A (en) * | 2018-11-07 | 2020-05-15 | 广州汽车集团股份有限公司 | Vehicle panoramic image blind area eliminating method and device, storage medium and terminal equipment |
-
2020
- 2020-12-01 CN CN202011378746.8A patent/CN112614050B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108068696A (en) * | 2016-11-17 | 2018-05-25 | 比亚迪股份有限公司 | The display methods and display device of full-view image |
| KR101795652B1 (en) * | 2017-04-12 | 2017-11-09 | 주식회사 누리플랜 | Device for Measuring Visibility for Fog Guardian Device |
| CN107274342A (en) * | 2017-05-22 | 2017-10-20 | 纵目科技（上海）股份有限公司 | A kind of underbody blind area fill method and system, storage medium, terminal device |
| CN109532714A (en) * | 2017-09-21 | 2019-03-29 | 比亚迪股份有限公司 | Obtain the method and system and vehicle of vehicle base map picture |
| CN109168071A (en) * | 2018-09-21 | 2019-01-08 | 西安万像电子科技有限公司 | Image processing method and device |
| CN111160070A (en) * | 2018-11-07 | 2020-05-15 | 广州汽车集团股份有限公司 | Vehicle panoramic image blind area eliminating method and device, storage medium and terminal equipment |
| CN110490172A (en) * | 2019-08-27 | 2019-11-22 | 北京茵沃汽车科技有限公司 | Information merges parking stall position compensation method, the system, device, medium parked |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112614050B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107577988B (en) | Method, device, storage medium and program product for realizing side vehicle positioning | |
| US9183449B2 (en) | Apparatus and method for detecting obstacle | |
| CN112614192B (en) | On-line calibration method of vehicle-mounted camera and vehicle-mounted information entertainment system | |
| US11910092B2 (en) | Panoramic look-around view generation method, in-vehicle device and in-vehicle system | |
| US9892519B2 (en) | Method for detecting an object in an environmental region of a motor vehicle, driver assistance system and motor vehicle | |
| JP7107931B2 (en) | Method and apparatus for estimating range of moving objects | |
| CN110705359A (en) | Parking space detection method | |
| US20190122387A1 (en) | Apparatus and method for image processing according to vehicle speed | |
| CN109345591B (en) | Vehicle posture detection method and device | |
| EP2432660B1 (en) | Method and device for extending a visibility area | |
| CN114919584A (en) | Motor vehicle fixed point target distance measuring method and device and computer readable storage medium | |
| US20230249620A1 (en) | Parking process display method and device, and vehicle | |
| CN112598743B (en) | Pose estimation method and related device for monocular vision image | |
| CN108189626B (en) | Tire pressure detection method and device, storage medium and automobile | |
| CN111160070A (en) | Vehicle panoramic image blind area eliminating method and device, storage medium and terminal equipment | |
| WO2021204867A1 (en) | A system and method to track a coupled vehicle | |
| CN112614050A (en) | Device and method for acquiring vehicle bottom road surface image of motor vehicle | |
| CN110827337B (en) | Method and device for determining posture of vehicle-mounted camera and electronic equipment | |
| EP3629292A1 (en) | Reference point selection for extrinsic parameter calibration | |
| US20180352214A1 (en) | Device for Securing a Travel Envelope | |
| CN112888604A (en) | Backward lane detection coverage | |
| CN114898325B (en) | Vehicle dangerous lane change detection method and device and electronic equipment | |
| KR20140088779A (en) | Rear Monitoring Apparatus and Method in Vehicle | |
| CN112270311B (en) | Near-target rapid detection method and system based on vehicle-mounted looking-around back projection | |
| CN112435167B (en) | Device and method for acquiring road surface image of motor vehicle bottom |
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 |