CN116958196A - Visual extraction parking space tracking anti-shake fusion method and system - Google Patents

Visual extraction parking space tracking anti-shake fusion method and system Download PDF

Info

Publication number
CN116958196A
CN116958196A CN202310717475.1A CN202310717475A CN116958196A CN 116958196 A CN116958196 A CN 116958196A CN 202310717475 A CN202310717475 A CN 202310717475A CN 116958196 A CN116958196 A CN 116958196A
Authority
CN
China
Prior art keywords
parking space
picture frame
frame data
information
list
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310717475.1A
Other languages
Chinese (zh)
Inventor
张龙
雷星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Kotei Informatics Co Ltd
Original Assignee
Wuhan Kotei Informatics Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Kotei Informatics Co Ltd filed Critical Wuhan Kotei Informatics Co Ltd
Priority to CN202310717475.1A priority Critical patent/CN116958196A/en
Publication of CN116958196A publication Critical patent/CN116958196A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • 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
    • 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
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

The invention relates to a vision-extracted parking space tracking anti-shake fusion method and system, wherein the method comprises the following steps: visual extraction is carried out on the parking spaces in each picture frame to obtain picture frame data containing parking space information, and frame number marking is carried out on the picture frame data; sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the corresponding parking space information if the matching is successful, and modifying the successful tracking times and the tracking frame number; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number is modified; when the number of the tracked frames reaches a set maximum threshold, judging whether the number of successful tracking exceeds a set minimum threshold, if so, judging that the parking space corresponding to the parking space ID is a stable parking space; the reliability and safety of the parking system can be improved.

Description

Visual extraction parking space tracking anti-shake fusion method and system
Technical Field
The invention relates to the technical field of automatic parking, in particular to a vision-extracted parking space tracking anti-shake fusion method and system.
Background
The parking system can recognize and extract marked parking spaces around the vehicle through the visual sensor in the parking space searching process, and the marked parking spaces extracted by the visual sensor can have certain precision errors and parking space false detection under the influence of light rays, distortion of the visual sensor, finish degree and integrity of parking space marked lines and other dirty characteristics of the ground.
If the original data of the marked parking space corner extracted by the vision sensor is not tracked and filtered, the situation of shaking and false detection of the fused and output parking space on the parking HMI interface can be caused, and the reliability and safety of a parking system are reduced.
The traditional parking space fusion method is to directly track the frame of the visually extracted parking space, then fusion is carried out according to the judgment mode of whether the parking space is erroneously detected or not according to the number of times of parking space output in a plurality of periods, and although the error detection probability of the fusion output parking space is reduced, the jumping situation of the parking space is not obviously improved.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a vision-extracted parking space tracking anti-shake fusion method and system, which can improve the reliability and safety of a parking system.
According to a first aspect of the invention, a vision-extracted parking space tracking anti-shake fusion method is provided, which comprises the following steps: step 1, obtaining picture frame data containing parking space information after visual extraction of parking spaces in each picture frame, and marking the picture frame data by frames;
step 2, constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information;
the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into the global parking space ID list, and the tracked frame number frame_count is modified;
and 3, judging whether the tracking success times track_count exceeds a set minimum threshold value when the frame number frame_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
On the basis of the technical scheme, the invention can also make the following improvements.
Optionally, the step 1 includes:
step 101, marking each picture frame data with a frame_seq_id;
in specific implementation, the vision sensor acquires real-time picture frames to extract parking spaces, writes the extracted data into a system memory, and marks the picture frame data with frame_seq_id (frame_seq_id self-adding when writing each time).
Step 102, periodically acquiring picture frame data containing frame_seq_id;
step 103, judging whether the frame_seq_id of the current picture frame data is changed from the previous frame, if so, executing step 2, otherwise, not processing.
3. The fusion method of claim 1, further comprising, prior to step 2: determining the direction type of the parking spaces in each picture frame data; the direction type includes: vertical, horizontal and diagonal;
the global parking space ID list includes: a parking space ID list corresponding to each direction type; the step 2 before matching comprises the following steps: and determining the corresponding parking space ID list according to the direction type of the parking space in the picture frame data.
4. The fusion method of claim 1, further comprising, prior to step 2: calculating the center point of the parking space in each picture frame data; the information recorded in the global parking space ID list includes: the center point of the parking space;
the matching process in the step 2 comprises the following steps: and matching the picture frame data with the parking space information and the central point of the parking space in the global parking space ID list by using a Hungary algorithm.
5. The fusion method according to claim 1, wherein in the step 2, in the process of successfully adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID, only the nearest frame_max_count frame is reserved by using a sliding window method, first-in first-out;
and when the matching is unsuccessful, setting the tracking times track_count and frame_count of the parking spaces to be 1, and adding the parking space ID and the parking space information in the picture frame data into the global parking space ID list.
6. The fusion method of claim 1, wherein in step 3,
when judging that the parking space corresponding to the parking space ID is a stable parking space, acquiring parking space frame information corresponding to the tracking success times track_count corresponding to the parking space ID, and performing median filtering to serve as parking space output information referenced by the parking space ID;
and when judging that the parking space corresponding to the parking space ID is an unstable parking space, setting the unstable parking space as false detection, and deleting data corresponding to the parking space ID from the global ID list.
7. The fusion method according to claim 1, wherein after the parking space corresponding to the parking space ID is determined to be a stable parking space in step 3, further comprises: and carrying out mean value filtering on the historical reference parking space output information and the current reference parking space output information of the same parking space ID to realize parking space anti-shake.
According to a second aspect of the present invention, there is provided a vision-extracted parking space tracking anti-shake fusion system, including: the system comprises a vision extraction module, a fusion module and a judgment module;
the visual extraction module is used for obtaining picture frame data containing parking space information after visual extraction of the parking spaces in each picture frame, and marking the number of frames of the picture frame data;
the fusion module acquires the picture frame data from the visual extraction module, and constructs a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information;
the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into the global parking space ID list, and the tracked frame number frame_count is modified;
in specific implementation, when matching is successful, tracking success times track_count++ of the parking space ID and tracking frame_count++; when the current frame is traversed and still is the parking space ID which is not successfully matched, the corresponding tracked frame number frame_count++.
And the judging module is used for judging whether the tracking success times track_count exceeds a set minimum threshold value when the frame number frame_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, and if not, judging that the parking space is an unstable parking space.
According to a third aspect of the present invention, there is provided an electronic device including a memory and a processor, where the processor is configured to implement a step of a fusion method for visually extracting parking space tracking anti-shake when executing a computer management program stored in the memory.
According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer management class program which, when executed by a processor, implements the steps of a fusion method of vision extracted parking space tracking anti-shake.
According to the vision-extracted parking space tracking anti-shake fusion method, system, electronic equipment and storage medium, the situation of false detection of the vision-extracted parking space is filtered, the parking space corner points detected in real time are subjected to smooth anti-shake, more accurate and reliable parking space information is provided for parking planning, and further the reliability and safety of a parking system can be improved.
Drawings
Fig. 1 is a flowchart of an embodiment of a vision-extracted parking space tracking anti-shake fusion method provided by the invention;
fig. 2 is a structural block diagram of vision-extracted parking space tracking anti-shake fusion;
fig. 3 is a schematic hardware structure of one possible electronic device according to the present invention;
fig. 4 is a schematic hardware structure of a possible computer readable storage medium according to the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
The invention belongs to the field of perception fusion in the automatic parking field. The automatic parking core functions comprise the parts of sensing, fusing, positioning, decision planning, controlling and the like of sensor data. The sensing fusion needs to track and filter the characteristics extracted by the sensor, so that the error of the original data of the sensor is reduced. The accuracy and reliability of the data are directly affected by the fusion algorithm, so that the safety and reliability of the parking system are affected.
Fig. 1 is a flowchart of a fusion method for tracking and anti-shake of a parking space by visual extraction, and as shown in fig. 1, the fusion method comprises:
and step 1, obtaining picture frame data containing the parking space information after visual extraction of the parking spaces in each picture frame, and marking the number of frames of the picture frame data.
Step 2, constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information.
The construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number frame_count is modified.
In specific implementation, when matching is successful, tracking success times track_count++ of the parking space ID and tracking frame_count++; when the current frame is traversed and still is the parking space ID which is not successfully matched, the corresponding tracked frame number frame_count++.
And 3, judging whether the number of tracking success times track_count exceeds a set minimum threshold value when the number of tracking frames_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
In particular implementations, the maximum threshold of frame_count, frame_max_count, and the minimum threshold of track_count are both adjustable. Traversing the global ID list, and judging whether the track_count of the successful tracking times is larger than a minimum tracking times threshold value when the frame_count reaches the frame_max_count.
The vision-extracted parking space tracking anti-shake fusion method provided by the invention can improve the reliability and safety of a parking system.
Example 1
The embodiment 1 provided by the invention is an embodiment of a vision-extracted parking space tracking anti-shake fusion method provided by the invention, and as can be known from fig. 1, the embodiment includes:
and step 1, obtaining picture frame data containing the parking space information after visual extraction of the parking spaces in each picture frame, and marking the number of frames of the picture frame data.
In one possible embodiment, step 1 comprises:
step 101, each picture frame data is marked with a frame_seq_id.
In specific implementation, the vision sensor acquires real-time picture frames to extract parking spaces, writes the extracted data into a system memory, and marks the picture frame data with frame_seq_id (frame_seq_id self-adding when writing each time).
Step 102, periodically acquiring picture frame data including frame_seq_id.
In specific implementation, the fusion module periodically acquires from the system memory and performs parking space tracking anti-shake processing on the frame_seq_id.
Step 103, judging whether the frame_seq_id of the current picture frame data changes from the previous frame, if so, executing step 2, otherwise, judging that the output data does not change, and not processing, and avoiding using the data which is not updated to carry out tracking processing when the data is read.
In a possible embodiment, step 2 further includes, before: determining the direction type of the parking spaces in each picture frame data; the direction types include: vertical, horizontal and diagonal.
The global parking space ID list includes: a parking space ID list corresponding to each direction type; the step 2 comprises the following steps before matching: and determining a corresponding parking space ID list according to the direction type of the parking space in the picture frame data.
In a possible embodiment, step 2 further includes, before: calculating the center point of the parking space in each picture frame data; the information recorded in the global parking space ID list includes: and a central point of the parking space.
The matching process in the step 2 comprises the following steps: and matching the picture frame data with the parking space information in the global parking space ID list and the central point of the parking space by using a Hungary algorithm.
And analyzing the current frame visual update according to the parking space type, calculating a center point, and improving the matching efficiency.
Step 2, constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information.
The construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number frame_count is modified.
In a possible embodiment, in step 2, in the process of successfully adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID, a sliding window method is used, and only the nearest frame_max_count frame is reserved in a first-in first-out manner.
And when the matching is unsuccessful, setting the tracking times track_count and frame_count of the parking spaces to be 1, and adding the parking space ID and the parking space information in the picture frame data into a global parking space ID list.
And 3, judging whether the number of tracking success times track_count exceeds a set minimum threshold value when the number of tracking frames_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
In one possible embodiment, in step 3,
when judging that the parking space corresponding to the parking space ID is a stable parking space, acquiring parking space frame information corresponding to the tracking success times track_count corresponding to the parking space ID, performing median filtering, and taking the median filtering as parking space output information referenced by the parking space ID to ensure that the parking space cannot be erroneously detected.
And when judging that the parking space corresponding to the parking space ID is an unstable parking space, setting the unstable parking space as false detection, and deleting data corresponding to the parking space ID from the global ID list.
In a possible embodiment, after determining that the parking space corresponding to the parking space ID is the stable parking space in step 3, the method further includes: and carrying out mean value filtering on the historical reference parking space output information and the current reference parking space output information of the same parking space ID to realize the anti-shake effect of the parking spaces.
Example 2
An embodiment 2 provided by the present invention is an embodiment of a vision-extracted parking space tracking anti-shake fusion system provided by the present invention, and fig. 2 is a structural diagram of a vision-extracted parking space tracking anti-shake fusion system provided by the embodiment of the present invention, and as can be known from fig. 2, the embodiment of the fusion system includes:
the device comprises a visual extraction module, a fusion module and a judgment module.
The visual extraction module is used for obtaining picture frame data containing the parking space information after visual extraction of the parking spaces in each picture frame, and marking the number of frames of the picture frame data.
The fusion module acquires picture frame data from the visual extraction module, constructs a global parking space ID list, and the information recorded in the global parking space ID list comprises: parking space ID and parking space information.
The construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number frame_count is modified.
In specific implementation, when matching is successful, tracking success times track_count++ of the parking space ID and tracking frame_count++; when the current frame is traversed and still is the parking space ID which is not successfully matched, the corresponding tracked frame number is framecount++.
The judging module is used for judging whether the tracking success times track_count exceeds a set minimum threshold value when the frame number frame_count reaches the set maximum threshold value, if yes, judging that the parking space corresponding to the parking space ID is a stable parking space, and if not, judging that the parking space is an unstable parking space.
It can be understood that the vision-extracted parking space tracking anti-shake fusion system provided by the invention corresponds to the vision-extracted parking space tracking anti-shake fusion method provided by the foregoing embodiments, and relevant technical features of the vision-extracted parking space tracking anti-shake fusion system can refer to relevant technical features of the vision-extracted parking space tracking anti-shake fusion method, which are not described herein.
Referring to fig. 3, fig. 3 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 3, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320, wherein the processor 1320 executes the computer program 1311 to implement the following steps: visual extraction is carried out on the parking spaces in each picture frame to obtain picture frame data containing parking space information, and frame number marking is carried out on the picture frame data; constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises the following steps: parking space ID and parking space information; the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number frame_count is modified; when the frame number frame_count of tracking reaches a set maximum threshold, judging whether the number track_count of successful tracking exceeds the set minimum threshold, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
Referring to fig. 4, fig. 4 is a schematic diagram of an embodiment of a computer readable storage medium according to the present invention. As shown in fig. 4, the present embodiment provides a computer-readable storage medium 1400 having stored thereon a computer program 1411, which computer program 1411, when executed by a processor, performs the steps of: visual extraction is carried out on the parking spaces in each picture frame to obtain picture frame data containing parking space information, and frame number marking is carried out on the picture frame data; constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises the following steps: parking space ID and parking space information; the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into a global parking space ID list, and the tracked frame number frame_count is modified; when the frame number frame_count of tracking reaches a set maximum threshold, judging whether the number track_count of successful tracking exceeds the set minimum threshold, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
According to the vision-extracted parking space tracking anti-shake fusion method, system, electronic equipment and storage medium provided by the embodiment of the invention, the situation of false detection of the vision-extracted parking space is filtered, the parking space corner points detected in real time are subjected to smooth anti-shake, more accurate and reliable parking space information is provided for parking planning, and the reliability and safety of a parking system can be further improved.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (10)

1. The utility model provides a vision draws parking stall tracking anti-shake fusion method which characterized in that, the fusion method includes:
step 1, obtaining picture frame data containing parking space information after visual extraction of parking spaces in each picture frame, and marking the picture frame data by frames;
step 2, constructing a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information;
the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into the global parking space ID list, and the tracked frame number frame_count is modified;
and 3, judging whether the tracking success times track_count exceeds a set minimum threshold value when the frame number frame_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, otherwise, judging that the parking space is an unstable parking space.
2. The fusion method of claim 1, wherein step 1 comprises:
step 101, marking each picture frame data with a frame_seq_id;
in specific implementation, the vision sensor acquires real-time picture frames to extract parking spaces, writes the extracted data into a system memory, and marks the picture frame data with frame_seq_id (frame_seq_id self-adding when writing each time).
Step 102, periodically acquiring picture frame data containing frame_seq_id;
step 103, judging whether the frame_seq_id of the current picture frame data is changed from the previous frame, if so, executing step 2, otherwise, not processing.
3. The fusion method of claim 1, further comprising, prior to step 2: determining the direction type of the parking spaces in each picture frame data; the direction type includes: vertical, horizontal and diagonal;
the global parking space ID list includes: a parking space ID list corresponding to each direction type; the step 2 before matching comprises the following steps: and determining the corresponding parking space ID list according to the direction type of the parking space in the picture frame data.
4. The fusion method of claim 1, further comprising, prior to step 2: calculating the center point of the parking space in each picture frame data; the information recorded in the global parking space ID list includes: the center point of the parking space;
the matching process in the step 2 comprises the following steps: and matching the picture frame data with the parking space information and the central point of the parking space in the global parking space ID list by using a Hungary algorithm.
5. The fusion method according to claim 1, wherein in the step 2, in the process of successfully adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID, only the nearest frame_max_count frame is reserved by using a sliding window method, first-in first-out;
and when the matching is unsuccessful, setting the tracking times track_count and frame_count of the parking spaces to be 1, and adding the parking space ID and the parking space information in the picture frame data into the global parking space ID list.
6. The fusion method of claim 1, wherein in step 3,
when judging that the parking space corresponding to the parking space ID is a stable parking space, acquiring parking space frame information corresponding to the tracking success times track_count corresponding to the parking space ID, and performing median filtering to serve as parking space output information referenced by the parking space ID;
and when judging that the parking space corresponding to the parking space ID is an unstable parking space, setting the unstable parking space as false detection, and deleting data corresponding to the parking space ID from the global ID list.
7. The fusion method according to claim 1, wherein after the parking space corresponding to the parking space ID is determined to be a stable parking space in step 3, further comprises: and carrying out mean value filtering on the historical reference parking space output information and the current reference parking space output information of the same parking space ID to realize parking space anti-shake.
8. A vision-extracted parking space tracking anti-shake fusion system, characterized in that the fusion system comprises: the system comprises a vision extraction module, a fusion module and a judgment module;
the visual extraction module is used for obtaining picture frame data containing parking space information after visual extraction of the parking spaces in each picture frame, and marking the number of frames of the picture frame data;
the fusion module acquires the picture frame data from the visual extraction module, and constructs a global parking space ID list, wherein the information recorded in the global parking space ID list comprises: parking space ID and parking space information;
the construction process comprises the following steps: sequentially matching each picture frame data with the parking space information in the global parking space ID list, adding the parking space information in the picture frame data to the parking space information of the corresponding parking space ID if the matching is successful, and modifying the tracking success times track_count and the tracking frame_count; if the matching is unsuccessful, a new parking space ID is allocated for the parking space in the picture frame data, the parking space ID and the parking space information in the picture frame data are added into the global parking space ID list, and the tracked frame number frame_count is modified;
and the judging module is used for judging whether the tracking success times track_count exceeds a set minimum threshold value when the frame number frame_count reaches the set maximum threshold value, if so, judging that the parking space corresponding to the parking space ID is a stable parking space, and if not, judging that the parking space is an unstable parking space.
9. An electronic device, comprising a memory and a processor, wherein the processor is configured to implement the method for merging the vision extracted parking space tracking and anti-shake according to any one of claims 1 to 7 when executing a computer management program stored in the memory.
10. A computer readable storage medium, having stored thereon a computer management class program which, when executed by a processor, implements the steps of the vision extracted parking space tracking anti-shake fusion method according to any one of claims 1 to 7.
CN202310717475.1A 2023-06-15 2023-06-15 Visual extraction parking space tracking anti-shake fusion method and system Pending CN116958196A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310717475.1A CN116958196A (en) 2023-06-15 2023-06-15 Visual extraction parking space tracking anti-shake fusion method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310717475.1A CN116958196A (en) 2023-06-15 2023-06-15 Visual extraction parking space tracking anti-shake fusion method and system

Publications (1)

Publication Number Publication Date
CN116958196A true CN116958196A (en) 2023-10-27

Family

ID=88445265

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310717475.1A Pending CN116958196A (en) 2023-06-15 2023-06-15 Visual extraction parking space tracking anti-shake fusion method and system

Country Status (1)

Country Link
CN (1) CN116958196A (en)

Similar Documents

Publication Publication Date Title
US20210190513A1 (en) Navigation map updating method and apparatus and robot using the same
CN110163107B (en) Method and device for recognizing roadside parking behavior based on video frames
CN109871745A (en) Identify method, system and the vehicle of empty parking space
CN103366250A (en) City appearance environment detection method and system based on three-dimensional live-action data
CN110587597A (en) SLAM closed loop detection method and detection system based on laser radar
CN108122412B (en) Method for monitoring robot to detect vehicle disorderly stop
CN111295666A (en) Lane line detection method, device, control equipment and storage medium
CN113771573B (en) Vehicle suspension control method and device based on identification road surface information
CN112990293A (en) Point cloud marking method and device and electronic equipment
CN114972911A (en) Method and equipment for collecting and processing output data of automatic driving perception algorithm model
CN109241984A (en) Tramway rubbish method for detecting position, computer installation and computer readable storage medium
CN117152949A (en) Traffic event identification method and system based on unmanned aerial vehicle
CN117173669A (en) Picture identification method and system based on artificial intelligence
CN116958196A (en) Visual extraction parking space tracking anti-shake fusion method and system
CN116358528A (en) Map updating method, map updating device, self-mobile device and storage medium
CN115249407B (en) Indicator light state identification method and device, electronic equipment, storage medium and product
CN116028660A (en) Weight value-based image data screening method, system and medium
CN102201166B (en) Preprocessing apparatus for floating car data and method thereof
CN111488771B (en) OCR hooking method, device and equipment
CN112347853A (en) License plate data desensitization method based on video, storage medium and server
CN112598314A (en) Method, device, equipment and medium for determining perception confidence of intelligent driving automobile
CN112906424B (en) Image recognition method, device and equipment
CN116255976B (en) Map fusion method, device, equipment and medium
CN114485689B (en) Road segment segmentation method and device for constructing high-precision map by utilizing crowdsourcing data
CN113129331B (en) Target movement track detection method, device, equipment and computer storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination