CN115423850A - Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area - Google Patents
Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area Download PDFInfo
- Publication number
- CN115423850A CN115423850A CN202210908147.5A CN202210908147A CN115423850A CN 115423850 A CN115423850 A CN 115423850A CN 202210908147 A CN202210908147 A CN 202210908147A CN 115423850 A CN115423850 A CN 115423850A
- Authority
- CN
- China
- Prior art keywords
- shaking
- area
- track
- filtering
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/273—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion removing elements interfering with the pattern to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an anti-interference high-altitude parabolic capturing method for automatically filtering a shaking target area, which comprises the following steps of: s10, identifying area division; s20, performing a foreground modeling algorithm on the divided areas; s30, automatically updating and generating a shaking area in a circulating manner, and eliminating interference objects according to the number and the shaking areas combined with the intersection; s40, tracking the parabola; and S50, generating a parabolic track. The interference objects are generated and eliminated through the cyclic updating of the shaking area, and the interference of the interference objects is further eliminated according to the parabolic track, so that the method has substantial significance for capturing the parabolic track.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an anti-interference high-altitude parabolic capturing method for automatically filtering a shaking target area.
Background
At present, traditional high-altitude parabolas all have methods for drawing or generating building areas, but still have high requirements for the installation position and content of a camera, and do not allow the blocking of areas such as trees or other vegetation which are easy to shake, although some algorithms provide a target filtering algorithm, the shaking of objects in practical application still can seriously interfere with a parabolic tracking algorithm, so that the overall parabolic monitoring effect is influenced.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an anti-interference high-altitude parabolic capturing method for automatically filtering a shaking target area.
The technical scheme adopted by the invention for solving the technical problem is as follows: the improvement of an anti-interference high-altitude parabolic capturing method for automatically filtering a shaking target area is characterized by comprising the following steps of:
s10, accessing a camera address, extracting a single-frame picture and drawing an identification area;
s20, accessing a video stream, obtaining each single-frame picture in the video stream, cutting to obtain an identification area, then using a foreground modeling algorithm to the picture, performing ecological transformation on a modeling mask and generating a target identification frame;
s30, judging whether a shaking area exists according to the number of the target identification frames, if so, initializing a shaking area mask and an original mask, continuously counting the number of foreground and background for a period of time based on the input mask, generating a shaking mask area, performing morphological operations such as opening and closing operations on the generated shaking area, merging the adjacent or wrapped shaking areas, outputting the automatically generated shaking area mask, and circularly repeating the steps after shielding the shaking area by using the generated shaking area mask;
s40, establishing a tracker for each target identification frame, establishing a speed model by using Kalman filtering, and predicting a target track result;
s50, updating the tracker by using the predicted track result and the real track result in matching based on the IOU, outputting the result, judging whether the tracking object is an interference object according to the number of continuous unmatched successful frames, and filtering out a target identification frame which is judged to be the interference object;
and S60, drawing the track result of the target identification frame conforming to the predicted track result into the picture and the stored video for output.
In the above technical solution, in the step S20, each acquired single-frame picture is subjected to noise removal, blur removal, picture binarization and image gray scale operation.
In the above technical solution, in the step S30, the continuous shaking area needs to be filtered according to the intersection of the shaking areas to eliminate the interference of weeds or leaves.
In the above technical solution, the track generation in step S60 includes the following steps:
s601, inputting a tracking result;
s602, establishing a track model for the same tracker;
s603, when the track is not updated for a long time, defining the track as ending;
s604, filtering tracks with insufficient track quantity and wrong direction;
s605, judging whether the track meets small shaking or not based on MSE, and filtering part of irregular tracks such as mosquitoes, birds and the like;
and S606, drawing the result into the picture and the stored video and outputting the result.
In the above technical solution, the foreground algorithm in the step S20 is a GMM or VIBE algorithm.
The invention has the beneficial effects that: the method carries out an algorithm for automatically generating the area easy to misreport in the existing drawing area, such as the swaying of the leaves blown by wind, the crown of a tree and the like, fundamentally solves a series of performance reduction caused by the swaying of the tree or other objects in the algorithm area through the superposition of masks, and has substantial significance for capturing the parabolic track.
Drawings
FIG. 1 is a flow chart of an anti-interference high-altitude parabolic capturing method for automatically filtering a shaking target area according to the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
The conception, the specific structure and the technical effects produced by the present invention will be clearly and completely described in conjunction with the embodiments and the attached drawings, so as to fully understand the objects, the features and the effects of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and other embodiments obtained by those skilled in the art without inventive efforts are within the protection scope of the present invention based on the embodiments of the present invention. In addition, all the connection/connection relations referred to in the patent do not mean that the components are directly connected, but mean that a better connection structure can be formed by adding or reducing connection auxiliary components according to specific implementation conditions. All technical characteristics in the invention can be interactively combined on the premise of not conflicting with each other.
Referring to fig. 1, as shown in the figure, the present invention provides an anti-interference high altitude parabolic capturing method for automatically filtering a shaking target area, comprising the following steps:
s10, accessing the camera address, extracting a single-frame picture, drawing an identification area, and dividing the identification area.
S20, accessing a video stream, obtaining each single-frame picture in the video stream, performing noise removal, fuzzy removal, picture binaryzation and image gray level operation on each obtained single-frame picture, cutting to obtain an identification area, then using a foreground modeling algorithm for the picture, wherein the foreground modeling algorithm is a VIBE algorithm, performing ecological transformation on a modeling mask and generating a target identification frame.
S30, judging whether a shaking area exists according to the number of the target identification frames, if so, initializing a shaking area mask with the same size as an original mask, generating and recording the existing shaking area, continuously counting the number of foreground and background for a period of time based on the input mask, generating the shaking area mask, performing morphological operations such as opening and closing operations on the generated shaking area, merging the adjacent or wrapped shaking areas, filtering the continuous shaking area according to the intersection of the shaking areas, eliminating the interference of weeds or leaves, outputting the automatically generated shaking area mask, shielding the shaking area by using the generated shaking area mask, and then repeating the steps in a circulating manner, updating the shaking area in a circulating manner, and automatically and circularly updating the generated shaking area.
And S40, establishing a tracker for each target identification frame, establishing a speed model by using Kalman filtering, and predicting a target track result.
S50, matching based on the IOU is carried out by using the predicted track result and the real track result to update the tracker, the result is output, whether the tracking object is an interference object or not is judged according to the number of frames which are continuously unmatched successfully, the tracking object is regarded as the interference object if three continuous frames are unmatched successfully, and the target identification frame which is judged to be the interference object is filtered.
And S60, drawing the track result of the target identification frame conforming to the predicted track result into the picture and the stored video for output.
Through the superposition of the mask, a series of performance reduction caused by the shaking of trees or other objects in the algorithm area is fundamentally solved.
The track generation in step S60 includes the following steps:
s601, inputting a tracking result.
And S602, establishing a track model for the same tracker.
And S603, defining the track to be ended when the track is not updated for a long time.
And S604, filtering tracks with insufficient track quantity and wrong direction.
S605, judging whether the track meets the requirements of small shaking and filtering irregular tracks such as partial mosquitoes, birds and the like based on MSE.
And S606, drawing the result into the picture and the stored video and outputting the result.
Drawing the tracking result into a picture and a video for output, and further eliminating the interferents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. An anti-interference high-altitude parabolic capturing method capable of automatically filtering a shaking target area is characterized by comprising the following steps of:
s10, accessing an address of a camera, extracting a single-frame picture and drawing an identification area;
s20, accessing a video stream, obtaining each single-frame picture in the video stream, cutting to obtain an identification area, then using a foreground modeling algorithm to the picture, performing ecological transformation on a modeling mask and generating a target identification frame;
s30, judging whether a shaking area exists according to the number of the target identification frames, if so, initializing a shaking area mask and an original mask, continuously counting the number of foreground and background for a period of time based on the input mask, generating a shaking mask area, performing morphological operations such as opening and closing operations on the generated shaking area, merging the adjacent or wrapped shaking areas, outputting the automatically generated shaking area mask, and circularly repeating the steps after shielding the shaking area by using the generated shaking area mask;
s40, establishing a tracker for each target identification frame, establishing a speed model by using Kalman filtering, and predicting a target track result;
s50, updating the tracker by using the predicted track result and the real track result in matching based on the IOU, outputting the result, judging whether the target is an interferent or not according to the number of continuous unmatched successful frames, and filtering a target identification frame which is judged to be the interferent;
and S60, drawing the track result of the target identification frame conforming to the predicted track result into the picture and the stored video for output.
2. The anti-interference high-altitude parabolic capturing method for automatically filtering the shaking target area according to claim 1, wherein the method comprises the following steps: in the step S20, each acquired single-frame picture is subjected to noise removal, blur removal, picture binarization and image grayscale operations.
3. The anti-interference high-altitude parabolic capturing method for automatically filtering the shaking target area according to claim 1, characterized in that: in step S30, the continuous shaking area needs to be filtered according to the intersection of the shaking areas to eliminate the interference of weeds or leaves.
4. The anti-interference high-altitude parabolic capturing method for automatically filtering the shaking target area according to claim 1, characterized in that: the track generation in step S60 includes the following steps:
s601, inputting a tracking result;
s602, establishing a track model for the same tracker;
s603, when the track is not updated for a long time, defining the track as ending;
s604, filtering tracks with insufficient track quantity and wrong direction;
s605, judging whether the track meets small shaking or not based on MSE, and filtering part of irregular tracks such as mosquitoes, birds and the like;
and S606, drawing the result into the picture and the stored video and outputting the result.
5. The anti-interference high-altitude parabolic capturing method for automatically filtering the shaking target area according to claim 1, characterized in that: the foreground algorithm in the step S20 is a GMM or VIBE algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210908147.5A CN115423850A (en) | 2022-07-29 | 2022-07-29 | Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210908147.5A CN115423850A (en) | 2022-07-29 | 2022-07-29 | Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115423850A true CN115423850A (en) | 2022-12-02 |
Family
ID=84196238
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210908147.5A Pending CN115423850A (en) | 2022-07-29 | 2022-07-29 | Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115423850A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116597340A (en) * | 2023-04-12 | 2023-08-15 | 深圳市明源云科技有限公司 | High altitude parabolic position prediction method, electronic device and readable storage medium |
CN116994201A (en) * | 2023-07-20 | 2023-11-03 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
-
2022
- 2022-07-29 CN CN202210908147.5A patent/CN115423850A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116597340A (en) * | 2023-04-12 | 2023-08-15 | 深圳市明源云科技有限公司 | High altitude parabolic position prediction method, electronic device and readable storage medium |
CN116597340B (en) * | 2023-04-12 | 2023-10-10 | 深圳市明源云科技有限公司 | High altitude parabolic position prediction method, electronic device and readable storage medium |
CN116994201A (en) * | 2023-07-20 | 2023-11-03 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
CN116994201B (en) * | 2023-07-20 | 2024-03-29 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11263434B2 (en) | Fast side-face interference resistant face detection method | |
CN115423850A (en) | Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area | |
CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
CN111583198A (en) | Insulator picture defect detection method combining FasterR-CNN + ResNet101+ FPN | |
CN101826228B (en) | Detection method of bus passenger moving objects based on background estimation | |
CN102663362B (en) | Moving target detection method based on gray features | |
CN102034240A (en) | Method for detecting and tracking static foreground | |
CN110659546B (en) | Illegal booth detection method and device | |
CN112329832B (en) | Passive positioning target track data enhancement method and system based on deep convolution generation countermeasure network | |
CN110599458A (en) | Underground pipe network detection and evaluation cloud system based on convolutional neural network | |
CN115797775A (en) | Intelligent illegal building identification method and system based on near-earth video image | |
CN115935144A (en) | Denoising and reconstructing method for operation and maintenance data | |
CN113280820B (en) | Orchard visual navigation path extraction method and system based on neural network | |
CN112699836A (en) | Segmentation method and device for low-altitude paddy field image and electronic equipment | |
CN116886869A (en) | Video monitoring system and video tracing method based on AI | |
CN110135224B (en) | Method and system for extracting foreground target of surveillance video, storage medium and terminal | |
CN115511921A (en) | High-precision real-time parabolic track generation method based on cascade matching | |
CN111127355A (en) | Method for finely complementing defective light flow graph and application thereof | |
CN115761580A (en) | Detection method of water surface floater, edge calculation terminal and storage medium | |
CN113284135B (en) | SAR ship detection method based on global and local context information | |
CN104732558A (en) | Moving object detection device | |
CN115862021B (en) | Automatic hydropower station gate identification method based on YOLO | |
CN113642608B (en) | Human-shaped target segmentation method based on convolutional neural network | |
CN112464928B (en) | Digital meter reading identification method, device, equipment and storage medium | |
CN118279834A (en) | Intelligent safety monitoring system based on visual identification |
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 |