CN110719474A - Monitoring video secondary compression method based on connected domain analysis - Google Patents
Monitoring video secondary compression method based on connected domain analysis Download PDFInfo
- Publication number
- CN110719474A CN110719474A CN201910992910.5A CN201910992910A CN110719474A CN 110719474 A CN110719474 A CN 110719474A CN 201910992910 A CN201910992910 A CN 201910992910A CN 110719474 A CN110719474 A CN 110719474A
- Authority
- CN
- China
- Prior art keywords
- frame
- moving object
- monitoring video
- background
- current frame
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
- H04N19/137—Motion inside a coding unit, e.g. average field, frame or block difference
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The invention discloses a monitoring video secondary compression method based on connected domain analysis, which relates to the technical field of video data processing, and comprises the steps of obtaining a monitoring video to be compressed, selecting a background frame, detecting that the difference value between the current frame and the background frame exceeds a set threshold value, determining that a moving object exists in the current frame, carrying out connected domain analysis on the current frame after image morphology operation, marking a region where the moving object exists, storing the region where the moving object exists in an image form, simultaneously reserving the frame number and the position of the corresponding current frame, and packaging the background frame and all frames where the moving object exists to complete secondary compression of the monitoring video.
Description
Technical Field
The invention discloses a monitoring video secondary compression method based on connected domain analysis, and relates to the technical field of video data processing.
Background
Video information plays an increasingly important role in the internet era. With the increasing popularization of monitoring equipment, a large amount of video data is generated, the storage space is consumed for long-time uninterrupted video storage, and most of monitoring video data generally contain limited effective information, but occupy a large amount of storage space, so that the long-term storage and use of videos are not facilitated.
The invention discloses a monitoring video secondary compression method based on connected domain analysis, which extracts and retains changed pixels through connected domain analysis based on compressing the pixels with less change among different frames, thereby achieving the purpose of secondary compression. The invention also extracts the background frame by using a method based on multi-frame image fusion, can reduce the storage space of video data under the condition of ensuring effective information retention, and has the possibility of optimizing and improving by using more complicated target detection and stronger expandability.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a monitoring video secondary compression method based on connected domain analysis, which can reduce the storage space of video data under the condition of ensuring effective information retention.
The specific scheme provided by the invention is as follows:
a monitoring video secondary compression method based on connected domain analysis obtains monitoring video to be compressed,
a background frame is selected and a background frame is selected,
detecting that the difference value between the current frame and the background frame exceeds a set threshold value, determining that the current frame has pixels of the moving object, performing connected domain analysis on the current frame after image morphological operation to mark the region where the moving object is located,
the area of the moving object is stored in the form of image, and the frame number and position of the corresponding current frame are retained,
and packaging the background frame and all frames with moving objects to finish secondary compression of the monitoring video.
In the method, a current frame with unchanged background and unchanged visual angle in a certain time is selected as a background frame.
In the method, images of a plurality of current frames of the monitoring video are selected within a certain time, and areas which are not changed in the plurality of images are subjected to multi-image fusion to serve as background frames.
In the method, a minimum rectangular region algorithm is used for marking the region where the moving object is located.
A monitoring video secondary compression tool based on connected domain analysis comprises an acquisition module, a selection module, a detection module and a compression module,
the acquisition module acquires a monitoring video to be compressed,
the selection module selects a background frame from the monitoring video,
the detection module detects that the difference value between the current frame and the background frame exceeds a set threshold value from the monitoring video, the pixel of the moving object exists in the current frame, the connected domain analysis is carried out on the current frame after the image morphological operation, the region where the moving object is located is marked,
the compression module stores the area where the moving object is in an image form, simultaneously reserves the frame number and the position of the corresponding current frame, and packs the background frame and all frames with the moving object to finish secondary compression of the monitoring video.
The selection module in the tool selects a current frame with unchanged background and unchanged visual angle within a certain time as a background frame.
The tool comprises a selecting module, a background frame and a video processing module, wherein the selecting module selects images of a plurality of current frames of a monitoring video within a certain time, and performs multi-image fusion on regions which are not changed in the plurality of images to serve as the background frame.
And the detection module in the tool marks the region of the moving object by using a minimum rectangular region algorithm.
The invention has the advantages that:
the invention provides a monitoring video secondary compression method based on connected domain analysis, which comprises the steps of obtaining a monitoring video to be compressed, selecting a background frame, detecting that the difference value between a current frame and the background frame exceeds a set threshold value, then considering that the current frame has pixels of a moving object, carrying out connected domain analysis on the current frame after image morphological operation to mark the region where the moving object is located, storing the region where the moving object is located into an image form, simultaneously reserving the frame number and the position of the corresponding current frame, and packaging the background frame and all frames where the moving object exists to complete secondary compression of the monitoring video;
the method extracts and retains the changed pixels through connected domain analysis based on compressing the pixels with less change among different frames, thereby achieving the purpose of secondary compression. The invention also extracts the background frame by using a method based on multi-frame image fusion, can reduce the storage space of video data under the condition of ensuring effective information retention, and has the possibility of optimizing and improving by using more complicated target detection and stronger expandability.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
Detailed Description
The invention provides a monitoring video secondary compression method based on connected domain analysis, which is used for obtaining a monitoring video to be compressed,
a background frame is selected and a background frame is selected,
detecting that the difference value between the current frame and the background frame exceeds a set threshold value, determining that the current frame has pixels of the moving object, performing connected domain analysis on the current frame after image morphological operation to mark the region where the moving object is located,
the area of the moving object is stored in the form of image, and the frame number and position of the corresponding current frame are retained,
and packaging the background frame and all frames with moving objects to finish secondary compression of the monitoring video.
In the method, a current frame with unchanged background and unchanged visual angle in a certain time is selected as a background frame.
Meanwhile, a monitoring video secondary compression tool based on connected domain analysis corresponding to the method is provided, which comprises an acquisition module, a selection module, a detection module and a compression module,
the acquisition module acquires a monitoring video to be compressed,
the selection module selects a background frame from the monitoring video,
the detection module detects that the difference value between the current frame and the background frame exceeds a set threshold value from the monitoring video, the pixel of the moving object exists in the current frame, the connected domain analysis is carried out on the current frame after the image morphological operation, the region where the moving object is located is marked,
the compression module stores the area where the moving object is in an image form, simultaneously reserves the frame number and the position of the corresponding current frame, and packs the background frame and all frames with the moving object to finish secondary compression of the monitoring video.
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
When the monitoring video based on connected domain analysis is utilized to carry out secondary compression, the method comprises the following specific processes:
s1: acquiring a monitoring video to be compressed, reading or directly storing the video by taking a frame as a unit,
s2: selecting a background frame, selecting a current frame with unchanged background and unchanged visual angle in a certain time as the background frame, such as selecting a first frame and the like,
or selecting a plurality of images of the current frames of the monitoring video within a certain time, carrying out multi-image fusion on the unchanged areas in the plurality of images to be used as background frames,
s3: the difference value between the current frame and the background frame is made, the difference value between the current frame and the background frame is detected to exceed a set threshold value, then the current frame is considered to have the pixel of the moving object, after the current frame is expanded through image morphology operation, connected domain analysis is carried out, the region where the moving object is located is marked by using a minimum rectangular region algorithm,
s4: the area of the moving object is stored in the form of image, and the information of frame number and position of the corresponding current frame is retained,
s5: and packaging the background frame and all frames with the moving object, and then completing secondary compression of the monitoring video, wherein the packaged background frame and all frames with the moving object can be used as an intermediate file for transmission, and the original video is restored at a receiving end.
In the above method, S3 may also use the target detection in deep learning, such as fast RCNN, YOLO, SSD, etc., to detect the moving object pixels, and keep the moving object and the area, which may also reduce the amount of computation, optimize the accuracy, and improve the efficiency and quality of video compression.
When the monitoring video based on connected domain analysis is utilized to carry out secondary compression, the specific process is as follows:
s1: the acquisition module acquires the monitoring video to be compressed, reads the video in frame unit or directly stores the video,
s2: the selecting module selects a background frame, selects a current frame with unchanged background and unchanged visual angle within a certain time as the background frame, such as a first frame and the like,
or selecting a plurality of images of the current frames of the monitoring video within a certain time, carrying out multi-image fusion on the unchanged areas in the plurality of images to be used as background frames,
s3: the detection module makes a difference value between the current frame and the background frame, detects that the difference value between the current frame and the background frame exceeds a set threshold value, considers that the current frame has pixels of a moving object, performs connected domain analysis after the current frame is expanded through image morphological operation, and marks the region where the moving object is located by using a minimum rectangular region algorithm,
s4: the compression module stores the area of the moving object as an image form, and simultaneously reserves the information of the frame number, the position and the like of the corresponding current frame,
s5: and the compression module packs the background frames and all the frames with the moving objects and then completes secondary compression of the monitoring video, wherein the packed background frames and all the frames with the moving objects can be used as intermediate files for transmission, and the recovery work of the original video is carried out at a receiving end.
In the above tool, the detection module in S3 may also use the target detection in deep learning, such as fast RCNN, YOLO, SSD, and other algorithms to detect the moving object pixels, and keep the moving object and the area, which may also reduce the amount of computation, optimize the accuracy, and improve the efficiency and quality of video compression.
The method of the invention regards the background frame as information with a large redundancy degree, and compresses a section of video to the size of an image under the condition that no interested object moves, thereby reducing the storage space of video data, keeping the original compression ratio of the video and optimizing and improving the quality of the restored video by using more complex target detection under the condition of ensuring the effective information retention.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (8)
1. A monitoring video secondary compression method based on connected domain analysis is characterized in that a monitoring video to be compressed is obtained,
a background frame is selected and a background frame is selected,
detecting that the difference value between the current frame and the background frame exceeds a set threshold value, determining that the current frame has pixels of the moving object, performing connected domain analysis on the current frame after image morphological operation to mark the region where the moving object is located,
the area of the moving object is stored in the form of image, and the frame number and position of the corresponding current frame are retained,
and packaging the background frame and all frames with moving objects to finish secondary compression of the monitoring video.
2. The method as claimed in claim 1, wherein a current frame with no change in background and no change in view angle for a certain time is selected as the background frame.
3. The method as claimed in claim 1, wherein images of a plurality of current frames of the surveillance video are selected within a certain time period, and a region of the plurality of images which is not changed is subjected to multi-image fusion to be used as a background frame.
4. A method as claimed in any one of claims 1 to 3, characterized in that the region of the moving object is marked using a minimum rectangular region algorithm.
5. A monitoring video secondary compression tool based on connected domain analysis is characterized by comprising an acquisition module, a selection module, a detection module and a compression module,
the acquisition module acquires a monitoring video to be compressed,
the selection module selects a background frame from the monitoring video,
the detection module detects that the difference value between the current frame and the background frame exceeds a set threshold value from the monitoring video, the pixel of the moving object exists in the current frame, the connected domain analysis is carried out on the current frame after the image morphological operation, the region where the moving object is located is marked,
the compression module stores the area where the moving object is in an image form, simultaneously reserves the frame number and the position of the corresponding current frame, and packs the background frame and all frames with the moving object to finish secondary compression of the monitoring video.
6. The tool of claim 5, wherein the selection module selects a current frame with unchanged background and unchanged view angle within a certain time as the background frame.
7. The method as claimed in claim 5, wherein the selecting module selects the images of the current frames of the monitored video within a certain time period, and performs multi-image fusion on the unchanged areas of the images to serve as the background frame.
8. A method according to any of claims 5-7, characterized in that the detection module uses a minimum rectangular area algorithm to label the area where the moving object is located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992910.5A CN110719474A (en) | 2019-10-18 | 2019-10-18 | Monitoring video secondary compression method based on connected domain analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910992910.5A CN110719474A (en) | 2019-10-18 | 2019-10-18 | Monitoring video secondary compression method based on connected domain analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110719474A true CN110719474A (en) | 2020-01-21 |
Family
ID=69211907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910992910.5A Pending CN110719474A (en) | 2019-10-18 | 2019-10-18 | Monitoring video secondary compression method based on connected domain analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110719474A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610029A (en) * | 2021-08-13 | 2021-11-05 | 贵州省烟草公司贵阳市公司 | Transmission method and device based on intelligent stripping of target and background in monitoring video |
| CN115314717A (en) * | 2022-10-12 | 2022-11-08 | 深流微智能科技(深圳)有限公司 | Video transmission method, video transmission device, electronic equipment and computer-readable storage medium |
| CN115665359A (en) * | 2022-10-09 | 2023-01-31 | 西华县环境监察大队 | Intelligent compression method for environmental monitoring data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080187219A1 (en) * | 2007-02-05 | 2008-08-07 | Chao-Ho Chen | Video Object Segmentation Method Applied for Rainy Situations |
| CN102724503A (en) * | 2012-06-13 | 2012-10-10 | 广东威创视讯科技股份有限公司 | Video compression method and system |
| CN103037205A (en) * | 2012-12-14 | 2013-04-10 | 广东威创视讯科技股份有限公司 | Method and system of video transmission |
| CN103179402A (en) * | 2013-03-19 | 2013-06-26 | 中国科学院半导体研究所 | Video compression coding and decoding method and device |
| CN104331905A (en) * | 2014-10-31 | 2015-02-04 | 浙江大学 | Surveillance video abstraction extraction method based on moving object detection |
| CN105469425A (en) * | 2015-11-24 | 2016-04-06 | 上海君是信息科技有限公司 | Video condensation method |
-
2019
- 2019-10-18 CN CN201910992910.5A patent/CN110719474A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080187219A1 (en) * | 2007-02-05 | 2008-08-07 | Chao-Ho Chen | Video Object Segmentation Method Applied for Rainy Situations |
| CN102724503A (en) * | 2012-06-13 | 2012-10-10 | 广东威创视讯科技股份有限公司 | Video compression method and system |
| CN103037205A (en) * | 2012-12-14 | 2013-04-10 | 广东威创视讯科技股份有限公司 | Method and system of video transmission |
| CN103179402A (en) * | 2013-03-19 | 2013-06-26 | 中国科学院半导体研究所 | Video compression coding and decoding method and device |
| CN104331905A (en) * | 2014-10-31 | 2015-02-04 | 浙江大学 | Surveillance video abstraction extraction method based on moving object detection |
| CN105469425A (en) * | 2015-11-24 | 2016-04-06 | 上海君是信息科技有限公司 | Video condensation method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610029A (en) * | 2021-08-13 | 2021-11-05 | 贵州省烟草公司贵阳市公司 | Transmission method and device based on intelligent stripping of target and background in monitoring video |
| CN115665359A (en) * | 2022-10-09 | 2023-01-31 | 西华县环境监察大队 | Intelligent compression method for environmental monitoring data |
| CN115314717A (en) * | 2022-10-12 | 2022-11-08 | 深流微智能科技(深圳)有限公司 | Video transmission method, video transmission device, electronic equipment and computer-readable storage medium |
| CN115314717B (en) * | 2022-10-12 | 2022-12-20 | 深流微智能科技(深圳)有限公司 | Video transmission method, video transmission device, electronic equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111681273B (en) | Image segmentation method and device, electronic equipment and readable storage medium | |
| CN110719474A (en) | Monitoring video secondary compression method based on connected domain analysis | |
| Feng et al. | Local background enclosure for RGB-D salient object detection | |
| CN107633526B (en) | Image tracking point acquisition method and device and storage medium | |
| CN111626201B (en) | Commodity detection method, commodity detection device and readable storage medium | |
| CN110781839A (en) | Sliding window-based small and medium target identification method in large-size image | |
| US9569695B2 (en) | Adaptive search window control for visual search | |
| CN111242973A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN106202333A (en) | A kind of method of store in a warehouse Video processing and quick-searching | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN103826109A (en) | Video monitoring image data processing method and system | |
| CN105243395A (en) | Human body image comparison method and device | |
| CN103795920A (en) | Photo processing method and device | |
| JP4496992B2 (en) | Animal up-frame detection method, program, and storage medium storing program, and animal up-shot detection method, animal up-frame or shot detection method, program, and storage medium | |
| EP3376470B1 (en) | Moving body tracking method, moving body tracking device, and program | |
| CN106683040B (en) | Infrared panoramic image splicing method based on NCC algorithm | |
| CN106067157A (en) | The reversible water mark that changing direction difference expansion and synchronizes to embed embeds and extracting method | |
| CN115809982B (en) | Method, device and system for detecting cell crush injury | |
| CN104796580B (en) | A kind of real-time steady picture video routing inspection system integrated based on selection | |
| CN110602504A (en) | Video decompression method and system based on YOLOv2 target detection algorithm | |
| CN115049731B (en) | Visual image construction and positioning method based on binocular camera | |
| CN109543534A (en) | Target loses the method and device examined again in a kind of target following | |
| US20120249837A1 (en) | Methods and Systems for Real-Time Image-Capture Feedback | |
| CN112101134B (en) | Object detection method and device, electronic equipment and storage medium | |
| CN110619626B (en) | Image processing apparatus, system, method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |