Multi-camera time alignment method and system for networking monitoring video analysis
A video analysis and network monitoring technology, applied in the field of network monitoring video analysis, can solve the problems of inconsistent frame rate and inconsistent start time, and achieve the effect of reducing construction cost, improving video look and feel, and eliminating asynchronous phenomenon.
Active Publication Date: 2020-08-25
WUHAN UNIV
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
But due to reasons such as IO and network delays
The saved offline videos may have the same duration but inconsistent start time, and the actual frame rate may be inconsistent with the set frame rate
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0043] like figure 1 As shown, a multi-camera time alignment method for network surveillance video analysis includes the following steps:
[0044] 1) Pull the video stream from the surveillance camera and save it as a fixed-time offline video;
[0045] 2) Use the offline video to make a timestamp data set, perform image recognition at the corresponding monitoring time position of each frame of the video, and obtain the corresponding timestamp of each frame of the video;
[0046] The process is as follows: First, determine the pixel position of the time stamp on the camera screen, and collect a number every certain time As...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-camera time alignment method and system for networking monitoring video analysis, and the method comprises the steps: 1), pulling a video stream from a monitoring camera, and storing the video stream in the form of an offline video with a fixed duration; 2) making a timestamp data set by using the offline video, and performing image identification at the corresponding monitoring time position of each frame of the video to obtain a timestamp corresponding to each frame of the video; 3) determining the frame rate per second of the offline video, enabling the timestamp of each frame of the video to be accurate to milliseconds, and storing the timestamp result of each frame of the video as a timestamp file of the video in a frame number timestamp form; 4) completing alignment of playing starting time of the multiple cameras; and 5) in the process of simultaneously playing multiple videos, controlling the videos to be played synchronously. According to the method, the corresponding timestamps are extracted from the video frames and are accurate to milliseconds, the problem of desynchrony of video playing is solved, and the method is of great significancein reducing the server building cost and improving the video impression.
Description
technical field [0001] The invention relates to network monitoring video analysis technology, in particular to a multi-channel camera time alignment method and system for network monitoring video analysis. Background technique [0002] With the improvement of intelligence in the security industry, more and more security products need to use computer vision technology (such as: pedestrian detection, multi-target tracking, pedestrian re-identification, etc.) to analyze the monitoring screen, and use a server Simultaneously completing the work of pulling video streams from the camera and analyzing the video not only has extremely high requirements on the computing power of the server, but also is not convenient for data storage. Therefore, it is more efficient to put the work of decoding the camera data and analyzing the decoded video on separate servers. But due to reasons such as IO and network latency. The saved offline videos may have the same duration but different start...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04J3/06G06K9/20G06K9/62G06N3/04H04N7/18
CPCH04J3/0661G06N3/04H04N7/181G06V10/22G06V10/751G06V30/10G06F18/214
Inventor 梁超沈宇轩朱家伟
Owner WUHAN UNIV