Video image analysis method
A technology of video image and analysis method, applied in the field of video recognition, which can solve the problems of increasing data, difficulty in quickly tracking and identifying moving objects, and low efficiency, so as to achieve good user experience and improve the efficiency of tracking and recognition
Pending Publication Date: 2022-04-08
NANJING THDALE NETWORK TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
When the image range is large and the moving object occupies a small image range, the efficiency of this method is low, and when the video length is large, the data to be processed increases sharply, making it difficult to quickly track and identify moving objects, and the user experience is relatively poor. Low
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
[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0022] According to an embodiment of the present invention, a video image analysis method is provided, figure 1 It is a flow chart of the video moving object tracking and recognition method, including the following steps: receiving a video moving object tracking and recognition instruction, detecting whether the change of two adjacent frames of images exceeds a certain preset change threshold, and if the change exceeds the threshold, issuing a recognition If the ch...
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 provides a video image analysis method, relates to the technical field of video recognition, and is used for efficiently tracking and recognizing video moving objects. The method comprises the following steps: detecting whether the change of two adjacent frames of images exceeds a certain preset change threshold value or not; establishing a moving object tracking grid for extracting spatial features of a moving object; dividing the tracking grid into M regions, detecting whether the change of two adjacent frames of images in each region exceeds a threshold value, and recording the information of the regions exceeding the threshold value; extracting spatial features of a moving object in the video image on the tracking grid, and enabling the spatial features to correspond to time features of the video image; continuing to detect the next frame of image until the change is lower than a threshold value; and tracking and identifying the moving object according to the spatial features and the time features. According to the invention, the tracking identification efficiency of the moving object in the video is greatly improved.
Description
technical field [0001] The invention relates to the technical field of video recognition, in particular to a video image analysis method. Background technique [0002] The tracking and recognition of moving objects in video is one of the most commonly used functions in video processing at present. The existing tracking and recognition technology of moving objects in video usually divides the video into frames and compares the changes of two consecutive frames of images. If the change exceeds a certain A threshold indicates that there is a moving object in the image, and then the moving object is identified by comparing the moving object with the data in the database. When the image range is large and the moving object occupies a small image range, the efficiency of this method is low, and when the video length is large, the data to be processed increases sharply, making it difficult to quickly track and identify moving objects, and the user experience is relatively poor. Lo...
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): G06T7/246G06V20/40G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
Inventor 颜兵
Owner NANJING THDALE NETWORK TECH CO LTD