Quick search method for target character points of image motion
A moving target and search method technology, which is applied in the field of fast search of image moving target feature points, can solve the problems of large search range, large error, and large amount of calculation in the full search method, and achieves the effect of reducing computational complexity and time complexity.
Active Publication Date: 2013-07-31
CHANGAN UNIV +1
View PDF2 Cites 22 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
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
[0046] Such as Figure 1 to Figure 7 As shown, it is a real-time traffic video image of a road section in Xi'an. The sampling frequency of the video is 25 frames per second, the video image size is 720×288, and the size of each block is 8×6, so each frame of video image is divided into 90× 48 blocks,
[0047] The selected threshold A is 48×20;
[0048] The selected threshold B is 48×20;
[0049] The selected threshold C is 4;
[0050] The selected threshold D is 55;
[0051] Following the above method, the 339th frame to the 355th frame image are processed sequentially.
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 quick search method for target character points of image motion. The quick search method comprises the steps as follows: images are decomposed into image blocks; the sum of the absolute values of the gray scale difference of first frame images, second frame images and the image blocks taking pixels as centers in third frame images and the second frame images is calculated; target blocks are marked, edge detection is carried out, optimum angle points are searched; basic matching templates taking the angle points as centers are built up, matching points are searched out, information of the matching points is saved, and the steps are repeated; the new matching points are predicted, and vehicle driving track lines are obtained; and based on the angle point positions recorded in the previous frame, the positions of the matching points of the targets recorded in the current frame are compared with the angle point positions so as to determine whether the vehicle targets are new. Compared with the prior art, the quick search method for the target character points of the image motion can quickly search and track all the vehicle targets in the video range in a matching manner, can obtain tracking trajectory and effective information rapidly and accurately, and can reduce the computation complexity and time complexity.
Description
technical field [0001] The invention belongs to the field of video detection, and in particular relates to a fast search method for feature points of an image moving target. Background technique [0002] Moving object tracking is a hotspot in the field of computer vision and pattern recognition, and has great prospects in the fields of security monitoring and motion detection. Moving object tracking includes two parts: detection and tracking of moving objects. [0003] The object tracking is to use the characteristics of the moving object, select the appropriate matching and search algorithm, find the position similar to the target, and realize the tracking of the moving object. The most commonly used search method is the full search method. The full search method is to calculate all positions within the search range sequentially, and select the small block most similar to the template as the matching block. This method has high computational complexity, but the highest ac...
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 IPC IPC(8): G06T7/20
Inventor 宋焕生刘雪琴杨媛席阳李建成李东方张鹏宋鹏飞
Owner CHANGAN UNIV
PatSnap Eureka turns technology decisions into work you can execute. Powered by our Innovation Knowledge Graph, it runs expert workflows across engineering, life sciences, materials and intellectual property. Get your review-ready output in minutes.
