Particle swarm optimization algorithm-based tracking and locating method for multiple moving targets in video
A particle swarm optimization, multi-moving target technology, applied in the field of image processing, can solve problems such as inability to solve multi-target positioning problems, and achieve the effects of solving stagnation, reducing computing costs, and low spatial resolution
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2017-09-15
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of image processing, in particular to a video multi-moving target tracking and positioning method based on particle swarm optimization algorithm. Background technique
[0002] Particle Swarm Optimization (PSO) is inspired by the regularity of bird cluster activities, and then uses swarm intelligence to establish a simplified model. Based on the observation of the behavior of animal clusters, particle swarm algorithm uses the information sharing of individuals in the group to make the movement of the whole group evolve from disorder to order in the problem solving space, so as to obtain the optimal solution. Similar to genetic algorithm, PSO is an optimization algorithm based on iteration. The system is initialized as a set of random solutions, and the optimal value is searched through iteration. But it does not have the crossover and mutation used by the genetic algorithm, but the particles follow the opti...
Examples
Embodiment Construction
[0033] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0034] Such as figure 1 Shown is the flow chart of the video multi-moving target positioning method based on the particle swarm optimization algorithm, as follows:
[0035] Step 1), select a section of 8046-frame video sequence from the vehicle monitoring video, compress the size to 240x320 pixels, and evenly extract 40 frames of the video at the same time interval. Access each pixel of each frame by row, record the color intensity values of the three channels of each pixel, calculate the grayscale value of each pixel, and convert each frame of image into a two-dimensional matrix, The two-dimensional matrix converted from the i-th frame image is denoted as I i , i∈{1,2,…,40};
[0036] Step 2), sequentially divide each frame of image into speckle pixels and background pixels to obtain the number of speckles and their geometric features, the spe...