Multiple moving target tracking method based on BP neural network
A BP neural network, multi-moving target technology, applied in the field of computer vision, can solve the problems of difficult video retrieval, many false positives and false negatives, and a large amount of garbage data.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0076] Now combined with the accompanying drawings Figure 1-4 , taking ordinary multi-target tracking as an example, the details are as follows: the frame difference method is the time difference method, which uses the inter-frame difference of images that are continuous or separated by a certain number of frames to determine the changing area in the image, so as to detect moving objects. Usually, the frame difference method performs difference operation on two consecutive frames of images or multiple frames of images, and then binarizes and filters the differenced images to detect possible moving areas, thereby detecting moving objects.
[0077] The difference map obtained by the frame difference method can be expressed by the following formula:
[0078] D. k (x,y)=|I k+1 (x,y)-I k (x,y)| (1)
[0079]
[0080] where D k (x,y), I k+1 (x,y), I k (x, y) are the inter-frame difference image, the k+1th frame image and the kth frame image respectively. T k (x, y) is th...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com