Pedestrian counting method based on deep neural network
A deep neural network and pedestrian counting technology, which is applied in the field of pedestrian counting based on deep neural network, can solve the problems of expensive professional equipment procurement, fixed detection scenarios, and decreased detection accuracy, achieving high practical application value and monitoring environmental impact Small, real-time effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0024] figure 1 It is the basic flow chart of the pedestrian counting method based on the deep neural network. First, the video stream is processed to obtain the video frame image, and then the pedestrian detection is performed, and the detected pedestrian frame is sent to the tracker to obtain the tracking frame. According to the center of the pedestrian tracking frame The change of point coordinates judges the direction of pedestrian movement and whether the center point is in the counting area for counting judgment. Specific steps are as follows:
[0025] 1. Use the webcam to obtain video frame images.
[0026] Obtain RTSP stream from the network camera and parse it into available video frame images. The traditional method uses CPU software. In order to reduce the pressure on the CPU, this embodiment uses the GPU hard solution through the ...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap