Deep learning retrograde motion detection method based on embedded terminal
An embedded terminal and deep learning technology, applied in the field of deep learning retrograde detection, can solve problems such as traffic accidents, achieve the effect of strengthening comprehensive judgment, accurately and automatically identifying the retrograde behavior of traffic vehicles, and improving the accuracy of judgment
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] This embodiment discloses as figure 1 A deep learning retrograde detection method based on an embedded terminal is shown, including the following steps:
[0027] S1 Set the detector area on the road section where the vehicle is traveling in reverse, and divide the detector area into two continuous sub-areas;
[0028] S2 collects two vehicle video images within the preset time slice Δt time range;
[0029] S3 identifies whether there is a vehicle passing through by analyzing and comparing the time sequence of the two images appearing in the detector;
[0030] S4 uses frame counting and boundary detection to identify the movement process of the vehicle, and calibrates the detector area from the beginning to the end;
[0031] S5 recognizes whether the vehicle has retrograde behavior through the relative movement direction of the moving vehicle, and inputs the deep learning neural network as a sample for learning and training;
[0032] S6 judges the occurrence of the veh...
Embodiment 2
[0040] This embodiment discloses a system that does not use the "warning line" method in setting. As long as the historical movement trajectory of the target is determined to be in the prohibited direction, the alarm will be issued. The detector setting uses a sector to mark the movement direction. The position and size of the sector can be passed The software of the system can be set arbitrarily, which is more extensive and practical for expanding applications to other industries.
[0041] Suppose the gray value of the moving target is X, and the gray value of the background pixel is Y, then the movement of the moving target in the detection area is equivalent to a block area moving in the background area of Y, and the area of the moving target A motion boundary is formed in the background area.
[0042] If the target is a vehicle, during the movement, the head and tail of the vehicle form a horizontal boundary, and the two sides of the vehicle form a vertical boundary. T...
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