驾驶行为的确定方法、装置、存储介质及电子装置
By performing object detection and key point extraction on images, it can determine whether motor vehicles and pedestrians are in the same depth of field. By using neural networks to analyze image changes, it solves the problem of low efficiency in judging uncivilized driving behavior in existing technologies and achieves efficient and accurate behavior recognition.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG DAHUA TECH CO LTD
- Filing Date
- 2022-12-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for identifying uncivilized driving behavior are inefficient, especially in rainy weather when motor vehicles splash pedestrians or non-motorized vehicles, making it difficult to make efficient judgments and consuming a lot of manpower.
By performing object detection and key point extraction on the current frame image, it is determined whether the first type of object and the second type of object are located in the same depth range. The detection box and key points are used to determine the local image, and the image changes are analyzed by neural network to determine whether there is uncivilized driving behavior.
It improves the efficiency of judging uncivilized driving behavior, reduces the reliance on manual analysis, and achieves efficient and accurate behavior recognition.
Smart Images
Figure CN115797880B_ABST