Road pedestrian event detection method based on video
A technology for event detection and pedestrians, which is applied in the field of road pedestrian event detection based on traffic video, can solve the problems of not meeting the real-time detection requirements, complicated video data processing process, poor reliability, etc., and achieves short detection time, high accuracy, easy-to-achieve effects
Inactive Publication Date: 2014-04-30
CHANGAN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although these methods can realize the alarm of pedestrian events, the processing process of video data is complicated, the reliability is poor, and it cannot meet the real-time requirements of detection and the requirements of practical applications.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0053] It is known that when the video is being broadcast, the pedestrian target appears completely in the first frame of image for the first time, such as figure 1 As shown, Figure 4 Is the second frame of image, Image 6 This is the 40th frame image. In the embodiment, the sampling frequency of the video during the processing is 25 frames per second, the frame image size is 720×288, and the size of each area is 8×6. The frame image is divided into 90×48 block areas, and the target area is binarized The segmentation threshold is 576, and the first frame to the fortieth frame of images are processed sequentially according to the method of the present invention.
[0054] From Figure 7 It can be seen that the white boxes in the figure are the boundaries of the pedestrians marking the targets in the first frame to the fortieth frame, and the white boxes containing the binarized marking targets are the boundaries of the marking targets in the fortieth frame. The pedestrian target ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a road pedestrian event detection method based on a video. The road pedestrian event detection method mainly comprises three steps as follows: based on binary segmentation of blocks, separating a target background in each frame of image in the video to be processed; based on the joint domain marks of the blocks, separating pedestrian targets through the profile characteristics of the marked targets, and recording the gravity center position information of the pedestrian targets at the same time; and based on the gravity center position characteristics, matching and calculating the speed of the pedestrian targets so as to judge whether the pedestrians pass through the road or not. Compared with the prior art, the road pedestrian event detection method can detect all the pedestrian targets in the video range and judge the real-time video, has the advantages of no environmental limit, short detection time, easiness in realization, higher accuracy and wide application prospect, and is suitable for real-time pedestrian event detection.
Description
Technical field [0001] The invention belongs to the technical field of video detection, and specifically relates to a road pedestrian incident detection method based on traffic video. Background technique [0002] Road pedestrian incidents refer to the behavior of pedestrians entering the motor vehicle lane without any protection measures, which interferes with the normal driving of motor vehicles. Although the traffic control department has taken measures, pedestrian intrusion into the motor vehicle lane has occurred from time to time, especially in urban traffic, this phenomenon is particularly obvious. This kind of traffic behavior is very dangerous, it is easy to cause traffic jams, and even lead to traffic accidents, bringing inconvenience and danger to people's lives. Traditional pedestrian incident detection methods mainly include temperature detection methods, electronic coil detection methods, and digital video detection methods. Among them, the temperature detection m...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/00
Inventor 宋焕生付洋朱小平杨孟拓陈艳刘童施春宁赵倩
Owner CHANGAN UNIV