Unlock instant, AI-driven research and patent intelligence for your innovation.

Tunnel vehicle type identification method based on video

A type of vehicle identification and video technology, applied in the field of tunnel vehicle identification based on traffic video, to achieve high efficiency and broad application prospects

Inactive Publication Date: 2012-08-15
CHANGAN UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned detectors all have many deficiencies when detecting dynamic vehicle information.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Tunnel vehicle type identification method based on video
  • Tunnel vehicle type identification method based on video
  • Tunnel vehicle type identification method based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] It is known that when the video is being broadcast, two vehicles of different sizes are passing through the same virtual coil (the virtual coil is shown by the gray line at the bottom 1 / 3 of the picture in Figure 1) at different times, as shown in Figure 1, where respectively Figure 1(b) for a large car and Figure 1(a) for a small car. It can also be seen from the two images that there are obvious differences when vehicles of different sizes pass through the same virtual coil, especially in the direction of vehicle height. figure 2 , image 3 is the histogram of the difference between the vehicle height direction and the background when the two vehicles pass through the virtual coil. It can be seen that there are obvious differences in the gray histograms corresponding to large and small vehicles. Generally speaking, the height of the cart (the intersection of the gray line on the right and the horizontal threshold line) is higher than the height of the cart. However,...

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

No PUM Login to View More

Abstract

The invention discloses a tunnel vehicle type identification method based on a video, mainly comprising the following steps of: arranging a virtual coil, wherein a detected video image is a video image when the vehicle passes through the virtual coil; and carrying out subtraction operation on the current frame and a background when the vehicle passes through the virtual coil, so as to obtain a grey level histogram of the vertical height of the vehicle; calculating the height of the vehicle by using the grey level histogram in a vehicle height direction of a frame difference method; and finally, utilizing the vehicle height to judge a vehicle type, namely classifying the vehicle type and dividing the vehicle into three types of big, middle and small types according the size of a vehicle body. The tunnel vehicle type identification method based on the video is mainly used for detecting the vehicle in a tunnel; the method does not consider the factor of a vehicle length due to a special environment in the tunnel and directly utilizes the height to judge the vehicle type; and the tunnel vehicle type identification method based on the video has better high efficiency, practical applicability and convenience, and has a wide application prospect.

Description

technical field [0001] The invention belongs to the technical field of video detection, and in particular relates to a traffic video-based identification method for tunnel vehicles. Background technique [0002] In modern Intelligent Transportation Systems (ITS), many applications place stringent requirements on video detection. It not only requires the ability to automatically detect traffic accidents, count traffic flow, and calculate vehicle speed, but also requires the ability to automatically identify various vehicle models. Currently commonly used vehicle identification facilities include magnetic induction coil detectors, microwave detectors, ultrasonic detectors and infrared detectors. However, the above-mentioned detectors all have many deficiencies when detecting dynamic vehicle information. As a new type of dynamic vehicle information collection facility, the video detector can simultaneously realize the dual functions of traffic video monitoring and traffic flo...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/017G06K9/00
Inventor 宋焕生李晓刘雪琴张辉李文敏杨媛李洁杨孟拓
Owner CHANGAN UNIV