A multi-lane traffic flow detection method for complex monitoring scenarios
A vehicle flow detection, multi-lane technology, applied in the field of intelligent transportation system and image processing
Active Publication Date: 2021-11-30
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the above problems, the present invention provides a multi-lane traffic flow detection method for complex monitoring scenarios, using the advantages of deep learning in the face of complex environments, to solve the congestion period in various scenarios, rain and snow Traffic flow statistics in weather, night and other scenarios
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 Construction
[0062] Embodiments of the present invention will be disclosed in the following diagrams. For the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the invention. That is, in some embodiments of the invention, these practical details are not necessary.
[0063] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0064] The present invention is a multi-lane traffic flow detection method aimed at complex monitoring scenes, comprising the following steps:
[0065] Step 1: Obtain real-time surveillance video streams from road traffic surveillance cameras, and use background modeling to extract moving foreground images ;
[0066] Step 2, superimpose multiple frames of foreground images to obtain the approximate driving area, and perform expansion processing on the driving ...
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 multi-lane traffic flow detection method aimed at complex monitoring scenes. The steps are as follows: step 1, obtain a real-time monitoring video stream, and extract a moving foreground image; step 2, obtain a rough driving area, perform expansion processing, and obtain a road area ; Step 3, extract the optical flow vector of the road area, retain the angle information of the optical flow vector and cluster it through the angle information, and obtain the lane segmentation results of different orientations; Step 4, track the vehicles in the image, and obtain the boundaries of each vehicle target frame and track information; step 5, use the vehicle distribution density estimation network to obtain vehicle distribution density information; step 6, obtain the actual vehicle number based on the distribution density information; step 7, delineate the virtual detection line, and count the vehicles to obtain the traffic flow statistics result. The invention detects the traffic flow in the scene by combining multi-target tracking and the vehicle distribution density heat map, and improves the vehicle detection accuracy in the complex congestion scene.
Description
technical field [0001] The invention relates to the technical field of intelligent transportation system and image processing technology, and specifically discloses a multi-lane traffic flow detection method for complex monitoring scenes. Background technique [0002] With the continuous development and expansion of modern cities, the number of urban motor vehicles has increased year by year. According to the statistics of the Ministry of Public Security, in 2019, there were 32.14 million newly registered motor vehicles nationwide, and the number of motor vehicles nationwide reached 348 million. All kinds of congestion caused by accidents, complex traffic scenes or abnormal weather are becoming more and more common. At the same time, the huge amount of data information brought by vehicles and traffic roads provides basic information resources for the construction of urban smart transportation systems, and also accelerates the development of the system. The urgent need for co...
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): G08G1/065G06K9/00G06K9/46G06K9/62G06N3/08
CPCG08G1/0125G08G1/0137G08G1/065G06N3/08G06F18/23G06F18/214
Inventor 吴聪朱凌志李晓飞
Owner NANJING UNIV OF POSTS & TELECOMM