Method for detecting parking in expressway tunnel
A technology for expressway and parking detection, which is applied in the traffic control system of road vehicles, traffic flow detection, closed-circuit television system, etc., and can solve the problems that cannot be improved
Active Publication Date: 2021-04-30
TAIYUAN UNIV OF TECH
View PDF5 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
On the basis of traditional image processing methods, the convolutional neural network model is introduced to identify vehicles, which overcomes the false detection caused by light interference to a certain extent, but it cannot fundamentally improve vehicle detection.
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
[0066] The present invention proposes a parking detection method in expressway tunnels based on improved YOLOv3, which overcomes the deficiencies of the prior art, provides a high-precision parking detection method, and provides a good guarantee for the traffic safety of expressway tunnels .
[0067] The invention utilizes the video images captured in real time in expressway tunnels to conduct research on parking detection. This research comes from the actual needs of expressway tunnel management in a certain province. Compared with open-air environments, the unique nature of highway tunnels makes parking detection behavior more difficult. These include:
[0068] (1) Vehicles with different distances from the camera have significantly different sizes in the picture, especially when large vehicles are at a short distance and small vehicles are at a long distance.
[0069] (2) Interferences such as car lights, ambient lighting, and reflected light from the road surface affect t...
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 relates to the field of parking detection in an expressway tunnel. The invention relates to a method for detecting parking in a highway tunnel, and the method comprises the following steps: photographing the interior of the highway tunnel in real time to obtain a monitoring video, establishing a vehicle detection model, making a data set, inputting the monitoring video into the vehicle detection model, and detecting the parking of a vehicle in the tunnel by using a parking detection algorithm, wherein the vehicle detection model adopts a YOLOv3-TunnelVehicle network structure, and the YOLOv3-TunnelVehile network structure is an improved network structure on the basis of the YOLOv3 network structure. According to the invention, the parking detection task can be well completed in the expressway tunnel, the parking detection efficiency is further improved, and more intellectualization and high efficiency are given to an expressway management system.
Description
technical field [0001] The invention relates to the field of parking detection in expressway tunnels. Background technique [0002] With the rapid development of expressway construction, the operating mileage of expressway tunnels continues to increase, bringing a lot of convenience to people. However, due to the narrow space, certain airtightness, and limited light in the tunnel, the highest proportion of traffic accidents occurred in expressway tunnels. Therefore, parking detection in expressway tunnels is very necessary, and it is of great significance to promote the intelligent development of expressway tunnel management systems. [0003] In the initial stage of detection research based on video images, the research mainly focused on the traditional image processing direction and most of them were aimed at open-air scenes. In 2007, a Peripheral multi-target tracker was proposed to determine the foreground of each vehicle from the background subtraction. position, but t...
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 IPC IPC(8): H04N7/18G08G1/01G06K9/00G06K9/62G06N3/04G06T7/277G06T7/73
CPCH04N7/18G08G1/0104G06T7/277G06T7/75G06T2207/10016G06T2207/20081G06T2207/20084G06V20/52G06V2201/08G06V2201/07G06N3/045G06F18/23213G06F18/253G06F18/214
Inventor 丁洁范绪阁杨祖莨
Owner TAIYUAN UNIV OF TECH