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

A video-based tunnel traffic flow statistics method

A statistical method and traffic flow technology, applied in the field of video-based tunnel traffic statistics, can solve problems such as low precision and easy-to-follow vehicles, and achieve the effects of improved detection accuracy, high robustness, and comprehensive statistical data

Active Publication Date: 2021-11-26
四川九通智路科技有限公司
View PDF20 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the mean shift is tracking the target, the size of the target frame does not change with the change of the target size, which makes the vehicle easy to follow.
The target tracking algorithm based on Kalman filter believes that the motion model of the object obeys the Gaussian model, so as to predict the target motion state, and then compare it with the observation model to update the state of the moving target according to the error. The accuracy of this algorithm is not very high

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
  • A video-based tunnel traffic flow statistics method
  • A video-based tunnel traffic flow statistics method
  • A video-based tunnel traffic flow statistics method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] This embodiment discloses a video-based tunnel traffic statistics method, refer to the description attached figure 1 with figure 2 , this method is based on the camera installed in the tunnel to collect image data, and the stake number information installed by the camera identifies its location, mainly including the following steps:

[0034] A. Data set production

[0035] Obtain a number of video images containing vehicles in the tunnel, convert the collected video images into pictures using Python, and use the labelImg tool to label each picture to obtain the original picture and label data; when labeling, divide the vehicle into three categories, namely cars, trucks and buses, and finally get the original pictures and label data in xml format, and put them into the JPEGImages and Annotations folders respectively; in the process of picture annotation, delete pictures that do not contain vehicles;

[0036] B. Data set division

[0037]Divide the marked pictures in ...

Embodiment 2

[0047] This embodiment discloses a video-based tunnel traffic statistics method. The yolov3 model is mainly composed of two parts, the Darknet-53 feature extraction network and the prediction network. The Darknet-53 feature extraction network obtains a feature map. On the basis of Example 1 , in this embodiment, the feature extraction network in the yolov3 model performs feature extraction on the input picture, and extracts three feature maps of different scales 13×13, 26×26, and 52×52 for prediction (13×13 represents the picture The width and height of the picture are both 13 pixels, 26×26 means that the width and height of the picture are both 26 pixels, and 52×52 means that the width and height of the picture are both 52 pixels), in the vehicle recognition detection model of this application , the size of the picture input to the network model is 416*416*3 (representing the width of the picture is 416 pixels, the height is 416 pixels, and 3 color channels), and each scale ca...

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

This application relates to the technical field of vehicle detection, and discloses a video-based tunnel traffic statistics method, including the following steps: A, data set production; B, data set division; C, building a vehicle identification and detection model based on improved yolov3; D , Vehicle recognition model training; D1, vehicle tracking; D2, traffic flow statistics. This application uses the improved yolov3 network to detect the vehicle in the current frame, which avoids the introduction of noise when using inter-frame information for vehicle recognition. Through feature extraction, the vehicle can be accurately predicted according to the weight and offset of the training, and it is almost unaffected. The impact of vehicle speed has high robustness, and the accuracy of vehicle detection and recognition is high.

Description

technical field [0001] The present application relates to the technical field of vehicle detection, and specifically relates to a video-based tunnel traffic flow statistics method. Background technique [0002] The current methods of traffic flow statistics are mainly based on ultrasonic detection, induction coil detection, microwave detection and video detection. Among them, ultrasonic testing equipment is relatively small and easy to install, but its performance gradually decreases with the influence of ambient temperature and airflow; induction coil testing has the advantages of standardization of product equipment and high detection accuracy, but it needs to dig out the road surface for burial during installation, which will cause problems. Blocking traffic will affect the life of the road surface; microwave detection is simple and convenient to install, will not damage the road surface, can realize all-weather detection, and has strong anti-interference ability, but has...

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 Patents(China)
IPC IPC(8): G06T7/00G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06T7/0002G06N3/08G06T2207/10016G06T2207/20076G06T2207/20081G06T2207/20084G06T2207/30232G06T2207/30236G06T2207/30242G06V20/52G06V10/44G06N3/047G06N3/045G06F18/23213G06F18/2415G06F18/241
Inventor 张蓉申莲莲邓承刚叶琳龚绍杰
Owner 四川九通智路科技有限公司