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

Real-time vehicle detection and trajectory tracking method in traffic video based on deep learning

A technology for vehicle detection and trajectory tracking, which is applied in instrumentation, calculation, character and pattern recognition, etc. It can solve the problems of inability to classify vehicles, high missed detection rate, poor robustness, etc., and achieve good feature extraction quality and low missed detection rate. , to meet the effect of vehicle detection and continuous tracking

Active Publication Date: 2022-05-03
TONGJI UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a real-time vehicle detection and trajectory tracking method in traffic video based on deep learning, which solves the problems of poor robustness, high missed detection rate and inability to classify vehicles in existing methods in somewhat complex scenes

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
  • Real-time vehicle detection and trajectory tracking method in traffic video based on deep learning
  • Real-time vehicle detection and trajectory tracking method in traffic video based on deep learning
  • Real-time vehicle detection and trajectory tracking method in traffic video based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0036] Such as figure 1 As shown, the real-time vehicle detection and trajectory tracking method in traffic video includes the following steps:

[0037] Step 1, using the target detection algorithm based on deep learning to detect the position of the vehicle in the traffic video, the feature vector and the category of the vehicle.

[0038] Such as figure 2 As shown, the specific detection process is as follows:

[0039] 11) Obtain a single frame video image in the traffic video, and perform size transformation on the image to adapt to the target detection algorithm.

[0040] 12) Use the target detection algorithm based on deep learning to obtain the coordinates of several detection candidat...

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 method for real-time vehicle detection and track tracking in traffic videos, comprising the following steps: using a target detection algorithm based on deep learning to detect the position of the vehicle in the traffic video, and extract the feature vector and category of the vehicle; Track and obtain the driving trajectory. The whole scheme of the present invention has strong robustness, low missed detection rate, and is easy to expand to various types of vehicles, so as to meet the requirements of vehicle detection and continuous tracking in surveillance video.

Description

technical field [0001] The invention relates to a method for real-time vehicle detection and track tracking in traffic video based on deep learning, belonging to the field of traffic video monitoring. Background technique [0002] The task of vehicle detection and trajectory tracking is to detect all the vehicles passing the camera in a surveillance video and draw their trajectories. The existing vehicle detection and trajectory tracking method is a combination of traditional video target detection and tracking, where the target detection steps are: training target classifier, extracting a single frame image, candidate area classification, target area fusion, target tracking step It is: extracting a single frame image, given the initial target frame, and predicting the target position based on the inter-frame image changes. [0003] The existing vehicle detection and trajectory tracking methods have fast calculation speed and can meet the requirements of real-time video pla...

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): G06V20/52G06K9/62G06V10/74G06V10/764
CPCG06V20/52G06F18/22G06F18/2411
Inventor 徐子豪黄伟泉王胤
Owner TONGJI UNIV