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

Target tracking method and system based on two-stage convolutional neural network

A convolutional neural network and target tracking technology, which is applied in the field of target tracking methods and systems based on two-stage convolutional neural networks, can solve problems such as inability to accurately reflect actual losses, calculation method deviations, etc., and achieve improved recall and accurate tracking. Detect and improve the effect of average accuracy

Pending Publication Date: 2021-04-20
浙江航天恒嘉数据科技有限公司 +1
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since these four parts of loss are not independent of each other, there is an interdependence relationship in actual calculation, so there is a deviation in this loss calculation method, which cannot accurately reflect the actual loss caused by the center coordinates and width and height
For example, there may be different center abscissa, center ordinate, width and height losses while the total center coordinates and width and height losses are the same

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
  • Target tracking method and system based on two-stage convolutional neural network
  • Target tracking method and system based on two-stage convolutional neural network
  • Target tracking method and system based on two-stage convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0051] like figure 1 As shown, a target tracking method based on a two-stage convolutional neural network includes the following steps:

[0052] S1. Obtain a video stream in the detection area, and preprocess the video stream to obtain multiple frames of pictures;

[0053] S2, inputting the multiple frames of the frame picture into the pre-trained YOLOv3 target detection improved model for target detection, and obtaining the frame picture with the detection target;

[0054] S3, using the deepsort multi-target tracking algorithm to track the detection target on the frame picture with the detection target, and track the real-time position of the detection target in the frame picture.

[0055] The present invention r...

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 relates to a target tracking method and system based on a two-stage convolutional neural network. The method comprises the following steps: acquiring a video stream in a detection area, and preprocessing the video stream to obtain multiple frames of pictures; inputting the plurality of frames of pictures into a pre-trained YOLOv3 target detection improved model for target detection to obtain a picture with a detection target frame; and carrying out detection target tracking on the frame picture with the detection target by utilizing a deepsort multi-target tracking algorithm, and tracking the real-time position of the detection target in the frame picture. According to the invention, the targets are monitored in real time by adopting the improved YOLOv3 and Deepsort multi-target tracking combined two-stage convolutional neural network, so that the real-time position information of the same moving object is obtained more accurately, the calculation errors of multiple targets and overlapped targets are avoided, the real-time tracking of the moving multi-target objects is realized, and the detection accuracy is high.

Description

technical field [0001] The invention relates to the field of parking detection, in particular to a target tracking method and system based on a two-stage convolutional neural network. Background technique [0002] Hazardous chemical transport vehicles, referred to as hazardous chemical vehicles, are extremely dangerous because their loading and unloading materials are usually flammable, explosive or highly toxic substances. Therefore, they must be parked at designated locations in strict accordance with the management measures for hazardous chemical vehicles. During transportation, it is not allowed to park at will, and temporary parking is not allowed near open flames, high-temperature places, crowded places and other places that may cause harm. In view of the problem that hazardous chemical vehicles may cause serious harm if they are not parked according to regulations during road transportation, especially in chemical industrial parks, [0003] At present, based on pure ...

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
IPC IPC(8): G06T7/20
Inventor 范梦婷刘浩宋春红郑谊峰
Owner 浙江航天恒嘉数据科技有限公司