Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Real-time multi-target tracking method based on single multi-frame detector and kalman filtering

A Kalman filter and multi-target tracking technology, which is applied in the field of real-time multi-target tracking, can solve problems such as background difference algorithm effect decline, tracking, counting, and trajectory drawing, etc., and achieve high robustness and practicality.

Active Publication Date: 2018-05-11
NANJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the multi-target detection and tracking algorithm, target detection plays an extremely important role, and due to the limitations of the background difference method, that is, when the light is poor and the target is blocked, the effect of the background difference algorithm is greatly reduced, thus It brings great difficulties to subsequent tracking, counting, drawing trajectory and other applications

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 multi-target tracking method based on single multi-frame detector and kalman filtering
  • Real-time multi-target tracking method based on single multi-frame detector and kalman filtering
  • Real-time multi-target tracking method based on single multi-frame detector and kalman filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0039] The schematic flow chart of the present invention is as figure 1 As shown, the following is a specific embodiment, and its specific steps are as follows:

[0040] Step A, read the video stream;

[0041] Step B, calling the SSD target detection algorithm model to detect the video frame;

[0042] The target detection algorithm is the SSD algorithm based on deep learning, and its specific steps are as follows:

[0043] Step B-1, training the detection model of the target detection algorithm SSD based on deep learning. The detection algorithm model can identify 21 types of objects including the background. The size of the picture in the model training is 300*300, the training data set uses VOC2007 and VOC2012, and the test data set uses VOC2012, with a tot...

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 real-time multi-target tracking method based on a single multi-frame detector and the kalman filtering. The method comprises the following steps of firstly, reading a video stream, then calling a single shot multibox detector (SSD) model to detect a video frame, adopting the kalman filtering algorithm to carry out single-step prediction (tracking) on the above detection result, judging whether a detection frame and a tracking frame are paired or not through the similarity between the euclidean distance and the HSV color histogram, correspondingly updating the pairingresult, deleting the tracking which does not meet the new double-decision condition, and finally completing the multi-target real-time tracking. According to the invention, the multi-target real-timeand stable tracking can be well achieved under various complex scenes and in different weathers.

Description

technical field [0001] The invention relates to a real-time multi-target tracking method based on a single multi-frame detector and a Kalman filter, belonging to the technical field of intelligent video monitoring. Background technique [0002] In recent years, target detection and tracking algorithms have been paid more and more attention by scholars in the field of computer vision, and it has become an important topic in the field of video surveillance technology, especially for multiple targets. Among them, the visual monitoring and monitoring system usually uses a static camera, and the main task of the target detection part is to detect the target of interest from the video image. The existing target detection method is usually the background difference method, that is, to separate the moving object from the so-called static background, usually by constructing a background model, and using the frame difference method to detect the foreground target, so as to realize the...

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 Applications(China)
IPC IPC(8): G06T7/277G06T7/292G06T7/90
CPCG06T7/277G06T7/292G06T7/90G06T2207/10016
Inventor 韩光苏晋鹏李晓飞葛亚鸣
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com