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

Robust Target Tracking Method Based on Support Vector Machine

A technology of support vector machine and support vector, applied in image data processing, instrumentation, computing, etc., can solve problems such as tracking drift, achieve good real-time performance and robustness, and solve the effect of tracking drift

Active Publication Date: 2017-02-01
NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Technical problem: The purpose of this invention is to provide a robust tracking method based on support vector machines to solve the problem of tracking drift caused by target motion crossing, half occlusion or temporary departure from the screen in video tracking

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
  • Robust Target Tracking Method Based on Support Vector Machine
  • Robust Target Tracking Method Based on Support Vector Machine
  • Robust Target Tracking Method Based on Support Vector Machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] 1. Architecture

[0026] 1, figure 1 Shown is the method of extracting samples in the update support vector stage. The center point is the center of the current positive sample frame. The sample network group is constructed according to the method of bisecting the radius and angle, and the points are staggered on the radius. This method of taking points can be used in Reduce the amount of computation without reducing the number of features.

[0027] 2, figure 2 Shown are the two parts of the Kalman filter, the time update and the measurement update, where, Indicates the position of the target in k frames, u k-1 Indicates the control amount of k-1 frames to the system, this paper sets u k-1 to zero, P k is the error covariance, Q and R are process noise and measurement noise respectively, which do not change with system state changes. A is the state transition matrix: A = 1 0 ...

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

A robust target tracking method based on a support vector machine comprises the steps of sample selection, support vector update, online target tracking based on the structured support vector machine, Kalman amendment and target repositioning. The invention aims at providing an improvement method for solving a tracking drifting problem caused by error accumulation produced when target motions are cross, half-occluded or temporarily leave away a frame. For the cross or half-occluded target motions, the support vector update is determined by adopting an interframe target matching degree fluctuating value, and a tracking result is corrected by combining Kalman filter. For the situation that a target temporarily leaves away the frame, the target repositioning is performed by adopting a support vector update stopping and search strategy changing method. The robust target tracking method improves the tracking real-timeliness and robustness and effectively solved the tracking drifting problem caused by the error accumulation.

Description

technical field [0001] The invention relates to the field of tracking drift in video target tracking, and specifically relates to the technical field of video image processing. Background technique [0002] Target tracking technology is one of the core technologies in the intelligent video target tracking system. Its basic task is to determine the position and attitude of the target in each frame according to the spatial and temporal correlation of video information in the sequence of images. With the needs of anti-terrorism, public safety and safe cities in the world, security has become an important field of video target tracking applications. However, the current level of intelligence in video surveillance facilities is low, and most of them only record video data for subsequent inquiries. Functions such as video target behavior analysis and tracking cannot meet the needs of reality. [0003] Video object tracking mainly includes learning-based, feature-based and region-...

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): G06T7/20G06T5/00
Inventor 李晓飞刘梦刘浏吴鹏飞
Owner NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
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