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

Computer vision tracking method and device

A computer vision and algorithm technology, applied in the field of computer vision, can solve the problem of low accuracy of target tracking

Inactive Publication Date: 2020-01-31
CHINA MOBILEHANGZHOUINFORMATION TECH CO LTD +1
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, since the noise of target occlusion and illumination change in the actual scene does not completely obey the Gaussian distribution, traditional computer vision tracking methods are very sensitive to target occlusion and noise of illumination change, resulting in low accuracy of target 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
  • Computer vision tracking method and device
  • Computer vision tracking method and device
  • Computer vision tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of them. Based on the embodiments of the present application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0075] The computer vision tracking method provided by the embodiment of the present invention can be applied on a server or a terminal. In order to ensure the accuracy of tracking, the server needs to have strong computing power; the terminal can be user equipment (User Equipment, UE) with strong computing power, handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing power, etc. device or other pro...

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 embodiment of the invention discloses a computer vision tracking method and device. The technical scheme comprises steps of based on area information of a tracking target in a first frame image, selecting at least one sample from a continuously acquired second frame image, based on the feature information of the at least one sample and the tracking target, a preset Gaussian distribution residual error and a preset Laplace distribution residual error, adopting a preset sparse representation algorithm to obtain a sparse representation coefficient of the feature information of each sample inthe at least one sample and the tracking target, and based on the sparse representation coefficient, determining the sample corresponding to the minimum preset Gaussian distribution residual in the atleast one sample as the tracking target of the second frame image. According to the technical scheme, the Laplace distribution is added to the residual error of the traditional tracking method, so that the accuracy of target tracking is improved.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a computer vision tracking method and device. Background technique [0002] Sparse representation of high-dimensional data is one of the hotspots in the fields of machine learning and computer vision tracking. Visual tracking is a very important research in the field of computer vision. The purpose of visual tracking is to obtain the trajectory of a specific target in a video sequence. Visual tracking has important applications in monitoring, human-computer interaction, vehicle navigation, video indexing, etc. The traditional computer vision tracking method focuses on the sparse representation, and assumes that all kinds of noise in the actual scene obey the Gaussian distribution. The sparse representation algorithm is used to linearize the samples collected on the image by tracking the characteristic information of the target. To express it, under the conditi...

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): G06T7/246G06K9/00G06K9/62
CPCG06T7/246G06V20/42G06F18/22
Inventor 王冰温亮生浮怀铎徐曜罗建孝毛敏
Owner CHINA MOBILEHANGZHOUINFORMATION TECH CO LTD