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

Multi-target tracking method and device

A multi-target tracking and target technology, applied in the field of multi-target tracking methods and devices, can solve problems such as low accuracy and poor real-time performance, and achieve the effect of solving time-consuming, accurate tracking, and taking into account the accuracy of algorithms

Inactive Publication Date: 2017-06-20
BOCOM SMART INFORMATION TECH CO LTD
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defects of poor real-time performance and low accuracy of existing multi-target tracking methods

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
  • Multi-target tracking method and device
  • Multi-target tracking method and device
  • Multi-target tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides a multi-target tracking method, and the multi-target tracking method is applicable to the tracking of rigid objects, such as vehicles and bicycles. The flowchart of the multi-target tracking method is as follows figure 1 shown, including the following steps:

[0056] S1: Acquire video images. The video image can be collected by a mobile camera device or a camera device set at a fixed position.

[0057] S2: Extract key points in the video image. Preferably, the amount of calculation can be reduced by controlling the number of target trajectories in each frame of the video image, thereby improving the real-time performance of multi-target tracking. Therefore, the key point in the video image can be a Harris corner point, and the Harris corner point in the video image can be extracted.

[0058] First, assuming that the video image is I(x, y), calculate the gradient I of I(x, y) in the X and Y directions according to formula (1) x and I y .

[...

Embodiment 2

[0105] This embodiment provides a multi-target tracking device, which is suitable for tracking targets that are rigid bodies, such as vehicles and bicycles. The schematic diagram of the device is figure 2 shown. include:

[0106] The video image acquiring unit 10 is configured to acquire video images. The video image can be collected by a mobile camera device or a camera device set at a fixed position.

[0107] A key point extracting unit 20, configured to extract key points in the video image. Preferably, the amount of calculation can be reduced by controlling the number of target trajectories in each frame of the video image, thereby improving the real-time performance of multi-target tracking. Therefore, the key point in the video image can be a Harris corner point, and the Harris corner point in the video image can be extracted.

[0108] A key point tracking unit 30, configured to track key points in the video image. Specifically, an optical flow tracking algorithm ...

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 provides a multi-target tracking method and a multi-target tracking device. Key points in a video image are extracted and tracked. Trajectories are formed for tracked consecutive N frames of key points. A certain similarity measure method is used to cluster the key point trajectories to form at least one complete target. A number of targets are continuously and accurately tracked in real time. According to the invention, a large number of tracked target trajectories are clustered; a number of targets are determined; the algorithm accuracy is taken into account; and the problem that the existing multi-target detection and tracking algorithm is time-consuming is solved.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a multi-target tracking method and device. Background technique [0002] Multi-target tracking technology has a wide range of applications in the field of intelligent security, vehicle auxiliary systems or military fields. Multi-target tracking technology generally detects the target first, then describes the characteristics of each detected target, and then tracks each target according to the characteristics. From detection to tracking, the algorithm is not only complicated but also takes a long time to calculate, resulting in The real-time performance and accuracy of multi-target tracking are poor. For long-term tracking or tracking when the tracked target has a shape change, many people use the detection method instead of tracking. Although this method can improve the tracking effect in some cases, it requires an offline learning process, that is, it needs to select ...

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): G06T7/246G06K9/62
CPCG06T2207/10016G06F18/232G06F18/22
Inventor 黄小刚王剑邦张如高
Owner BOCOM SMART INFORMATION TECH 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