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

A pedestrian identification method based on multivariate spatial trajectory association

A trajectory association and identity recognition technology, applied in biometric recognition, character and pattern recognition, image analysis, etc., can solve problems such as difficulty in fusion of exotic spatial attributes

Active Publication Date: 2022-07-05
WUHAN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the attribute information structure of single-domain space such as traditional video images has the same nature, and the similarity calculation can be directly performed. However, video images and geographic information belong to different domain spatial attributes, but there is a relationship between them, and the fusion between heterogeneous spatial attributes changes. very difficult

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
  • A pedestrian identification method based on multivariate spatial trajectory association
  • A pedestrian identification method based on multivariate spatial trajectory association
  • A pedestrian identification method based on multivariate spatial trajectory association

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to facilitate those skilled in the art to understand and implement the present invention, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the embodiments described herein are only used to illustrate and explain the present invention, but not to limit the present invention.

[0024] see figure 1 , figure 2 , a pedestrian identification method based on multi-dimensional space trajectory association provided by the present invention includes the following steps:

[0025] Step 1: Screen the video images on the known path according to the detected geographic track positioned by the mobile device;

[0026] In this embodiment, according to the signal path of the mobile device, all images that meet the time constraints under the camera network are extracted, and the monitoring point information on the known path is retrieved;

[0027] The mobile device signal path p is determin...

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 pedestrian identification method based on multi-space trajectory association. Based on the characteristics that the identity attributes of pedestrian objects in multi-space corroborate and complement each other, the invention proposes to fuse the information of video space and geographic space. The similarity measurement of spatial information in different domains is carried out by means of trajectory association. First, the video images on the known path are screened according to the detected geographic trajectory of the mobile device, and then the Hidden Markov Model (HMM) is used to build the Hidden Markov Model for the image path. Finally, the Viterbi algorithm is used to find the maximum association probability. The image path of the target person is retrieved under each monitoring point on the known geographic path. In the problem of pedestrian identification in a large-scale open scene, the method of the present invention can greatly improve the calculation accuracy.

Description

technical field [0001] The invention belongs to the technical field of surveillance video retrieval, and relates to a pedestrian identification method, in particular to a pedestrian identification method associated with multiple tracks. [0002] technical background [0003] With the wide application of surveillance video in the public security business, video investigation technology for discovering case clues and tracking suspected targets from video recordings has become the fourth major technical means to detect and solve cases after criminal technology, mobile technology and network investigation technology. play an increasingly important role in detection. At present, pedestrian re-identification technology is developing rapidly as one of the main technologies of video detection technology, and it mainly focuses on the appearance characteristics of pedestrians for metric calculation. However, in the real investigation environment, it is necessary to retrieve the target...

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): G06V40/10G06V20/52G06V10/764G06V10/84G06K9/62G06T7/246
CPCG06T7/246G06T2207/10016G06T2207/30196G06T2207/30232G06T2207/30241G06T2207/20076G06V40/103G06V20/52G06F18/295G06F18/241
Inventor 陈军黄文心李东阳高熙越
Owner WUHAN UNIV