A Pedestrian Loitering Detection Method Based on Object Tracking

A technology for target tracking and detection methods, which is applied in image data processing, instrumentation, computing, etc., and can solve problems such as poor robustness and reduced matching effect.

Active Publication Date: 2018-08-24
FUDAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The features designed by this method are sensitive to illumination changes, and the matching effect will drop sharply in scenes with obvious illumination changes; SSDA matching has a good effect on rigid objects, but is less robust to non-rigid objects such as pedestrians.

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 Loitering Detection Method Based on Object Tracking
  • A Pedestrian Loitering Detection Method Based on Object Tracking
  • A Pedestrian Loitering Detection Method Based on Object Tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The following explains the specific implementation of the pedestrian tracking-based wandering detection algorithm with reference to the accompanying drawings. It should be noted that the implementation of the present invention is not limited to the following implementations.

[0082] figure 1 The flow chart of pedestrian detection algorithm based on target tracking is given. The specific steps are:

[0083] 1. First set up a surveillance camera in the scene to be monitored to obtain surveillance video. Such as figure 2 As shown, a camera is set up above the scene to obtain information of the entire scene.

[0084] 2. Preprocess the image sequence captured by the camera to adapt its resolution to the processing requirements. In this example, the image size is 640x480 and no scaling is required.

[0085] 3. Use the Vibe model to perform background difference on the preprocessed image to calculate the foreground image. Create a sample set of size N=20 for each pixel in the imag...

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 belongs to the digital image processing and pattern recognition technical field and relates to a target tracking-based pedestrian loitering detection algorithm. The algorithm includes a target extraction phase, an object tracking phase and a loitering judgment phase. In the target extraction phase, a moving target is extracted from an image through a Vibe background difference method, and therefore, high time performance and recall rate can be realized; in the object tracking phase, color histogram characteristics of the extracted moving object are calculated, and successive frames are tracked through utilizing a particle filter algorithm, so that the movement trajectory of the target can be obtained, and therefore, high robustness and real-time performance in an actual scene can be realized; and in the loitering judgment phase, the geometric characteristics of the movement trajectory of the target are utilized to perform loitering judgment. The algorithm of the invention has the advantages of high real-time performance and easiness in implementation. With the algorithm adopted, detection requirements of different scenes such as classrooms, workshops, stations and squares can be satisfied.

Description

Technical field [0001] The invention belongs to the technical field of digital image processing and pattern recognition, and specifically relates to a pedestrian wandering detection method based on target tracking. Background technique [0002] Compared with traditional monitoring methods, intelligent video surveillance technology has obvious advantages: it can monitor all-weather without fatigue; it has powerful processing capabilities and can monitor multiple targets at the same time; it has high autonomy and can automatically identify targets And alarm. [0003] Pedestrian wandering detection and analysis is an important part of the field of intelligent video surveillance. When a pedestrian continuously and reciprocally moves in the monitoring area, it can be considered that the pedestrian is in a hovering state. Wandering detection can evaluate pedestrian behavior in the monitoring area and issue warnings in time. Wandering detection can be applied in many scenarios. For exa...

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): G06T7/20G06T3/60
CPCG06T3/60
Inventor 朱梦哲冯瑞
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap