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

Unsupervised under-bridge pedestrian intrusion detection method and device

A technology of intrusion detection and supervision bridge, applied in instruments, biological neural network models, computing, etc., can solve the problems of low accuracy and easy false positives.

Pending Publication Date: 2021-02-26
招商新智科技有限公司 +2
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that the accuracy rate is low, which leads to false positives of the detection results

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
  • Unsupervised under-bridge pedestrian intrusion detection method and device
  • Unsupervised under-bridge pedestrian intrusion detection method and device
  • Unsupervised under-bridge pedestrian intrusion detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] A desktop computer with CPU: I7 8700, memory: 16G, graphics card: GTX1660TI is selected as the training and testing machine. The input of the implementation case is the high-point surveillance video under a bridge in eastern Hubei. The specific steps of the implementation case are as follows:

[0104] Use LabelImage software to manually calibrate the pedestrian position information of the pedestrians at the intersection, and obtain the manually calibrated dataset.

[0105] The dataset obtained by manual calibration is merged with the pedestrian part of the Pascal VOC 2007+2012 open source dataset, and the merged training set is sent to the original YOLOv3 network for iterative training to obtain the trained YOLOv3 model.

[0106] Use the obtained YOLO v3 model as the network model for detection, detect the surveillance video, use detect.py to read the video stream data in rtsp format, and obtain the marked frame of the position of the pedestrian in the picture (that is,...

Embodiment approach

[0118] As an optional implementation manner, the detection module includes:

[0119] An acquisition unit, configured to acquire historical trajectory data;

[0120] A clustering unit is used to cluster the historical trajectory data using a clustering algorithm to obtain information on conventional paths that pedestrians often pass by;

[0121] a preprocessing unit, configured to preprocess the trajectory data;

[0122] A comparing unit, configured to compare the preprocessed trajectory data with the conventional path information, and mark the trajectory data deviating from the conventional path information as first abnormal data;

[0123] a marking unit, configured to mark the preprocessed trajectory data whose residence time exceeds a threshold as second abnormal data;

[0124] an output unit, configured to output the first abnormal data and the second abnormal data.

[0125] As an optional implementation, the preprocessing unit is used for:

[0126] Performing feature e...

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

One or more embodiments of the invention provide an unsupervised under-bridge pedestrian intrusion detection method and device, and the method comprises the steps: marking pedestrian position information in an original image through a pre-trained neural network model, and obtaining a marked image; processing the marked images through a Kalman filtering multi-target tracking algorithm and a Hungaryalgorithm, obtaining trajectory data of each pedestrian, then detecting the trajectory data, finding abnormal data in the trajectory data, and the abnormal data indicate that the pedestrians abnormally intrude into a detection area, so that high-precision monitoring of pedestrian intrusion under the bridge is realized.

Description

technical field [0001] One or more embodiments of this specification relate to the technical field of under-bridge pedestrian intrusion detection, and in particular, to an unsupervised under-bridge pedestrian intrusion detection method and device. Background technique [0002] As a key node and major infrastructure on the transportation line, the safety of the bridge is extremely important. At present, most bridges have built under-bridge monitoring systems. By setting up a monitoring system connected to the Internet at the location that needs to be monitored, and through the system to process and analyze the data collected by monitoring in real time, it is judged whether there is an incident of abnormal pedestrian intrusion. This ensures the safety of the bridge. [0003] For example, Patent No. CN103150550A "A Road Pedestrian Event Detection Method Based on Motion Trajectory Analysis", this invention proposes a road pedestrian event detection method based on motion trajec...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V40/10G06V10/462G06N3/045G06F18/214
Inventor 张威奕邹晓芳杨德元王勇卢佳程
Owner 招商新智科技有限公司
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