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

Substation Personnel Behavior Recognition Method Based on Surveillance Video Timing Action Location and Abnormal Detection

A technology for monitoring video and substations, applied in the field of personnel behavior identification in substations, can solve problems such as difficulty in identifying personnel by application, and achieve the effects of improving utilization value, enhancing accuracy and generalization ability, and improving operation efficiency

Active Publication Date: 2022-06-03
SHANDONG UNIV +3
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In summary, there are still many technical deficiencies in the existing technical field, and it is difficult to be applied to the substation scene to identify the specific behavior of the staff

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
  • Substation Personnel Behavior Recognition Method Based on Surveillance Video Timing Action Location and Abnormal Detection
  • Substation Personnel Behavior Recognition Method Based on Surveillance Video Timing Action Location and Abnormal Detection
  • Substation Personnel Behavior Recognition Method Based on Surveillance Video Timing Action Location and Abnormal Detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] As shown in Figure 1 .

[0086] S3: construct a time sequence candidate region extraction network: used to extract candidates that may have abnormal behavior of substation personnel

[0087] S4: construct a time-series behavior classification network: classify and regress the extracted substation personnel behavior video segments

[0093] S12: perform time-series behavior annotation on typical behavior categories to construct video data for time-series action detection tasks

[0096] S21: Improve the C3D (3D Convolution) feature extraction network: use depthwise separable convolution to replace

[0098] The frame sequence of the input surveillance video passes through a feature consisting of multiple depthwise separable 3D convolutional layers.

[0101] S32: Use a 3x3x3 3D ​​convolution filter to expand the temporal receptive field, and then use a size of

[0102] S33: in the feature map C

[0106] S43: The output feature is first sent to a large fully connected layer for fe...

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

A substation personnel behavior recognition method based on monitoring video timing action location and abnormal detection, using prior knowledge to carry out autonomous collection, processing and construction of substation personnel abnormal behavior monitoring video data sets, and introducing new substation abnormal behavior detection video data collection; the present invention acquires timing information through a video action detection model based on transfer learning, and can realize accurate surveillance video timing action positioning, so as to find the start and end time of a staff member's action in a section of unedited video, and determine the action sort. At the same time, for the video clips of specific behaviors of people obtained by video motion detection. The present invention utilizes the video anomaly detection technology and trains under weak supervision by adopting multi-example learning, and the obtained model can judge whether there is abnormal behavior in the segment, realizes accurate detection of abnormal behavior and the timing position of occurrence, and improves the efficiency of substation video monitoring Leverage value and anomaly detection accuracy.

Description

Personnel behavior recognition in substation based on surveillance video sequence action location and anomaly detection other way technical field The present invention discloses a kind of substation personnel behavior identification based on monitoring video sequence action location and abnormal detection The method belongs to the technical field of grid intelligent management. Background technique In the current power system, the operation and maintenance of power transmission and transformation are particularly important, which are directly related to the normal operation of the power system. Operation and social production and living electricity. During the operation of the power system, some equipment malfunctions will cause the power The power system collapses, and the mistakes of the relevant staff can also create problems with the power system. In many substation scenarios, often There will be safety accidents caused by the abnormal operation of the staff....

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): G06V20/40G06V10/762G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08G06Q50/06G06Q50/26
CPCG06N3/08G06Q50/06G06Q50/265G06V40/20G06V20/42G06V20/49G06V20/52G06N3/045G06F18/23213G06F18/241Y04S10/50
Inventor 聂礼强战新刚郑晓云姚一杨徐万龙尉寅玮
Owner SHANDONG UNIV
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