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

Transformer substation personnel behavior recognition method based on monitoring video time sequence action positioning and anomaly detection

A monitoring video and anomaly detection technology, applied in character and pattern recognition, neural learning methods, instruments, etc., can solve problems that are difficult to be applied to identify staff, achieve accurate monitoring video sequence action positioning, accurately detect abnormal behavior, and improve Effect of Exploitation Value and Anomaly Detection Accuracy

Active Publication Date: 2020-06-16
SHANDONG UNIV +3
View PDF6 Cites 18 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
  • Transformer substation personnel behavior recognition method based on monitoring video time sequence action positioning and anomaly detection
  • Transformer substation personnel behavior recognition method based on monitoring video time sequence action positioning and anomaly detection
  • Transformer substation personnel behavior recognition method based on monitoring video time sequence action positioning and anomaly detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] Such as figure 1 shown.

[0083] A substation personnel behavior recognition method based on surveillance video sequence action location and abnormal detection, the method comprising the following steps:

[0084] S1: Using prior knowledge to independently collect, process and construct substation personnel abnormal behavior monitoring video data sets;

[0085] S2: Build a 3D convolutional feature extraction network: perform feature extraction on the input undivided substation monitoring long video, and extract the feature information of the monitoring video sequence;

[0086] S3: Construction of time series candidate area extraction network: used to extract candidate time series fragments that may have abnormal behavior of substation personnel;

[0087] S4: Build a time series behavior classification network: perform classification and regression operations on the extracted substation personnel behavior video segments;

[0088] S5: Build an abnormal behavior detectio...

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 relates to a transformer substation personnel behavior identification method based on monitoring video time sequence action positioning and anomaly detection, which comprises the following steps of autonomously acquiring, processing and constructing a transformer substation personnel abnormal behavior monitoring video data set by using priori knowledge, and introducing a new transformer substation abnormal behavior detection video data set. According to the method, the time sequence information is acquired through the video action detection model based on transfer learning, and accurate monitoring video time sequence action positioning can be realized, so that the action starting and ending time of a worker is found in an unedited video, and actions are classified. And meanwhile, the video clip of the specific behavior of the person is obtained through video action detection. According to the method, the video anomaly detection technology is utilized, training is carriedout under weak supervision through multi-example learning, the obtained model can judge whether abnormal behaviors exist in the fragments or not, accurate detection of the abnormal behaviors and the occurring time sequence positions is achieved, and the utilization value and anomaly detection accuracy of transformer substation video monitoring are improved.

Description

technical field [0001] The invention discloses a substation personnel behavior recognition method based on monitoring video sequence action positioning and abnormal detection, and belongs to the technical field of power grid intelligent management. Background technique [0002] In the current power system, the operation and maintenance of power transmission and transformation is particularly important, which is directly related to the normal operation of the power system and the electricity consumption for production and life in society. During the operation of the power system, the failure of some equipment will cause the power system to collapse, and the mistakes of relevant staff will also cause problems in the power system. In many substation scenarios, there are often safety accidents caused by abnormal operations of the staff. The occurrence of these accidents not only brings great danger to the operators, but also seriously endangers the order of social production and...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G06Q50/06G06Q50/26
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
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com