A I based violation detection system

Project Title

A I based violation detection system

Project Area of Specialization Information & Communication TechnologyProject Summary

Workplace video surveillance and timely response to operational violations are critical to avoid operator injuries at power construction sites. Here, a system that combines remote substation construction management and artificial intelligence object detection techniques to intellectualize the power construction management process and identify violations during construction in real time is proposed. To improve the detection accuracy, a data augmentation method, including three operations: (1) object segmentation and background fusion; (2) partial erasing; and (3) other basic transformations, is also proposed. Six variants of the You Only Look Once (YOLO) model will be trained as detectors for comparative experiments on a dataset collected at the practical construction site.

Project Objectives

To improve the detection accuracy.

To intellectualize the power construction management process .

And

To Identify violations during construction in real time.

To build a system that combines remote substation construction management and artificial intelligence object detection techniques.

Project Implementation Method

Our proposed Substation Remote Licensing Intelligent Safety

Construction Management and Control System is composed

of three main components: multi-video stream capture devices,

AI detection server, and remote construction management plat-

form. Our system, which is based on a traditional power substation work order management system, implements the remote intelligent work order issuance procedure and integrates AI technology to automatically identify violations in substation construction.

Our proposed Substation Remote Licensing Intelligent Safety

Construction Management and Control System is composed

of three main components: multi-video stream capture devices, 

AI detection server, and remote construction management plat-

form. Our system, which is based on a traditional power substa-

tion work order management system, implements the remote

intelligent work order issuance procedure and integrates AI

technology to automatically identify violations in substation

construction. The framework of our proposed system is shown.

Benefits of the Project

Our system overcomes the drawbacks of traditional manual

safety monitoring methods in the power construction process,

such as low ef?ciency of work order issuance in substation management, small monitoring range, poor real-time performance,and a high missed detection rate.

Violations will be automatically classi?ed and saved as violation video clips during the construction process to facilitate accountability and safety education for violators after the project is completed.

Technical Details of Final Deliverable

This project proposes a power safety construction monitoring system that combines the traditional power construction

surveillance process with AI to automatically detect violations

in the power construction surveillance videos and save the violation clips. In order to compensate for the problem of insufficient training samples, this project proposes a data augmentation method to better detect objects in realistic power construction scenes. The Substation Remote Licensing Intelligent Safety Construction Management and Control System proposed here Will be in use after completion of the project.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Agriculture Core Technology Artificial Intelligence(AI)Other Technologies Augmented & Virtual RealitySustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	79500
Stationary and Thesis	Miscellaneous	2	5000	10000
All in One laser jet..	Equipment	1	32000	32000
viewsonic monitor for display	Equipment	1	28000	28000
External Hard disk	Equipment	1	9500	9500