Fuel Stealing Detection

As with the advancements in the field of artificial intelligence and automation, the importance of precise Deep learning/computer vision has greatly increased. One of the most significant aspects of the computer vision is to detect the unusual activities accurately. The foremost motivation to work o

2025-06-28 16:32:41 - Adil Khan

Project Title

Fuel Stealing Detection

Project Area of Specialization Artificial IntelligenceProject Summary

As with the advancements in the field of artificial intelligence and automation, the importance of precise Deep learning/computer vision has greatly increased. One of the most significant aspects of the computer vision is to detect the unusual activities accurately. The foremost motivation to work on this project is security concern regarding the fuel stealing at industrial and academic sectors. CCTV monitoring is available which is manually controlled to keep track unusual activities, but manually monitoring is not an optimized solution because it is extremely cost-effective, less efficient and not possible for 24 hours, so these complications persuades us to come up with high accurate, efficient, low cost and prolonged sprint solution.
The proposed project is to detect the unusual activities using CNN and deep learning, this project is to enhance the security by smart monitoring. This smart system will detect the person who attempts any activity to steal the fuel, our system will capture the frame and notify the concerned staff and it also keep track that how times refueling of tank occurred in a month

Project Objectives

The main objective of this project is to enhance the security system to overcome the theft activities which is increasing day by day, Fuel stealing is part of that crime activities, however the existing CCTV footages which are not efficient given that footage are obtained later, after the incident has occurred, since there is a huge amount of video feeds so it is inefficient to look on these feeds.so the objective of our system is to introduce a real time stealing detection

Project Implementation Method

For the solution of above given problem at real time, we will use deep learning and computer vision algorithms like YOLO-v3 for the detection of stealing activities and Resnet18 algorithm for the detection of fuel vehicle to maintain the history of refueling.
for the efficiency and fast response to alert the concerned staff we will use distributed system, there are two or more nodes in which our model and app will be execute and one master pc control the data flow in abide of activities.

Benefits of the Project

1) This project would reduce the stealing activities in those sectors where generators are extensively using.
2) This project will reduce the cost of human resources
3) The concerned staff would be aware about how many times the tank refuel in a month.
4) This Project will enhance the security system

Technical Details of Final Deliverable

The final deliverable of our project would be a product for the detection of stealing activities and  Research Paper/Report  that will contain the system architecture and the results of experiments performed on distributed system .

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 60000
NVIDIA Graphics card Equipment14000040000
IP Night Vision Camera Equipment12000020000

More Posts