“I used to think that AI would steal jobs from humans, so I chose to study AI instead so that I wouldn’t be taken away from it.” This is a simple answer to the reason why “CuddleCam: CCTV Security Project AI Detects Accidents, Traffic Violations, and Solves Traffic Congestion”, the brainchild of the Teletubbies team of four second-year female students majoring in Robotics and Automation Engineering, Institute of Field Robotics (FIBO), King Mongkut’s University of Technology Thonburi (KMUTT), won the Muang Thong Hackathon 2024, which was first held in mid-2024. The project also received support to further develop it into actual use in Muang Thong Thani.
A student in the field of robotics and automation engineering said that he chose this topic because he thought it would be useful for people living in Muang Thong.
“Muang Thong’s challenge for this competition is to use AI to improve the quality of life of people in Muang Thong. Before applying, we looked at the problems and needs of Muang Thong Thani and people living in Muang Thong online and found that traffic and road accidents are one of the major problems that they face regularly. We therefore want to use AI to enable CCTV cameras in Muang Thong to detect and quickly notify those responsible about road accidents.”
And from the initial round of 75 project summary documents submitted from 30 universities, the Teletubbies team’s project was one of 13 finalists who had to gather data to make the project clear in both technology and economic terms.
“He took us to see important routes and intersections and provided information on frequent accident spots, major traffic violations such as parking in no-parking zones, double-parking, and the locations of CCTV cameras installed at important points. We also had the opportunity to observe the CCTV room, which still uses people to monitor and report traffic conditions at each point at all times. We are confident that AI will help reduce the workload for officers and make accident reporting and traffic analysis faster and more accurate, which means a better quality of life, in line with the Smart City requirements.”
The next step is to create an MVP (Minimum Viable Product), which is a shortened version of the project to be presented to the final judging panel.
“We did not just present the idea, but also presented the AI prototype that can analyze car-to-car accidents from still images, a sample screen for reporting the analysis results to users, while the numbers from our Business Canvas were also very worthwhile because it was an investment in software, while the CCTV camera system almost did not require additional investment, or even if there was an investment in changing to use completely new cameras, the calculations would still be worthwhile. All of this was to make the judges understand and see the potential of our work as much as possible.”
And from the strengths of the project above, Muang Thong has signed a contract with the Teletubbies team to develop from MVP to AI system to analyze traffic accidents for real testing at Muang Thong Thani. “In addition to enabling AI to analyze road accidents, including analyzing parking on solid lines or double parking, using images from CCTV cameras in real time, which requires tens of thousands of image files for AI to analyze and learn, and including adding other functions that are beneficial to the owners of the area, such as assessing traffic jams, counting and classifying the types of cars sharing the road, which in addition to reducing the workload of officials, can also be used for long-term planning.”
