AI to Monitor Abandoned E-Scooters, Ensuring Pedestrian Safety

For the first time in South Korea, artificial intelligence (AI) technology has been developed to automatically detect illegal parking and stopping of shared personal mobility devices (hereafter referred to as shared PMs) and to suggest the priority for relocating them.

The Korea Institute of Civil Engineering and Building Technology (KICT) announced on May 28 that a research team from its Road Traffic Research Division has developed a technology that analyzes existing public CCTV footage to automatically detect illegal parking and stopping of shared PMs, assesses whether the devices have fallen over, and determines the risk level by analyzing the duration of illegal parking or stopping.

A technology has been developed to automatically detect illegal parking of shared PMs by analyzing public CCTV footage. Detection screen of illegal parking of shared PMs in CCTV footage. Provided by Korea Institute of Civil Engineering and Building Technology.

This technology can identify the operating company based on the shape and color of each device. It also provides the priority order for relocating illegally parked or stopped shared PMs according to their risk level.

In particular, the main advantages of this technology are that it utilizes existing public CCTV infrastructure?eliminating the need for additional installations and reducing costs?and that it can dramatically improve the efficiency of monitoring illegal parking and stopping of shared PMs without increasing personnel.

KICT emphasized that this technology goes beyond simple detection of illegal parking and stopping, enabling identification of operating companies and assessment of risk levels, which allows for rapid response in situations requiring urgent action.

Shared PMs are gaining attention as eco-friendly means of transportation powered by electricity. On the other hand, illegal parking and stopping of shared PMs has emerged as a social issue, as it threatens pedestrian safety and causes inconvenience for vulnerable road users.

Park Seonkyu, President of KICT, stated, "The development of this technology will help ensure pedestrian safety and maximize the efficiency of shared PM management," adding, "KICT will continue to conduct research and development to create a safer traffic environment."

This research was conducted as part of the "Development of Video AI-Based Detection Technology for Illegal Parking and Stopping of Shared PMs (2023-2024)" project, which is one of KICT's support programs for small and medium-sized enterprises funded by the Ministry of Science and ICT. KICT has transferred the developed technology to Pintel Co., Ltd.