Abstract
The growing adoption of electric scooters (e-scooters) in urban environments has corresponded with a notable increase in traffic accidents and injuries. Due to their smaller wheels, lack of suspension system, and significant variances in the system center of gravity among different riders, e-scooters are more susceptible to the negative effects of uneven surfaces.
While deep learning-based object detection has been successfully applied to improve automobile safety, its potential for obstacle detection especially for e-scooters remains unexplored. This study introduces a novel ground obstacle detection system for e-scooters, integrating an RGB camera, and a depth camera to enhance real-time road hazard detection. Additionally, the Inertial Measurement Unit (IMU) measures linear vertical acceleration to identify surface vibrations, guiding the selection of six obstacle categories: tree branches, manhole covers, potholes, pine cones, non-directional cracks, and truncated domes. All sensors, including the RGB camera, depth camera, and IMU, are integrated within the Intel RealSense Camera D435i. A deep learning model powered by YOLO (You Only Look Once) detects road hazards and utilizes depth data to estimate obstacle proximity. Evaluated on the seven hours of naturalistic riding dataset, the system achieves a high mean average precision (mAP) of 0.827 and demonstrates excellent real-time performance.
This approach provides an effective solution to enhance e-scooter safety through advanced computer vision and data fusion. This system enhances e-scooter rider safety by detecting road infrastructure hazards, leveraging advanced computer vision, and data fusion to provide real-time hazard awareness.
