Real-Time Roadway Obstacle Detection for Electric Scooters Using Deep Learning and Multi-Sensor Fusion
🤖 AI Summary
Electric scooters (e-scooters) suffer from frequent accidents due to their small wheel diameter, lack of suspension, and high sensitivity to road irregularities, leading to poor obstacle detection performance. To address this, we propose the first multi-modal real-time obstacle detection system specifically designed for e-scooter scenarios. Our method fuses RGB images, depth maps, and vertical acceleration signals from an IMU—integrated via a lightweight YOLO architecture and a spatiotemporally synchronized data fusion algorithm—to robustly detect six common road obstacles (e.g., potholes, manhole covers, and tree branches) on embedded devices. Key innovations include leveraging IMU vibration signatures to enhance discrimination of small or low-texture obstacles and optimizing edge inference efficiency. Evaluated on a 7-hour real-world riding dataset, our system achieves an mAP of 0.827 while satisfying real-time constraints (<30 FPS). The source code and dataset are publicly released.
Application Category
📝 Abstract
The increasing adoption of electric scooters (e-scooters) in urban areas has coincided with a rise in traffic accidents and injuries, largely due to their small wheels, lack of suspension, and sensitivity to uneven surfaces. While deep learning-based object detection has been widely used to improve automobile safety, its application for e-scooter obstacle detection 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 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. The dataset is accessible at https://zenodo.org/records/14583718, and the project code is hosted on https://github.com/Zeyang-Zheng/Real-Time-Roadway-Obstacle-Detection-for-Electric-Scooters.
Problem
Research questions and friction points this paper is trying to address.
Detect roadway obstacles for e-scooters in real-time
Integrate multi-sensor data to enhance hazard detection
Improve e-scooter safety using deep learning and IMU
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deep learning model with YOLO for hazard detection
Multi-sensor fusion using RGB and depth cameras
IMU integration for surface vibration analysis
🔎 Similar Papers
No similar papers found.
