Affiliation:
1. Department of Photogrammetry and Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran 19697-64499, Iran
2. 3D Optical Metrology (3DOM) Unit, Bruno Kessler Foundation (FBK), 38100 Trento, Italy
Abstract
Motorcycle detection and collision warning are essential features in advanced driver assistance systems (ADAS) to ensure road safety, especially in emergency situations. However, detecting motorcycles from videos captured from a car is challenging due to the varying shapes and appearances of motorcycles. In this paper, we propose an integrated and innovative remote sensing and artificial intelligence (AI) methodology for motorcycle detection and distance estimation based on visual data from a single camera installed in the back of a vehicle. Firstly, MD-TinyYOLOv4 is used for detecting motorcycles, refining the neural network through SPP (spatial pyramid pooling) feature extraction, Mish activation function, data augmentation techniques, and optimized anchor boxes for training. The proposed algorithm outperforms eight existing YOLO versions, achieving a precision of 81% at a speed of 240 fps. Secondly, a refined disparity map of each motorcycle’s bounding box is estimated by training a Monodepth2 with a bilateral filter for distance estimation. The proposed fusion model (motorcycle’s detection and distance from vehicle) is evaluated with depth stereo camera measurements, and the results show that 89% of warning scenes are correctly detected, with an alarm notification time of 0.022 s for each image. Outcomes indicate that the proposed integrated methodology provides an effective solution for ADAS, with promising results for real-world applications, and can be suitable for running on mobility services or embedded computing boards instead of the super expensive and powerful systems used in some high-tech unmanned vehicles.
Subject
General Earth and Planetary Sciences
Reference86 articles.
1. Markiewicz, P., Długosz, M., and Skruch, P. (2017, January 18–21). Review of tracking and object detection systems for advanced driver assistance and autonomous driving applications with focus on vulnerable road users sensing. Proceedings of the Polish Control Conference, Kraków, Poland.
2. Pineda-Deom, D. (2019). Motorcycle Blind Spot Detection System and Rear Collision Alert Using Mechanically Aligned Radar. (10,429,501), U.S. Patent.
3. Motorcycle detection for ADAS through camera and V2V Communication, a comparative analysis of two modern technologies;Anaya;Expert Syst. Appl.,2017
4. De Raeve, N., De Schepper, M., Verhaevert, J., Van Torre, P., and Rogier, H. (2020). A bluetooth-low-energy-based detection and warning system for vulnerable road users in the blind spot of vehicles. Sensors, 20.
5. Gruyer, D., and Rahal, M.-C. (2019, January 3–7). Multi-Layer Laser Scanner Strategy for Obstacle Detection and Tracking. Proceedings of the 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA), Abu Dhabi, United Arab Emirates.