Motorcycle Detection and Collision Warning Using Monocular Images from a Vehicle

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.

Vision-Based On-Road Nighttime Vehicle Detection and Tracking Using Improved HOG Features

“…One can mainly be divided into two steps: region of interest (ROI) generation and vehicle verification. (1) The removal of background illumination (saliency segmentation-based and template-based methods) was applied in the object proposal method to create the ROI. (2) The region-based superpixel and HOG features of grey and red images were combined for SVM classification.…”

“…As one of the basic directions of automatic driving technology, vehicle detection provides technical support for the follow-up anti-collision early warning system and has become the current research hotspot. Numerous studies on vehicle detection using monocular vision primarily concentrate on identifying vehicles during daylight hours [ 1 , 2 ]. Despite the traffic flow at night being much lower than during the daytime, insufficient illumination, complex road conditions, and the inapparent car contour lead to 42% of accidents occurring at nighttime [ 3 ].…”