Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN
This addresses the problem of detecting motorcycles in traffic for applications like autonomous driving, but it is incremental as it applies an existing method to a new dataset.
The paper tackles motorcycle detection and classification in urban environments, achieving 75% average precision in occluded scenarios and up to 92% in low-occlusion datasets using a Faster R-CNN-based model.
This paper introduces a Deep Learning Convolutional Neural Network model based on Faster-RCNN for motorcycle detection and classification on urban environments. The model is evaluated in occluded scenarios where more than 60% of the vehicles present a degree of occlusion. For training and evaluation, we introduce a new dataset of 7500 annotated images, captured under real traffic scenes, using a drone mounted camera. Several tests were carried out to design the network, achieving promising results of 75% in average precision (AP), even with the high number of occluded motorbikes, the low angle of capture and the moving camera. The model is also evaluated on low occlusions datasets, reaching results of up to 92% in AP.