Publication: Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN
Loading...
Identifiers
Publication date
2018-05-22
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
The Institution of Engineering and Technology
Impact
Export
Abstract
This paper introduces a Deep Learning Convolutional Neutral 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.
Description
This paper has been presented at: 9th International Conference on Pattern Recognition Systems (ICPRS-18)
Keywords
Motorcycle classification, Convolutional neural network, Occluded images, Faster R-CNN, Deep learning
Bibliographic citation
Espinosa, J.E., Velastin, S.A. y Branch, J. W. (2018). Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN. In 9th International Conference on Pattern Recognition Systems, pp. 91-96.