Two-Wheeled Vehicle Detection Using Two-Step and Single-Step Deep Learning Models
- PDF / 5,171,891 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 43 Downloads / 168 Views
RESEARCH ARTICLE-COMPUTER ENGINEERING AND COMPUTER SCIENCE
Two-Wheeled Vehicle Detection Using Two-Step and Single-Step Deep Learning Models Adeeba Kausar1 · Afshan Jamil1 · Nudrat Nida1 · Muhammad Haroon Yousaf1,2 Received: 26 August 2019 / Accepted: 29 July 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract Road accidents are major cause of death which has been increased by 46% since 1990. In recent years, significant efforts have been invested in four-wheeled vehicle detection that improved intelligent transportation systems and decreased the calamity rate. However, the automatic detection of two-wheeled vehicles remains challenging due to occlusion, illumination variation, environmental conditions, and viewpoint variations. In this paper, we present a comprehensive methodology of two-wheeled vehicle detection using two categories of deep learning-based object detection models including two-step and single-step techniques. In two-step object detection techniques, experiments are carried out with object detection models such as a regionbased convolutional neural network (RCNN), Fast-RCNN, Faster-RCNN, and region-based fully convolutional network (RFCN), while in single-step object detection techniques, detection is performed using the single-shot multibox detector (SSD), SDDLite, and you only look once (YOLOv3) detection models. The performance of the proposed methodology is evaluated on two benchmark datasets, i.e., MB7500 and Tsinghua-Daimler Cyclist data. The experimentation results demonstrate that Faster-RCNN with the Inception-Resnetv2 backbone model impressively outperforms two-step object detection techniques, while in single-step object detection techniques, SSD with the Inceptionv2 model shows superior performance. Further, the performance comparison of the proposed methodology with existing state-of-the-art methods confirms its effectiveness in two-wheeled vehicle detection. Keywords Two-wheeled vehicle detection · Computer vision · Intelligent transportation system · Deep learning
1 Introduction The intelligent transportation system (ITS) is an important area of research that provides significant services of traffic control, distinct modes of transport, and efficient use of transport networks [1,2]. ITS aims to increase the safety, mobility, productivity, and environmental effectiveness for traffic road users. Due to the extensive construction of urban
B
Muhammad Haroon Yousaf [email protected] Adeeba Kausar [email protected] Afshan Jamil [email protected] Nudrat Nida [email protected]
1
Department of Computer Engineering, University of Engineering and Technology, Taxila, Pakistan
2
Swarm Robotics Lab-NCRA, University of Engineering and Technology, Taxila, Pakistan
highways and expressways, the interest of four-wheeled vehicle detection has been increased. Four-wheeled vehicle detection systems [3–7] deliver information of vehicle counting, vehicle speed estimation, traffic accident identification, and traffic flow measurement. In the last de
Data Loading...
