This paper aims to introduce an approach to the organization of road traffic monitoring by the means of unmanned aerial vehicles (UAVs), which is based on the automatic situation control of UAVs. The research includes analysis of existing methods of on-board automatic detection of emergency and abnormal traffic situations with UAV artificial vision systems (AVS), preliminary classification of these situations including the allocation of emergencies and disastrous situations. The paper presents the choice of UAV controls in compliance with the recognized situation. The traffic situation identification method introduced in the paper is based on Bayes and Neyman-Pearson criterion. Furthermore, the research involves the analysis of the existing approaches to the detection of moving and stationary vehicles by the means of UAV AVS. The paper proposes vehicles detection method based on the image segmentation, along with the use of machine learning methods, particularly the artificial neural network method known as Deep Learning. The research provides solutions for vehicle tracking and velocity detection problems in order to describe traffic situations. The proposed approach contributes to the efficiency of UAV in road traffic monitoring by means of the management and detection processes automation.
This work describes a cascade detection of vehicles in Unmanned Aerial Vehicle (UAV) images and videos. There are some new approaches used in the detection. In particular, the Region of Interest (ROI) search is not only based on GIS and navigation data, but also employs visual method based on rapid image segmentation and road detection. The work also suggests doing ROI segmentation by the superpixel technique and trainable four-level cascade detector that uses artificial neural networks as classifiers. Characteristics of the being analyzed regions (combined superpixels) are based on geometric and texture features, as well as on deep features extracted from the image patches by nonlinear auto encoders. To improve the detection quality of the moving vehicles a separate stage of the detector based on optical flow analysis was introduced. Proposed detection algorithm was benchmarked on the real UAV videos and showed the sufficiently high accuracy. Performance of the algorithm allows supposing the on-board usage.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.