Abstract
Vehicle counting from an unmanned aerial vehicle (UAV) is becoming a popular research topic in traffic monitoring. Camera mounted on UAV can be regarded as a visual sensor for collecting aerial videos. Compared with traditional sensors, the UAV can be flexibly deployed to the areas that need to be monitored and can provide a larger perspective. In this paper, a novel framework for vehicle counting based on aerial videos is proposed. In our framework, the moving-object detector can handle the following two situations: static background and moving background. For static background, a pixel-level video foreground detector is given to detect vehicles, which can update background model continuously. For moving background, image-registration is employed to estimate the camera motion, which allows the vehicles to be detected in a reference coordinate system. In addition, to overcome the change of scale and shape of vehicle in images, we employ an online-learning tracker which can update the samples used for training. Finally, we design a multi-object management module which can efficiently analyze and validate the status of the tracked vehicles with multi-threading technique. Our method was tested on aerial videos of real highway scenes that contain fixed-background and moving-background. The experimental results show that the proposed method can achieve more than 90% and 85% accuracy of vehicle counting in fixed-background videos and moving-background videos respectively.
Highlights
With the rapid development of intelligent video analysis, traffic monitoring has become a key technique for collecting information about traffic conditions
Researchers improve the traditional traffic monitoring methods and apply vehicle detection and tracking on vehicle counting, the traditional surveillance camera still cannot be applied for monitoring large areas, which is very restrictive for vehicle counting
Images captured by unmanned aerial vehicle (UAV) are characterized by complex background and variable vehicle shape, which leads to discontinuity of detector, and affects the accuracy of vehicle counting
Summary
With the rapid development of intelligent video analysis, traffic monitoring has become a key technique for collecting information about traffic conditions. Researchers improve the traditional traffic monitoring methods and apply vehicle detection and tracking on vehicle counting, the traditional surveillance camera still cannot be applied for monitoring large areas, which is very restrictive for vehicle counting. Proposed a real-time method for image-registration dedicating to small moving-object detection from a UAV. Guvenc [22] proposed a review paper for object detection and tracking from UAVs. Shi [23] proposed a moving vehicle detection method in wide area motion imagery, which constructs a cascade of support vector machine classifiers for classifying object and can extract road context. A multi-vehicle detection and tracking framework based on UAV is proposed, which can be used for vehicle counting and can handle both fixed-background and moving-background.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
