Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature poi
- PDF / 2,444,715 Bytes
- 21 Pages / 439.642 x 666.49 pts Page_size
- 43 Downloads / 178 Views
Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis Ahmed Gomaa1,2,3 · Moataz M. Abdelwahab2 · Mohammed Abo-Zahhad2,4 Received: 25 June 2019 / Revised: 1 May 2020 / Accepted: 24 June 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Real-time automatic detection and tracking of moving vehicles in videos acquired by airborne cameras is a challenging problem due to vehicle occlusion, camera movement, and high computational cost. This paper presents an efficient and robust real-time approach for automatic vehicle detection and tracking in aerial videos that employ both detections and tracking features to enhance the final decision. The use of Top-hat and Bottom-hat transformation aided by the morphological operation in the detection phase has been adopted. After detection, background regions are eliminated by motion feature points’ analysis of the obtained object regions using a combined technique between KLT tracker and K-means clustering. Obtained object features are clustered into separate objects based on their motion characteristic. Finally, an efficient connecting algorithm is introduced to assign the vehicle labels with their corresponding cluster trajectories. The proposed method was tested on videos taken in different scenarios. The experimental results showed that the recall, precision, and tracking accuracy of the proposed method were about 95.1 %, 97.5%, and 95.2%, respectively. The method also achieves a fast processing speed. Thus, the proposed approach has superior overall performance compared to newly published approaches. Keywords Morphological operations · Aerial surveillance · Remote sensing · KLT tracker · K-means clustering · Vehicle detection and tracking.
1 Introduction Traffic management technology using cameras mounted on drones or airplanes is becoming a hot topic [18, 29]. Recently, airborne surveillance provides more advantages than traditional monitoring techniques, as a stationary camera and bridge sensors. Such methods are providing more coverage with lessen expenses and are better in emergency response. Moreover, UAVs are highly portable to collect traffic data in an area with difficult geographic locations, when the conventional data-gathering techniques cannot be applied. However, the Ahmed Gomaa
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
data collected by UAV cameras are needed to turn into useful resources. For traffic monitoring concerns, vehicle detection and tracking are considered as essential and challenging tasks. While there are many existing approaches designed for handling surveillance detection and tracking challenges such as shadows, occlusion, and reflections using cameras at a fixed location, the most challenging issue in the aerial video is the camera movement[20]. Both the background and foreground, in this case, are moving in the image due to the irregul
Data Loading...
