Abstract
Vehicle detection in aerial images plays a significant role in civil and military applications and it faces many challenges including the overhead-view perspective, the highly complex background, and the variants of vehicles. This paper presents a robust vehicle detection scheme to overcome these issues. In the detection stage, we propose a novel algorithm to generate oriented proposals that could enclose the vehicle objects properly as rotated rectangles with orientations. To discriminate the object and background in the proposals, we propose a modified vector of locally aggregated descriptors (VLAD) image representation model with a recently proposed image feature, i.e., local steering kernel (LSK) feature. By applying non-maximum suppression (NMS) after classification, we show that each vehicle object is detected with a single-oriented bounding box. Experiments are conducted on aerial images to compare the proposed method with state-of-art methods and evaluate the impact of the components in the model. The results have proven the robustness of the proposed method under various circumstances and the superior performance over other existing vehicle detection approaches.
Highlights
With the improvement of airborne camera and remote sensing system, high-resolution aerial images captured by un-manned airborne vehicles (UAVs) or satellites are trending to be more common recently
Following Hosang [23], we evaluated the performance of methods with the recall metric, which is computed as the ratio of the number of bounding boxes above a certain IoU overlap threshold to the number of ground-truth bounding boxes
In order to depict the performances of a method between IoU 0.5 to 1, a metric namely average recall (AR) [23] was introduced, which calculates recalls under different IoU thresholds and performs with an average value
Summary
With the improvement of airborne camera and remote sensing system, high-resolution aerial images captured by un-manned airborne vehicles (UAVs) or satellites are trending to be more common recently. These aerial images provide lots of data for researchers, in this paper, we focus on vehicle detection in overhead imagery. This task has been a standing topic for several decades owing to the demands of gathering crucial information of targets in many applications, such as traffic surveillance, road assistance, urban planning, optical mapping, and military reconnaissance [1,2].
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
