AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
This work addresses the challenge of small vehicle detection in aerial surveillance, which is important for applications like traffic monitoring and security, but it appears incremental as it builds on existing detection frameworks with specific enhancements.
The paper tackled the problem of detecting small vehicles in aerial images by proposing AVDNet, a one-stage detection network that uses ConvRes residual blocks and enlarged feature maps to improve feature representation for small objects, achieving significant performance improvements in mAP, computation, and space complexity over state-of-the-art methods.
Detection of small-sized targets in aerial views is a challenging task due to the smallness of vehicle size, complex background, and monotonic object appearances. In this letter, we propose a one-stage vehicle detection network (AVDNet) to robustly detect small-sized vehicles in aerial scenes. In AVDNet, we introduced ConvRes residual blocks at multiple scales to alleviate the problem of vanishing features for smaller objects caused because of the inclusion of deeper convolutional layers. These residual blocks, along with enlarged output feature map, ensure the robust representation of the salient features for small sized objects. Furthermore, we proposed a recurrent-feature aware visualization (RFAV) technique to analyze the network behavior. We also created a new airborne image data set (ABD) by annotating 1396 new objects in 79 aerial images for our experiments. The effectiveness of AVDNet is validated on VEDAI, DLR- 3K, DOTA, and the combined (VEDAI, DLR-3K, DOTA, and ABD) data set. Experimental results demonstrate the significant performance improvement of the proposed method over state-of-the-art detection techniques in terms of mAP, computation, and space complexity.