Fast Vehicle Detection in Aerial Imagery
This addresses the need for efficient vehicle detection in aerial imagery for applications like surveillance or mapping, though it is incremental as it builds on an existing method.
The paper tackled the problem of detecting vehicles in aerial imagery, where existing object detectors are slow or ineffective, by modifying YOLOv2 to achieve near state-of-the-art performance at over 4x the speed compared to Faster RCNN.
In recent years, several real-time or near real-time object detectors have been developed. However these object detectors are typically designed for first-person view images where the subject is large in the image and do not directly apply well to detecting vehicles in aerial imagery. Though some detectors have been developed for aerial imagery, these are either slow or do not handle multi-scale imagery very well. Here the popular YOLOv2 detector is modified to vastly improve it's performance on aerial data. The modified detector is compared to Faster RCNN on several aerial imagery datasets. The proposed detector gives near state of the art performance at more than 4x the speed.