Object sieving and morphological closing to reduce false detections in wide-area aerial imagery
This work addresses false detection reduction in aerial imagery analysis, which is incremental as it builds on existing object detection algorithms with a new post-processing method.
The authors tackled the problem of reducing false detections in object detection for wide-area aerial imagery by proposing a two-stage post-processing scheme involving area-thresholding sieving and morphological closing, resulting in performance improvements as measured by several metrics on two aerial videos.
For object detection in wide-area aerial imagery, post-processing is usually needed to reduce false detections. We propose a two-stage post-processing scheme which comprises an area-thresholding sieving process and a morphological closing operation. We use two wide-area aerial videos to compare the performance of five object detection algorithms in the absence and in the presence of our post-processing scheme. The automatic detection results are compared with the ground-truth objects. Several metrics are used for performance comparison.