Object sieving and morphological closing to reduce false detections in wide-area aerial imagery

TL;DR

This paper introduces a two-stage post-processing method combining object sieving and morphological closing to improve detection accuracy in wide-area aerial imagery, validated across multiple algorithms and datasets.

Contribution

The paper presents a novel two-stage post-processing scheme that effectively reduces false detections in aerial imagery object detection tasks.

Findings

Significant reduction in false positives across tested algorithms

Improved detection metrics with the proposed post-processing

Validated on two aerial video datasets

Abstract

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.