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

10/28/2020
by   Xin Gao, et al.
0

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.

READ FULL TEXT
02/26/2016

Seq-NMS for Video Object Detection

Video object detection is challenging because objects that are easily de...
09/22/2017

Elliptification of Rectangular Imagery

We present and discuss different algorithms for converting rectangular i...
10/23/2020

Automated crater detection with human level performance

Crater cataloging is an important yet time-consuming part of geological ...
08/22/2019

Object detection on aerial imagery using CenterNet

Detection and classification of objects in aerial imagery have several a...
01/07/2020

Detection of Diabetic Anomalies in Retinal Images using Morphological Cascading Decision Tree

This research aims to develop an efficient system for screening of diabe...
11/16/2017

Priming Neural Networks

Visual priming is known to affect the human visual system to allow detec...
10/04/2020

MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection

In object detection with deep neural networks, the box-wise objectness s...