Anchor Free remote sensing detector based on solving discrete polar coordinate equation

TL;DR

This paper introduces BWP-Det, an anchor-free remote sensing object detector that effectively detects rotating and multi-scale objects by utilizing a novel split polar coordinate IoU and a double-branch up-sampling network.

Contribution

The paper proposes a novel anchor-free detector with a double-branch network and a new rotating IoU based on split polar coordinates, improving detection of complex remote sensing objects.

Findings

Achieves state-of-the-art performance on DOTA, UCAS-AOD, and NWPU VHR-10 datasets.

Uses fewer regression parameters with a simpler model architecture.

Effectively detects rotating and multi-scale objects in remote sensing images.

Abstract

As the rapid development of depth learning, object detection in aviatic remote sensing images has become increasingly popular in recent years. Most of the current Anchor Free detectors based on key point detection sampling directly regression and classification features, with the design of object loss function based on the horizontal bounding box. It is more challenging for complex and diverse aviatic remote sensing object. In this paper, we propose an Anchor Free aviatic remote sensing object detector (BWP-Det) to detect rotating and multi-scale object. Specifically, we design a interactive double-branch(IDB) up-sampling network, in which one branch gradually up-sampling is used for the prediction of Heatmap, and the other branch is used for the regression of boundary box parameters. We improve a weighted multi-scale convolution (WmConv) in order to highlight the difference between foreground and background. We extracted Pixel level attention features from the middle layer to guide the two branches to pay attention to effective object information in the sampling process. Finally, referring to the calculation idea of horizontal IoU, we design a rotating IoU based on the split polar coordinate plane, namely JIoU, which is expressed as the intersection ratio following discretization of the inner ellipse of the rotating bounding box, to solve the correlation between angle and side length in the regression process of the rotating bounding box. Ultimately, BWP-Det, our experiments on DOTA, UCAS-AOD and NWPU VHR-10 datasets show, achieves advanced performance with simpler models and fewer regression parameters.