A Light-Weight Object Detection Framework with FPA Module for Optical Remote Sensing Imagery

TL;DR

This paper introduces CenterFPANet, a lightweight, anchor-free object detection framework for optical remote sensing images that balances high speed and accuracy through a novel FPA module and efficient backbone design.

Contribution

The paper presents a new lightweight, anchor-free detector with a novel FPA module and asymmetric revolution block, improving detection speed and accuracy for remote sensing images.

Findings

Achieves 64.00% mAP on DOTA dataset

Runs at 22.2 FPS, close to current accuracy levels

Outperforms Faster R-CNN in speed by 60.87%

Abstract

With the development of remote sensing technology, the acquisition of remote sensing images is easier and easier, which provides sufficient data resources for the task of detecting remote sensing objects. However, how to detect objects quickly and accurately from many complex optical remote sensing images is a challenging hot issue. In this paper, we propose an efficient anchor free object detector, CenterFPANet. To pursue speed, we use a lightweight backbone and introduce the asymmetric revolution block. To improve the accuracy, we designed the FPA module, which links the feature maps of different levels, and introduces the attention mechanism to dynamically adjust the weights of each level of feature maps, which solves the problem of detection difficulty caused by large size range of remote sensing objects. This strategy can improve the accuracy of remote sensing image object detection without reducing the detection speed. On the DOTA dataset, CenterFPANet mAP is 64.00%, and FPS is 22.2, which is close to the accuracy of the anchor-based methods currently used and much faster than them. Compared with Faster RCNN, mAP is 6.76% lower but 60.87% faster. All in all, CenterFPANet achieves a balance between speed and accuracy in large-scale optical remote sensing object detection.