LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images

TL;DR

LO-Det is a lightweight, efficient, and accurate oriented object detection model for remote sensing images, featuring novel CSA-DRF and DSC-Head components that improve shape constraint and detection precision.

Contribution

The paper introduces a novel lightweight oriented object detector with CSA-DRF and DSC-Head, enhancing efficiency and accuracy over existing methods.

Findings

Runs efficiently on embedded devices.

Achieves competitive accuracy in oriented object detection.

Effectively constrains object shape detection.

Abstract

A few lightweight convolutional neural network (CNN) models have been recently designed for remote sensing object detection (RSOD). However, most of them simply replace vanilla convolutions with stacked separable convolutions, which may not be efficient due to a lot of precision losses and may not be able to detect oriented bounding boxes (OBB). Also, the existing OBB detection methods are difficult to constrain the shape of objects predicted by CNNs accurately. In this paper, we propose an effective lightweight oriented object detector (LO-Det). Specifically, a channel separation-aggregation (CSA) structure is designed to simplify the complexity of stacked separable convolutions, and a dynamic receptive field (DRF) mechanism is developed to maintain high accuracy by customizing the convolution kernel and its perception range dynamically when reducing the network complexity. The CSA-DRF component optimizes efficiency while maintaining high accuracy. Then, a diagonal support constraint head (DSC-Head) component is designed to detect OBBs and constrain their shapes more accurately and stably. Extensive experiments on public datasets demonstrate that the proposed LO-Det can run very fast even on embedded devices with the competitive accuracy of detecting oriented objects.