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

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.

arXiv comment15 pages

References in corpus (10)

• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• Squeeze-and-Excitation Networks
• Gliding vertex on the horizontal bounding box for multi-oriented object detection
• R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• Learning Modulated Loss for Rotated Object Detection
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

Cited by in corpus (4)

• A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection
• Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images
• Multi-Grained Angle Representation for Remote Sensing Object Detection
• Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection