ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features

Abstract

With the rapid development of spaceborne imaging techniques, object detection in optical remote sensing imagery has drawn much attention in recent decades. While many advanced works have been developed with powerful learning algorithms, the incomplete feature representation still cannot meet the demand for effectively and efficiently handling image deformations, particularly objective scaling and rotation. To this end, we propose a novel object detection framework, called optical remote sensing imagery detector (ORSIm detector), integrating diverse channel features extraction, feature learning, fast image pyramid matching, and boosting strategy. ORSIm detector adopts a novel spatial-frequency channel feature (SFCF) by jointly considering the rotation-invariant channel features constructed in frequency domain and the original spatial channel features (e.g., color channel, gradient magnitude). Subsequently, we refine SFCF using learning-based strategy in order to obtain the high-level or semantically meaningful features. In the test phase, we achieve a fast and coarsely-scaled channel computation by mathematically estimating a scaling factor in the image domain. Extensive experimental results conducted on the two different airborne datasets are performed to demonstrate the superiority and effectiveness in comparison with previous state-of-the-art methods.

References in corpus (4)

• A Survey on Object Detection in Optical Remote Sensing Images
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
• Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification
• Dynamical spectral unmixing of multitemporal hyperspectral images

Cited by in corpus (18)

• Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep (Overview and Toolbox)
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification
• X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
• Coupled Convolutional Neural Network with Adaptive Response Function Learning for Unsupervised Hyperspectral Super-Resolution
• Spectral Superresolution of Multispectral Imagery with Joint Sparse and Low-Rank Learning
• Fourier-based Rotation-invariant Feature Boosting: An Efficient Framework for Geospatial Object Detection
• A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models
• MIMA: MAPPER-Induced Manifold Alignment for Semi-Supervised Fusion of Optical Image and Polarimetric SAR Data
• AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data
• Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration
• Vehicle Detection of Multi-source Remote Sensing Data Using Active Fine-tuning Network
• Multi-Grained Angle Representation for Remote Sensing Object Detection
• Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images
• Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection
• Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images