Rotation Equivariant Feature Image Pyramid Network for Object Detection in Optical Remote Sensing Imagery

Abstract

Detection of objects is extremely important in various aerial vision-based applications. Over the last few years, the methods based on convolution neural networks have made substantial progress. However, because of the large variety of object scales, densities, and arbitrary orientations, the current detectors struggle with the extraction of semantically strong features for small-scale objects by a predefined convolution kernel. To address this problem, we propose the rotation equivariant feature image pyramid network (REFIPN), an image pyramid network based on rotation equivariance convolution. The proposed model adopts single-shot detector in parallel with a lightweight image pyramid module to extract representative features and generate regions of interest in an optimization approach. The proposed network extracts feature in a wide range of scales and orientations by using novel convolution filters. These features are used to generate vector fields and determine the weight and angle of the highest-scoring orientation for all spatial locations on an image. By this approach, the performance for small-sized object detection is enhanced without sacrificing the performance for large-sized object detection. The performance of the proposed model is validated on two commonly used aerial benchmarks and the results show our proposed model can achieve state-of-the-art performance with satisfactory efficiency.

References in corpus (11)

• Graph Convolutional Networks for Hyperspectral Image Classification
• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
• Arbitrary-Oriented Scene Text Detection via Rotation Proposals
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
• Group Equivariant Convolutional Networks
• Learnable Manifold Alignment (LeMA) : A Semi-supervised Cross-modality Learning Framework for Land Cover and Land Use Classification
• Rotation equivariant vector field networks
• ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features
• Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks
• Fourier-based Rotation-invariant Feature Boosting: An Efficient Framework for Geospatial Object Detection
• CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers