Object Detection in Large-Scale Remote-Sensing Images Based on Time-Frequency Analysis and Feature Optimization

Recently, optical remote-sensing images have been steadily growing in size, as they contain massive data and complex backgrounds. This trend presents several problems for object detection, for example, increased computation time and memory consumption and more false positives due to the complex backgrounds of large-scale images. Inspired by deep neural networks combined with time-frequency analysis, we propose a time-frequency analysis-based object detection method for large-scale remote-sensing images with complex backgrounds. We utilize wavelet decomposition to carry out a time-frequency transform and then integrate it with deep learning in feature optimization. To effectively capture the time-frequency features, we propose a feature optimization method based on deep reinforcement learning to select the dominant time-frequency channels. Furthermore, we design a discrete wavelet multiscale attention mechanism (DW-MAM), enabling the detector to concentrate on the object area rather than the background. Extensive experiments show that the proposed method of learning from time-frequency channels not only solves the challenges of large-scale and complex backgrounds, but also improves the performance compared to the original state-of-the-art object detection methods. In addition, the proposed method can be used with almost all object detection neural networks, regardless of whether they are anchor-based or anchor-free detectors, horizontal or rotation detectors.

I. Introduction

Remote-sensing image processing and analysis play an increasingly significant role in earth observation [1]–[3]. Object detection is a fundamental but challenging task in the remote-sensing community and plays an important role in wide-scope applications including target reconnaissance, land monitoring, and environmental conservation [4]–[7]. For instance, object detection in the remote-sensing system can monitor airports and harbors to obtain the spatial distribution and geographic coordinates of objects such as aircraft and ships [8]–[11]; it can also be used to observe the growth of crops [12]–[14].