Real-Time Semantic Segmentation: A brief survey and comparative study in remote sensing

Real-time semantic segmentation of remote sensing imagery is a challenging task that requires a tradeoff between effectiveness and efficiency. It has many applications, including tracking forest fires, detecting changes in land use and land cover, crop health monitoring, and so on. With the success of efficient deep learning methods [i.e., efficient deep neural networks (DNNs)] for real-time semantic segmentation in computer vision, researchers have adopted these efficient DNNs in remote sensing image analysis. This article begins with a summary of the fundamental compression methods for designing efficient DNNs and provides a brief but comprehensive survey, outlining the recent developments in real-time semantic segmentation of remote sensing imagery. We examine several seminal efficient deep learning methods, placing them in a taxonomy based on the network architecture design approach. Furthermore, we evaluate the quality and efficiency of some existing efficient DNNs on a publicly available remote sensing semantic segmentation benchmark dataset, OpenEarthMap. The experimental results of an extensive comparative study demonstrate that most of the existing efficient DNNs have good segmentation quality, but they suffer low inference speed (i.e., a high latency rate), which may limit their capability of deployment in real-time applications of remote sensing image segmentation. We provide some insights into the current trend and future research directions for real-time semantic segmentation of remote sensing imagery.