With the advancements in remote sensing, satellite images have become a popular data modality and are widely used in many applications. Among others, satellite images are used by surveyors and engineers for urban planning and asset management, e.g., for rapidly growing cities, urban
[...] Read more.
With the advancements in remote sensing, satellite images have become a popular data modality and are widely used in many applications. Among others, satellite images are used by surveyors and engineers for urban planning and asset management, e.g., for rapidly growing cities, urban sprawl, and informal settlement. A preliminary step in satellite image analysis is identifying the regions of interest or target objects in the scene and extracting them from irrelevant objects for further processing. This image segmentation task is challenging due to various factors, e.g., occlusions, lighting conditions, and noises. To address these issues, many researchers have proposed different approaches, e.g., UNET, which is regarded as a state-of-the-art method. However, it has high memory consumption, low accuracy, and poor quality prediction when applying satellite images. Thus, we propose a multi-channel decomposition semantic segmentation method, MNET, for object classification. We used the dataset obtained by MBRSC satellites and divided the scene objects into six classes (vegetation, water, road, building, land, unused). The study area is in Dubai. We compared our approach with UNET++, U2NET, and 2D-VNET. Experimental findings show that: (1) MNET outperforms others with a mIoU score of 79.4%, whereas UNET gives 75.1%, and (2) accurate patch generation is a crucial part of the model performance, as ignoring less informative patches during training increases the accuracy by 5%. In conclusion, our proposed method offers a lightweight structure, is a computationally less expensive model, and is simple to deploy in industry applications. In this work, we conducted an extensive analysis of domain transferability, class bias, and class co-occurrence. We also compared the best and worst predictions with a number of current methods. We believe that our MNET can also benefit other domains, such as in floodwater detection using Interferometric Synthetic Aperture Radar (InSAR) data, building extraction, and crop segmentation, due to the prediction accuracy and memory consumption efficiency of MNET.