Improved Land Cover Classification of VHR Optical Remote Sensing Imagery Based Upon Detail Injection Procedure

Abstract

Development of very high resolution (VHR) remote sensing imaging platforms have resulted in a requirement for developing refined land cover classification maps for various applications. Therefore, aiming at exploring the accurate boundary and complex interior texture retrieval in VHR optical remote sensing images, a novel detail injection network (DI-Net) is proposed in this paper, which is composed of three aspects. First, the decoupling refinement module (DRM) embedded with a multiscale representation is designed to improve the feature extraction capabilities that precede the encoding-to-decoding process. Second, we pay attention to the hard examples of boundary and complex interior texture in land cover classification and design two detail injection attention modules to solve the feature inactivation phenomenon in gradually convolutional encoding-to-decoding process. Third, a specific stage grading (SG) loss is proposed to adaptively regulate the structural-level weights of the encoding and decoding stages, which facilitates the details retrieval and produce refined land cover classification results. Finally, various datasets (incl. ISPRS and GID) are employed to demonstrate that the proposed DI-Net achieves better performance than state-of-the-art methods. DI-Net provides more accurate boundaries and more consistent interior textures, and it achieves 86.86% PA and 68.37% mIoU on ISPRS dataset as well as 77.04% PA and 64.38% mIoU on GID dataset, respectively.

SERNet: Squeeze and Excitation Residual Network for Semantic Segmentation of High-Resolution Remote Sensing Images

“…Many traditional methods use machine learning algorithms to extract features based on the color, texture and spatial location of objects for image segmentation, such as threshold [17], edge detection [18], and clustering [19], but the handcrafted features used in most traditional methods have some limitations in terms of feature representation capacity. To address this problem, many advanced methods based on deep learning have been proposed and widely used recently [20]. Among them, the classical convolutional neural network (CNN) is the pioneer and became the tool of choice for many image segmentation tasks in computer vision [21,22].…”

A Semantic Guidance and Transformer-Based Matching Method for UAVs and Satellite Images for UAV Geo-Localization

“…Some other works were dedicated to semantic segmentation of remote sensing images [5]- [8]. Another line of works focused on the large scene images classification [9]- [12]. In recent years, the booming development of Unmanned aerial vehicles (UAVs) has promoted the application of drones in all walks of life.…”