Building Multi-Feature Fusion Refined Network for Building Extraction from High-Resolution Remote Sensing Images

Abstract

Deep learning approaches have been widely used in building automatic extraction tasks and have made great progress in recent years. However, the missing detection and wrong detection causing by spectrum confusion is still a great challenge. The existing fully convolutional networks (FCNs) cannot effectively distinguish whether the feature differences are from one building or the building and its adjacent non-building objects. In order to overcome the limitations, a building multi-feature fusion refined network (BMFR-Net) was presented in this paper to extract buildings accurately and completely. BMFR-Net is based on an encoding and decoding structure, mainly consisting of two parts: the continuous atrous convolution pyramid (CACP) module and the multiscale output fusion constraint (MOFC) structure. The CACP module is positioned at the end of the contracting path and it effectively minimizes the loss of effective information in multiscale feature extraction and fusion by using parallel continuous small-scale atrous convolution. To improve the ability to aggregate semantic information from the context, the MOFC structure performs predictive output at each stage of the expanding path and integrates the results into the network. Furthermore, the multilevel joint weighted loss function effectively updates parameters well away from the output layer, enhancing the learning capacity of the network for low-level abstract features. The experimental results demonstrate that the proposed BMFR-Net outperforms the other five state-of-the-art approaches in both visual interpretation and quantitative evaluation.

A Lightweight Fully Convolutional Neural Network for SAR Automatic Target Recognition

“…In this section, ablation studies were uesd to discuss the effect of the fully convolutional (FC) neural network, Channel-Attention (CA) mechanism, Channel-Shuffle (CS) mechanism, and Inverted-Residual (IR) block. Referring to the ablation studies in literature [41,42], we design four variants of our ASIR-Net as follows for comparison:…”

Discriminative Context-Aware Network for Target Extraction in Remote Sensing Imagery

“…Li et al [56] designed a hybrid convolutional network to fuse multi-grained road segmentation maps from three subnetworks. Ran et al [57] presented a multi-feature fusion refined network to address the issue of incomplete and incorrect identification. Similarly, Li et al [58] proposed a Y-shaped model which was composed of two independent branches for feature extraction and a fusion module for feature aggregation.…”

Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images

“…In order to leverage large-scale contextual information and extract critical cues for identifying building pixels in the presence of complex background and when there is occlusion, researchers have proposed methods to capture local and long-range spatial dependencies among the ground entities in the aerial scene [55], [56]. Several researchers are also using transformers [60], attention modules [12], [61]- [63], and multiscale information [8], [43], [45], [46], [64]- [66] for this purpose. Recently, multiview satellite images [67], [68] are also being used to perform semantic segmentation of points on ground.…”