Land-use mapping (LUM) using high-spatial resolution remote sensing images (HSR-RSIs) is a challenging and crucial technology. However, due to the characteristics of HSR-RSIs, such as different image acquisition conditions and massive, detailed information, and performing LUM faces unique scientific challenges. With the emergence of new deep learning (DL) algorithms in recent years, methods to LUM with DL have achieved huge breakthroughs, which offer novel opportunities for the development of LUM for HSR-RSIs. This article aims to provide a thorough review of recent achievements in this field. Existing high spatial resolution datasets in the research of semantic segmentation and single-object segmentation are presented first. Next, we introduce several basic DL approaches that are frequently adopted for LUM. After reviewing DL-based LUM methods comprehensively, which highlights the contributions of researchers in the field of LUM for HSR-RSIs, we summarize these DL-based approaches based on two LUM criteria. Individually, the first one has supervised learning, semisupervised learning, or unsupervised learning, while another one is pixel-based or object-based. We then briefly review the fundamentals and the developments of the development of semantic segmentation and single-object segmentation. At last, quantitative results that experiment on the dataset of ISPRS Vaihingen and ISPRS Potsdam are given for several representative models such as fully convolutional network (FCN) and U-Net, following up with a comparison and discussion of the results.

This paper presents a new approach to the automatic registration of terrestrial laser scanning (TLS) point clouds using panoramic reflectance images. The approach follows a two-step procedure that includes both pair-wise registration and global registration. The pair-wise registration consists of image matching (pixel-to-pixel correspondence) and point cloud registration (point-to-point correspondence), as the correspondence between the image and the point cloud (pixel-to-point) is inherent to the reflectance images. False correspondences are removed by a geometric invariance check. The pixel-to-point correspondence and the computation of the rigid transformation parameters (RTPs) are integrated into an iterative process that allows for the pair-wise registration to be optimised. The global registration of all point clouds is obtained by a bundle adjustment using a circular self-closure constraint. Our approach is tested with both indoor and outdoor scenes acquired by a FARO LS 880 laser scanner with an angular resolution of 0.036° and 0.045°, respectively. The results show that the pair-wise and global registration accuracies are of millimetre and centimetre orders, respectively, and that the process is fully automatic and converges quickly.

With the emergence of huge volumes of high-resolution remote sensing images produced by all sorts of satellites and airborne sensors, processing and analysis of these images require effective retrieval techniques. To alleviate the dramatic variation of the retrieval accuracy among queries caused by the single image feature algorithms, we developed a novel graph-based learning method for effectively retrieving remote sensing images. The method utilizes a three-layer framework that integrates the strengths of query expansion and fusion of holistic and local features. In the first layer, two retrieval image sets are obtained by, respectively, using the retrieval methods based on holistic and local features, and the top-ranked and common images from both of the top candidate lists subsequently form graph anchors. In the second layer, the graph anchors as an expansion query retrieve six image sets from the image database using each individual feature. In the third layer, the images in the six image sets are evaluated for generating positive and negative data, and SimpleMKL is applied to learn suitable query-dependent fusion weights for achieving the final image retrieval result. Extensive experiments were performed on the UC Merced Land Use-Land Cover data set. The source code has been available at our website. Compared with other related methods, the retrieval precision is significantly enhanced without sacrificing the scalability of our approach.

An efficient method for the continuous extraction of subway tunnel cross sections using terrestrial point clouds is proposed. First, the continuous central axis of the tunnel is extracted using a 2D projection of the point cloud and curve fitting using the RANSAC (RANdom SAmple Consensus) algorithm, and the axis is optimized using a global extraction strategy based on segment-wise fitting. The cross-sectional planes, which are orthogonal to the central axis, are then determined for every interval. The cross-sectional points are extracted by intersecting straight lines that rotate orthogonally around the central axis within the cross-sectional plane with the tunnel point cloud. An interpolation algorithm based on quadric parametric surface fitting, using the BaySAC (Bayesian SAmpling Consensus) algorithm, is proposed to compute the cross-sectional point when it cannot be acquired directly from the tunnel points along the extraction direction of interest. Because the standard shape of the tunnel cross section is a circle, circle fitting is implemented using RANSAC to reduce the noise. The proposed approach is tested on terrestrial point clouds that cover a 150-m-long segment of a Shanghai subway tunnel, which were acquired using a LMS VZ-400 laser scanner. The results indicate that the proposed quadric parametric surface fitting using the optimized BaySAC achieves a higher overall fitting accuracy (0.9 mm) than the accuracy (1.6 mm) obtained by the plain RANSAC. The results also show that the proposed cross section extraction algorithm can achieve high accuracy (millimeter level, which was assessed by comparing the fitted radii with the designed radius of the cross section and comparing corresponding chord lengths in different cross sections) and high efficiency (less than 3 s/section on average).