Geometric primitives that consist of a group of discrete points may be viewed as one kind of abstraction and representation of lidar data at the entity level. In recent years, many efforts from different scientific communities, such as photogrammetry, computer vision and computer graphics, have been made into geometric primitive detection, regularization, and in-depth applications. The most recent lidar-based surveys focus only on reconstruction, object segmentation, and recognition, as well as the data processing techniques based on a specific platform such as mobile LiDAR. However, in this paper, lidar point clouds are understood from a new perspective, i.e., geometric primitives embedded in versatile objects in physical world. We categorize geometric primitives into two classes: shape primitives, e.g., lines, surfaces, and volumetric shapes, as well as structure primitives, represented by skeletons and edges. Interpretations of geometric primitive from multiple disciplines try to convey the significance of geometric primitives, the latest processing techniques regarding geometric primitives, and their potential possibilities in the context of lidar point clouds. To this end, applications of these primitives are reviewed with an emphasis on object extraction and reconstruction to clearly show the significances of this paper. Next, we survey and compare methods for geometric primitive extraction and then survey primitive regularization methods that add real-world geometry constrains to detected primitives. Finally, we summarize the problems and challenges and describe possible future for primitive extraction methods that can be achieved globally optimal results efficiently, even with disorganized, uneven, noisy, incomplete, and large-scale lidar point clouds.

Road network extraction is one of the significant assignments for disaster emergency response, intelligent transportation systems, and real-time updating road network. Road extraction base on high-resolution remote sensing images has become a hot topic. Presently, most of the researches are based on traditional machine learning algorithms, which are complex and computational because of impervious surfaces such as roads and buildings that are discernible in the images. Given the above problems, we propose a new method to extract the road network from remote sensing images using a DenseUNet model with few parameters and robust characteristics. DenseUNet consists of dense connection units and skips connections, which strengthens the fusion of different scales by connections at various network layers. The performance of the advanced method is validated on two datasets of high-resolution images by comparison with three classical semantic segmentation methods. The experimental results show that the method can be used for road extraction in complex scenes.

Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.

Owing to the limitation of spatial resolution and spectral resolution, deep learning methods are rarely used for the classification of multispectral remote sensing images based on the real spectral dataset from multispectral remote sensing images. This study explores the application of a deep learning model to the spectral classification of multispectral remote sensing images. To address the problem of the large workload with respect to selecting training samples during classification by deep learning, first, linear spectral mixture analysis and the spectral index method were applied to extract the pixels of impervious surfaces, soil, vegetation, and water. Second, through the Euclidean distance threshold method, a spectral dataset of multispectral image pixels was established. Third, a deep learning classification model, ResNet-18, was constructed to classify Landsat 8 OLI images based on pixels’ real spectral information. According to the accuracy assessment, the results show that the overall accuracy of the classification results can reach 0.9436, and the kappa coefficient can reach 0.8808. This study proposes a method that allows for the more optimized establishment of the actual spectral dataset of ground objects, addresses the limitations of difficult sample selection in deep learning classification and of spectral similarity in traditional classification methods, and applies the deep learning method to the classification of multispectral remote sensing images based on a real spectral dataset.

Identifying and extracting building boundaries from remote sensing data has been one of the hot topics in photogrammetry for decades. The active contour model (ACM) is a robust segmentation method that has been widely used in building boundary extraction, but which often results in biased building boundary extraction due to tree and background mixtures. Although the classification methods can improve this efficiently by separating buildings from other objects, there are often ineluctable salt and pepper artifacts. In this paper, we combine the robust classification convolutional neural networks (CNN) and ACM to overcome the current limitations in algorithms for building boundary extraction. We conduct two types of experiments: the first integrates ACM into the CNN construction progress, whereas the second starts building footprint detection with a CNN and then uses ACM for post processing. Three level assessments conducted demonstrate that the proposed methods could efficiently extract building boundaries in five test scenes from two datasets. The achieved mean accuracies in terms of the F1 score for the first type (and the second type) of the experiment are 96.43 ± 3.34% (95.68 ± 3.22%), 88.60 ± 3.99% (89.06 ± 3.96%), and 91.62 ±1.61% (91.47 ± 2.58%) at the scene, object, and pixel levels, respectively. The combined CNN and ACM solutions were shown to be effective at extracting building boundaries from high-resolution optical images and LiDAR data.

Building change detection from very high-spatial-resolution (VHR) remote sensing images has gained increasing popularity in a variety of applications, such as urban planning and damage assessment. Detecting fine-grained ``from-to'' changes (change transition from one land cover type to another) of buildings from the VHR images is still challenging as multitemporal representation is complicated. Recently, fully convolutional neural networks (FCNs) have been proven to be capable of feature extraction and semantic segmentation of VHR images, but its ability in change detection is untested and unknown. In this letter, we leverage the semantic segmentation of buildings as an auxiliary source of information for the fine-grained ``from-to'' change detection. A deep multitask learning framework for change detection (MTL-CD) is proposed for detecting building changes from the VHR images. MTL-CD adopts the encoder-decoder architecture and solves the main task of change detection and the auxiliary tasks of semantic segmentation simultaneously. Accordingly, the change detection loss function is constrained by the auxiliary semantic segmentation tasks and enables the back-propagation of the building footprints' detection errors for the improvement of change detection. A building change detection data set named the Guangzhou data set is also developed for model evaluation, in which the bitemporal R-G-B images were collected by airplane (2009) and unmanned aerial vehicle (UAV, 2019) with different flight heights. Experiments on the Guangzhou data set demonstrate that the MTL-CD method effectively detects fine-grained ``from-to'' changes and outperforms the postclassification methods and the direct change detection methods.