Change detection is an important task in remote sensing (RS) image analysis. It is widely used in natural disaster monitoring and assessment, land resource planning, and other fields. As a pixel-to-pixel prediction task, change detection is sensitive about the utilization of the original position information. Recent change detection methods always focus on the extraction of deep change semantic feature, but ignore the importance of shallow-layer information containing high-resolution and fine-grained features, this often leads to the uncertainty of the pixels at the edge of the changed target and the determination miss of small targets. In this letter, we propose a densely connected siamese network for change detection, namely SNUNet-CD (the combination of Siamese network and NestedUNet). SNUNet-CD alleviates the loss of localization information in the deep layers of neural network through compact information transmission between encoder and decoder, and between decoder and decoder. In addition, Ensemble Channel Attention Module (ECAM) is proposed for deep supervision. Through ECAM, the most representative features of different semantic levels can be refined and used for the final classification. Experimental results show that our method improves greatly on many evaluation criteria and has a better tradeoff between accuracy and calculation amount than other state-of-the-art (SOTA) change detection methods.

LiDAR technology is rapidly evolving as various new systems emerge, providing unprecedented data to characterize forest vertical structure. Data from different LiDAR systems present distinct characteristics owing to a combined effect of sensor specifications, data acquisition strategies, as well as forest conditions such as tree density and canopy cover. Comparative analysis of multi-platform, multi-resolution, and multi-temporal LiDAR data provides guidelines for selecting appropriate LiDAR systems and data processing tools for different research questions, and thus is of crucial importance. This study presents a comprehensive comparison of point clouds from four systems, linear and Geiger-mode LiDAR from manned aircraft and multi-beam LiDAR on unmanned aerial vehicle (UAV), and in-house developed Backpack, with the consideration of different forest canopy cover scenarios. The results suggest that the proximal Backpack LiDAR can provide the finest level of information, followed by UAV LiDAR, Geiger-mode LiDAR, and linear LiDAR. The emerging Geiger-mode LiDAR can capture a significantly higher level of detail while operating at a higher altitude as compared to the traditional linear LiDAR. The results also show: (1) canopy cover percentage has a critical impact on the ability of aerial and terrestrial systems to acquire information corresponding to the lower and upper portions of the tree canopy, respectively; (2) all the systems can obtain adequate ground points for digital terrain model generation irrespective of canopy cover conditions; and (3) point clouds from different systems are in agreement within a ±3 cm and ±7 cm range along the vertical and planimetric directions, respectively.

The timely and accurate recognition of damage to buildings after destructive disasters is one of the most important post-event responses. Due to the complex and dangerous situations in affected areas, field surveys of post-disaster conditions are not always feasible. The use of satellite imagery for disaster assessment can overcome this problem. However, the textural and contextual features of post-event satellite images vary with disaster types, which makes it difficult to use models that have been developed for a specific disaster type to detect damaged buildings following other types of disasters. Therefore, it is hard to use a single model to effectively and automatically recognize post-disaster building damage for a broad range of disaster types. Therefore, in this paper, we introduce a building damage detection network (BDD-Net) composed of a novel end-to-end remote sensing pixel-classification deep convolutional neural network. BDD-Net was developed to automatically classify every pixel of a post-disaster image into one of non-damaged building, damaged building, or background classes. Pre- and post-disaster images were provided as input for the network to increase semantic information, and a hybrid loss function that combines dice loss and focal loss was used to optimize the network. Publicly available data were utilized to train and test the model, which makes the presented method readily repeatable and comparable. The protocol was tested on images for five disaster types, namely flood, earthquake, volcanic eruption, hurricane, and wildfire. The results show that the proposed method is consistently effective for recognizing buildings damaged by different disasters and in different areas.

Information about urban built-up areas is important for urban planning and management. However, obtaining accurate information about urban built-up areas is a challenge. This study developed a general-purpose built-up area intelligent classification (BAIC) system that supports various types of data and classifiers. All of the steps in the BAIC were implemented using Python modules including Numpy, Pandas, matplotlib, and scikit-learn. We used the BAIC to conduct a classification experiment that involved seven types of input data; namely, Point of Interest (POI), Road Network (RN), nighttime light (NTL), a combination of POI and RN data (POI_RN), a combination of POI and NTL data (POI_NTL), a combination of RN and NTL data (RN_NTL), and a combination of POI, RN, and NTL data (POI_RN_NTL), and five classifiers, namely, Logistic Regression (LR), Decision Tree (DT), Random Forests (RF), Gradient Boosted Decision Trees (GBDT), and AdaBoost. The results show the following: (1) among the 35 combinations of the five classifiers and seven types of input data, the overall accuracy (OA) ranged from 76 to 89%, F₁ values ranged from 0.73 to 0.86, and the area under the receiver operating characteristic (ROC) curve (AUC) ranged from 0.83 to 0.95. The largest F₁ value and OA were obtained using the POI_RN_NTL data and AdaBoost, while the largest AUC was obtained using POI_RN_NTL and POI_NTL data against AdaBoost, LR, and RF; and (2) the advantages of the BAIC include its support for multi-source input data, its objective accuracy assessment, and its robust classifiers. The BAIC can quickly and efficiently realize the automatic classification of urban built-up areas at a reasonably low cost and can be readily applied to other urban areas in the world where any kind of POI, RN, or NTL data coverage is available. The results of this study are expected to provide timely and effective reference information for urban planning and urban management departments, and could also potentially be used to develop large-scale maps of urban built-up areas in the future.

Land-use planning and design (LPD) is one of the most critical passways toward sustainable development. LPD without thorough considerations can cause many problems, such as disharmony between people’s perception and nature, the chaos of spatial patterns, and the misuse of land resources. Landsenses ecology, a discipline based on natural elements and people’s perception, provide scientific basis to guide LPD. Here we summarized the state-of-the-art concept of optimal visual perception based on conventional optical theory and contemporary visualization technology. Instead of solely using an artistic design perspective to sum up experience, we combined human binocular visual angle and distance with the field of view (FOV) of cell phone cameras to determine an optimal visual perception. We explained the rationality of the concept of optimal visual perception with three examples, located at the Institute of Urban Environmental (IUE) from Chinese Academy of Sciences, the Welcoming-Guests Pine on Huangshan Mountain, and the Sunlight Rock of Gulangyu Island in Xiamen, China, respectively. Both landsenses involving the IUE and Welcoming-Guests Pine satisfy the required conditions for optimal visual perception, whereas the Sunlight Rock shows the chaos of near and far landscapes, which is not compatible with the optimal visual perception. At the end of this paper, we provide pieces of advice on applying optimal visual perception to land-use planners and architects as well as sustainability scholars.