Classification is a common objective when analyzing hyperspectral images, where each pixel is assigned to a predefined label. Deep learning-based algorithms have been introduced in the remote-sensing community successfully in the past decade and have achieved significant performance improvements compared with conventional models. However, research on the extraction of sequential features utilizing a single image, instead of multi-temporal images still needs to be further investigated. In this paper, a novel strategy for constructing sequential features from a single image in long short-term memory (LSTM) is proposed. Two pixel-wise-based similarity measurements, including pixel-matching (PM) and block-matching (BM), are employed for the selection of sequence candidates from the whole image. Then, the sequential structure of a given pixel can be constructed as the input of LSTM by utilizing the first several matching pixels with high similarities. The resulting PM-based LSTM and BM-based LSTM are appealing, as all pixels in the whole image are taken into consideration when calculating the similarity. In addition, BM-based LSTM also utilizes local spectral-spatial information that has already shown its effectiveness in hyperspectral image classification. Two common distance measures, Euclidean distance and spectral angle mapping, are also investigated in this paper. Experiments with two benchmark hyperspectral images demonstrate that the proposed methods achieve marked improvements in classification performance relative to the other state-of-the-art methods considered. For instance, the highest overall accuracy achieved on the Pavia University image is 96.20% (using both BM-based LSTM and spectral angle mapping), which is an improvement compared with 84.45% overall accuracy generated by 1D convolutional neural networks.

Classification is a critical, widely employed type of hyperspectral image (HSI) processing. Recently, deep learning models have been attracting more attention within the hyperspectral remote-sensing community due to their improved classification performance. Among them, recurrent neural networks (RNNs), which were initially used to handle sequential data, have been applied to HSI classification with promising results. The key point for such RNN-based models in a classification context is the extraction of a sequential feature for each individual pixel in a HSI. One popular strategy is to first extract similar pixels compared with a target pixel from the HSI, and then use those similar pixels to encode its sequential feature. However, the computational cost is tremendous, especially if such similarity-calculation search is done on the whole image. In this article, inspired by our previous work regarding similarity measurement-based sequential feature construction, a faster sequential feature extraction framework for long short-term memory (LSTM)-based HSI classification is proposed, where object-based segmentation method is employed for the purpose of imposing spatial constraints and computational acceleration. Within the proposed framework, both the local segment containing the target pixel and nonlocal segments are considered. For a target pixel, similar segments are selected first based on segment-based features, and then similar pixels from selected segments are extracted to construct a sequential feature. During pixel-wise similarity measurement, both spectral and spatial information are considered in such computation. Experimental results on three benchmark HSI data sets illustrate that the proposed methods achieve promising classification performance with markedly lower computation-time cost.

Auditing and mapping traffic infrastructure is a crucial task in urban management. For example, signalized intersections play an essential role in transportation management; however, effectively identifying these intersections remains unsolved. Traditionally, signalized intersection data are manually collected through field audits or checking street view images (SVIs), which is time-consuming and labor-intensive. This study proposes an effective protocol to identify signalized intersections using road networks and SVIs. First, we propose a six-step geoprocessing model to generate an intersection feature layer from road networks. Second, we utilize up to three nearest SVIs to capture streetscapes at each intersection. Then, a deep learning-based image segmentation model is adopted to recognize traffic light-related pixels from each SVI. Last, we design a post-processing step to generate new features characterizing SVIs’ segmentation results at each intersection and build a decision tree model to determine the traffic control type. Results demonstrate that the proposed protocol can effectively identify signalized intersections with an overall accuracy of 97.05%. It also proves the effectiveness of SVIs for auditing urban infrastructures. This study can directly benefit transportation agencies by providing a ready-to-use smart audit and mapping solution for large-scale identification and mapping of signalized intersections.

Surface processes on debris-covered glaciers are governed by a variety of controlling factors including climate, debris load, water bodies, and topography. Currently, we have not achieved a general consensus on the role of supraglacial processes in regulating climate–glacier sensitivity in High Mountain Asia, which is mainly due to a lack of an integrated understanding of glacier surface dynamics as a function of debris properties, mass movement, and ponding. Therefore, further investigations on supraglacial processes is needed in order to provide more accurate assessments of the hydrological cycle, water resources, and natural hazards in the region. Given the scarcity of long-term in situ data and the difficulty of conducting fieldwork on these glaciers, many numerical models have been developed by recent studies. This review summarizes our current knowledge of surface processes on debris-covered glaciers with an emphasis on the related modeling efforts. We present an integrated view on how numerical modeling provide insights into glacier surface ablation, supraglacial debris transport, morphological variation, pond dynamics, and ice-cliff evolution. We also highlight the remote sensing approaches that facilitate modeling, and discuss the limitations of existing models regarding their capabilities to address coupled processes on debris-covered glaciers and suggest research directions.