Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the basic architecture of U-Net, an end-to-end deep convolutional neural network (denoted as DeepResUnet) was proposed, which can effectively perform urban building segmentation at pixel scale from VHR imagery and generate accurate segmentation results. The method contains two sub-networks: One is a cascade down-sampling network for extracting feature maps of buildings from the VHR image, and the other is an up-sampling network for reconstructing those extracted feature maps back to the same size of the input VHR image. The deep residual learning approach was adopted to facilitate training in order to alleviate the degradation problem that often occurred in the model training process. The proposed DeepResUnet was tested with aerial images with a spatial resolution of 0.075 m and was compared in performance under the exact same conditions with six other state-of-the-art networks—FCN-8s, SegNet, DeconvNet, U-Net, ResUNet and DeepUNet. Results of extensive experiments indicated that the proposed DeepResUnet outperformed the other six existing networks in semantic segmentation of urban buildings in terms of visual and quantitative evaluation, especially in labeling irregular-shape and small-size buildings with higher accuracy and entirety. Compared with the U-Net, the F1 score, Kappa coefficient and overall accuracy of DeepResUnet were improved by 3.52%, 4.67% and 1.72%, respectively. Moreover, the proposed DeepResUnet required much fewer parameters than the U-Net, highlighting its significant improvement among U-Net applications. Nevertheless, the inference time of DeepResUnet is slightly longer than that of the U-Net, which is subject to further improvement.

Urban green space provides a series of esthetic, environmental and psychological benefits to urban residents. However, the relationship between the visibility of green vegetation and perceived safety is still in debate. This research investigated whether green vegetation could help to increase the perceived safety based on a crowdsourced dataset: the Place Pulse 1.0 dataset. Place Pulse 1.0 dataset, which was generated from a large number of votes by online participants, includes geo-tagged Google Street View images and the corresponding perceived safety score for each image. In this study, we conducted statistical analyses to analyze the relationship between perceived safety and green vegetation characteristics, which were extracted from Google Street View images. Results show that the visibility of green vegetation plays an important role in increasing perceived safety in urban areas. For different land use types, the relationship between vegetation structures and perceived safety varies. In residential, urban public/institutional, commercial and open land areas, the visibility of vegetation higher than 2.5 m has significant positive correlations with perceived safety, but there exists no significant correlation between perceived safety and the percentage of green vegetation in transportation and industrial areas. The visibility of vegetation below 2.5 m has no significant relationship with the perceived safety in almost all land use types, except for multifamily residential land and urban public/institutional land. In general, this study provided insight for the relationship between green vegetation characteristics and the perception of environment, as well as valuable reference data for developing urban greening programs.

We are currently living in the era of big data. The volume of collected or archived geospatial data for land use and land cover (LULC) mapping including remotely sensed satellite imagery and auxiliary geospatial datasets is increasing. Innovative machine learning, deep learning algorithms, and cutting-edge cloud computing have also recently been developed. While new opportunities are provided by these geospatial big data and advanced computer technologies for LULC mapping, challenges also emerge for LULC mapping from using these geospatial big data. This article summarizes the review studies and research progress in remote sensing, machine learning, deep learning, and geospatial big data for LULC mapping since 2015. We identified the opportunities, challenges, and future directions of using geospatial big data for LULC mapping. More research needs to be performed for improved LULC mapping at large scales.

Change detection (CD) with hyperspectral images (HSIs) can be effectively performed using deep learning networks (DLNs) by taking advantage of HSIs for their abundant spectral and spatial information and the excellent performance of DLN in machine learning. By modeling the temporal dependence of multiscale representative features, more discriminative information reflecting land use and land cover (LULC) changes can be obtained by suppressing less correlated information while improving the robustness of pseudo-changes caused by imaging noises. However, preserving time-dependent multiscale representative features while extracting spatial–spectral features based on conventional DLN is difficult, mainly due to the structural limitation of conventional DLN. A multipath convolutional long short-term memory (LSTM) multipath convolutional long short-term memory neural network (MP-ConvLSTM) taking advantage of LSTM and convolutional neural network (CNN) through the designed parallel architecture to learn multilevel temporal dependencies of bitemporal HSIs, therefore, was proposed for extracting multiscale temporal–spatial–spectral features by combining hidden states from different paths of ConvLSTM in the present study. In the proposed MP-ConvLSTM, the efficient channel attention (ECA) module was introduced to refine features of different paths, and Siamese CNN was adopted to reduce HSIs’ dimensionality and extract preliminary features to build up an end-to-end trainable model for CD with HSIs. The validity of the MP-ConvLSTM was evaluated using the binary and multiclass CD datasets. The CD accuracy of the proposed MP-ConvLSTM was visually and statistically evaluated by different criteria and compared with those derived from several state-of-the-art (SOTA) CD algorithms. The experiments demonstrated that our proposed model not only outperformed those SOTA CD models but also exhibited better tradeoff between complexity and accuracy in general.

Traditional methods of detecting and mapping utility poles are inefficient and costly because of the demand for visual interpretation with quality data sources or intense field inspection. The advent of deep learning for object detection provides an opportunity for detecting utility poles from side-view optical images. In this study, we proposed using a deep learning-based method for automatically mapping roadside utility poles with crossarms (UPCs) from Google Street View (GSV) images. The method combines the state-of-the-art DL object detection algorithm (i.e., the RetinaNet object detection algorithm) and a modified brute-force-based line-of-bearing (LOB, a LOB stands for the ray towards the location of the target [UPC at here] from the original location of the sensor [GSV mobile platform]) measurement method to estimate the locations of detected roadside UPCs from GSV. Experimental results indicate that: (1) both the average precision (AP) and the overall accuracy (OA) are around 0.78 when the intersection-over-union (IoU) threshold is greater than 0.3, based on the testing of 500 GSV images with a total number of 937 objects; and (2) around 2.6%, 47%, and 79% of estimated locations of utility poles are within 1 m, 5 m, and 10 m buffer zones, respectively, around the referenced locations of utility poles. In general, this study indicates that even in a complex background, most utility poles can be detected with the use of DL, and the LOB measurement method can estimate the locations of most UPCs.

Land use and land cover (LULC) patterns play an important role in the establishment and spread of invasive plants. Understanding LULC changes is useful for early detection and management of land-use change to reduce the spread of invasive species. The primary objective of this study is to analyze and predict LULC changes in Connecticut. LULC maps for 1996, 2001 and 2006 were selected to analyze past land cover changes, and then potential LULC distribution in 2018 was predicted using the Multi-Layer Perceptron Markov Chain (MLP_MC) model. This study shows that the total area of forest has been decreasing, mainly caused by urban development and other human activity in Connecticut. The model predicts that the study area will lose 5535 ha of deciduous forest and gain 3502 ha of built-up area from 2006 to 2018. Moreover, forests near built-up areas and agriculture lands appear to be more vulnerable to conversion. Changes in LULC may result in subtle spatial shifts in invasion risk by an abundant invasive shrub, Japanese barberry (Berberis thunbergii). The gain of developed areas at the landscape scale was most closely linked to increased future invasion risk. Our findings suggest that the forest conversion needs to be controlled and well managed to help mitigate future invasion risk.