Green space is an important adaptation strategy against urban thermal environmental change. However, the impact of the spatiotemporal changes in green space on urban mesoscale meteorology and human thermal comfort has been understudied. Here, we incorporated gridded urban green fraction (GF) corresponding to 2016 and 2020 in central Wuhan into the Weather Research and Forecasting model to investigate the thermal environmental effects of changes in GF. Results show that a 10% increase in GF produced a nighttime cooling of 0.167 degrees C and a daytime cooling of 0.075 degrees C. Meanwhile, it increased atmospheric moisture content by 0.131 g/kg in the daytime and 0.042 g/kg at night. Consequently, the nighttime heat index (HI) was reduced by 0.258 degrees C but the daytime HI was raised by 0.056 degrees C. Addition of GF induced a greater magnitude of change in 2-m air temperature and the HI when the GF in a grid cell exceeded 0.6. The reduction in ground heat flux due to the conversion of urban fraction to green fraction, in conjunction with the weak turbulence, contributed to the greater magnitude of cooling in the nighttime than in the daytime. To enhance green space connectivity should be an effective pathway to thermal adaptation in high-density built environments like Wuhan.

Research on ecological corridor extraction methods has made some progress and has been gradually applied to the planning and construction of regional ecological corridors, which play a role in biodiversity conservation efforts. However, the factors affecting species migration in ecological environments are very complex, especially anthropogenic disturbances, typically including noise pollution. Their effects on species habitats, reproduction, predation, and other activities are currently underestimated. In this paper, we propose an algorithm for superposition analysis of multiple road impacts and construct an ecological corridor extraction method that considers landscape pattern, habitat quality, remote sensing ecology, and road traffic resistance to address the shortcomings of current ecological corridor extraction methods that underestimate the potential impacts of road traffic. An extraction of ecological corridors was completed in Wuhan, and a quantitative comparative analysis was conducted from multiple perspectives. The results show that the improved method was effective, with the proportion of ecological corridors not re-identified due to road traffic impacts being 0.45% and the proportion of ecological corridors with significant changes in spatial location, represented by regions far from roads or high road network density, being 22.15% in the whole of Wuhan.

Given the initial calibration of multiple sensors, the fine registration between Mobile Laser Scanning (MLS) point clouds and panoramic images is still challenging due to the unforeseen movement and temporal misalignment while collecting. To tackle this issue, we proposed a novel automatic method to register the panoramic images and MLS point clouds based on the matching of pole objects. Firstly, 2D pole instances in the panoramic images are extracted by a semantic segmentation network and then optimized. Secondly, every corresponding frustum point cloud of each pole instance is obtained by a shape-adaptive buffer region in the panoramic image, and the 3D pole object is extracted via a combination of slicing, clustering, and connected domain analysis, then all 3D pole objects are fused. Finally, 2D and 3D pole objects are re-projected onto virtual images respectively, and then fine 2D-3D correspondences are collected through maximizing pole overlapping area by Particle Swarm Optimization (PSO). The accurate extrinsic orientation parameters are acquired by the Efficient Perspective-N-Point (EPnP). The experiments indicate that the proposed method performs effectively on two challenging urban scenes with an average registration error of 2.01 pixels (with RMSE 0.88) and 2.35 pixels (with RMSE 1.03), respectively.

Outdated or sketchy inventory of street furniture may misguide the planners on the renovation and upgrade of transportation infrastructures, thus posing potential threats to traffic safety. Previous studies have taken their steps using point clouds or street-view imagery (SVI) for street furniture inventory, but there remains a gap to balance semantic richness, localization accuracy and working efficiency. Therefore, this paper proposes an effective pipeline that combines SVI and point clouds for the inventory of street furniture. The proposed pipeline encompasses three steps: (1) Off-the-shelf street furniture detection models are applied on SVI for generating two-dimensional (2D) proposals and then three-dimensional (3D) point cloud frustums are accordingly cropped; (2) The instance mask and the instance 3D bounding box are predicted for each frustum using a multi-task neural network; (3) Frustums from adjacent perspectives are associated and fused via multi-object tracking, after which the object-centric instance segmentation outputs the final street furniture with 3D locations and semantic labels. This pipeline was validated on datasets collected in Shanghai and Wuhan, producing component-level street furniture inventory of nine classes. The instance-level mean recall and precision reach 86.4%, 80.9% and 83.2%, 87.8% respectively in Shanghai and Wuhan, and the point-level mean recall, precision, weighted coverage all exceed 73.7%.

Benefiting from the development of deep learning, researchers have made significant progress and achieved superior performance in the semantic segmentation of remote sensing (RS) data. However, when encountering an unseen scenario, the performance of a trained model deteriorates dramatically because of the domain shift. Unsupervised domain adaptation (UDA) provides an alternative to address the issue. Aligning the high-level representations via adversarial learning is a popular way, but it is difficult when there is a large gap in input space. With this consideration, we design a framework to jointly align the distribution in input and feature space. For input space alignment, we unify the resolution for the consistency of content and propose a lightweight module named Digital Number Transformer (DNT) to reduce the visual differences. For feature space alignment, we design a Multi-Scale Feature aggregation (MSF) module and introduce the Fine-Grained Discriminator (FGD) to conduct a category-level alignment at multiple layers so that features can be fully aligned and negative transfer can be reduced. We carried out experiments in diverse cross-domain scenarios, including the discrepancy in geographic position and the discrepancy in both geographic position and imaging mode. Comprehensive experiments demonstrate that our method outperforms other state-of-the-art methods in all scenarios.