Visual Simultaneous Localization and Mapping (VSLAM) is a prerequisite for robots to accomplish fully autonomous movement and exploration in unknown environments. At present, many impressive VSLAM systems have emerged, but most of them rely on the static world assumption, which limits their application in real dynamic scenarios. To improve the robustness and efficiency of the system in dynamic environments, this paper proposes a dynamic RGBD SLAM based on a combination of geometric and semantic information (DGS-SLAM). First, a dynamic object detection module based on the multinomial residual model is proposed, which executes the motion segmentation of the scene by combining the motion residual information of adjacent frames and the potential motion information of the semantic segmentation module. Second, a camera pose tracking strategy using feature point classification results is designed to achieve robust system tracking. Finally, according to the results of dynamic segmentation and camera tracking, a semantic segmentation module based on a semantic frame selection strategy is designed for extracting potential moving targets in the scene. Extensive evaluation in public TUM and Bonn datasets demonstrates that DGS-SLAM has higher robustness and speed than state-of-the-art dynamic RGB-D SLAM systems in dynamic scenes.

Path planning is one of the key parts of unmanned aerial vehicle (UAV) fast autonomous flight in an unknown cluttered environment. However, real-time and stability remain a significant challenge in the field of path planning. To improve the robustness and efficiency of the path planning method in complex environments, this paper presents RETRBG, a robust and efficient trajectory replanning method based on the guiding path. Firstly, a safe guiding path is generated by using an improved A* and path pruning method, which is used to perceive the narrow space in its surrounding environment. Secondly, under the guidance of the path, a guided kinodynamic path searching method (GKPS) is devised to generate a safe, kinodynamically feasible and minimum-time initial path. Finally, an adaptive optimization function with two modes is proposed to improve the optimization quality in complex environments, which selects the optimization mode to optimize the smoothness and safety of the path according to the perception results of the guiding path. The experimental results demonstrate that the proposed method achieved good performance both in different obstacle densities and different resolutions. Compared with the other state-of-the-art methods, the quality and success rate of the planning result are significantly improved.

Point cloud fitting plays an important role in various applications of laser scanning technology. Currently, the most dominant algorithms are the linear least squares (LS) method and the Random Sample Consensus (RANSAC) algorithm, in which the random noises of the point cloud coordinates and the influence of the corresponding stochastic model cannot be fully considered. In this study, the mathematical model of point cloud fitting is uniformly described using the nonlinear Gauss-Helmert (NGH) model, in which the nonlinear relationship between the measurements and parameters as well as the effects of all random errors can be considered. In addition, the covariance matrix of point cloud coordinates obtained from the precision of the original measurements is employed to construct the corresponding stochastic model. By further introducing an equivalent weight scheme of robust estimation, a novel point cloud fitting method is proposed based on the robust NGH (RNGH) model. Unlike the previous studies, the RNGH-based algorithm can effectively resist the negative effects of outliers with a full consideration of all random errors in various linear and nonlinear fitting problems. To verify the performance of the proposed RNGH, comparative experiments of point cloud fitting are employed in both simulated and real-world scenarios, respectively. The results demonstrate that the proposed point cloud fitting algorithm has significant advantages over LS and RANSAC in terms of the accuracy and robustness.

In semantic segmentation tasks, the transition from convolutional neural networks (CNN) to transformers is driven by the latter's superior ability to capture global semantic information in remote sensing images. However, most transformer methods face challenges such as slow inference speed and limitations in capturing local features. To address these issues, this study designs a hybrid approach that integrates knowledge distillation with a combination of CNN and transformer to enhance semantic segmentation in remote sensing images. First, this paper proposes the Dual-Path Convolutional Transformer Network (DP-CTNet) with a dual-path structure to leverage the strengths of both CNN and transformers. It incorporates Feature Refinement Module to optimize the transformer's feature learning, and Feature Fusion Module to effectively merge CNN and transformer features, preventing the insufficiently learning of local features by the transformer. Then DP-CTNet serves as the teacher model, and pruning and knowledge distillation are employed to create Efficient DP-CTNet (EDP-CTNet) with superior segmentation speed and accuracy. Angle Knowledge Distillation (AKD) is proposed to enhance the feature migration learning of DP-CTNet during knowledge distillation, leading to improved EDP-CTNet performance. Experimental results demonstrate that DP-CTNet thoroughly combines the respective advantages of CNN and Transformer, maintaining local detail features while learning extensive sequential semantic information. EDP-CTNet not only delivers impressive segmentation speed but also exhibits excellent segmentation accuracy following AKD training. In comparison to other models, the two models proposed in this paper notably distinguish themselves in terms of accuracy and result visualization.

Intangible cultural heritage (ICH) reflects a region’s history and culture, serving as a significant indicator of regional identity and cohesion. The Grand Canal Basin in China is rich in historical traditions, containing a rich array of ICH resources. Analyzing the spatiotemporal distribution characteristics and influencing factors of ICH within the Grand Canal Basin of China can provide a scientific basis for developing cultural industries and promoting sustainable regional economic growth. This study employed GIS-based spatial analysis methods, including kernel density estimation, the mean nearest neighbor index, and standard deviation ellipse, to investigate the spatiotemporal distribution of 504 national-level ICH items (including extensions) in the Grand Canal Basin of China. The results demonstrate the significant spatial clustering of ICH, with concentrations in high-density regions, particularly at the northern and southern ends of the canal. There is significant regional disparity in the distribution of ICH, with an uneven quantity and structure, predominantly featuring traditional skills and traditional drama categories. The average centroid shift of ICH exhibits a north-to-south oscillatory trajectory. However, overall, it demonstrates a southward-moving trend. This study also underscores the impacts of urbanization, population density, economic development, and transportation infrastructure on ICH distribution. Among these factors, urbanization exerts the strongest influence on the spatial distribution of ICH. The impact of the natural environment is relatively minor; however, it remains a significant element that cannot be overlooked during development. This research offers valuable data and insights for local governments and institutions to formulate evidence-based strategies for the protection and sustainable utilization of ICH resources, promoting sustainable cultural and economic development in the Grand Canal Basin.

Accurate estimation of terrestrial ecosystem carbon storage and the scientific formulation of ecological conservation and land use policies are essential for promoting regional low-carbon sustainable development and achieving the goal of “carbon neutrality.” In this study, the FLUS–InVEST model was used to evaluate the carbon stocks of the Jiangsu coastal zone in China from 1995 to 2020 and scientifically forecast the changes in carbon stocks in 2030 under three scenarios: natural exploitation, ecological protection, and economic development. The results are as follows: (1) From 1995 to 2020, carbon storage in the coastal zone initially remained stable before declining, a trend closely linked to the accelerated urbanization and economic growth of Jiangsu Province. (2) By 2030, carbon storage under the three scenarios exhibits a pattern of “S1 decrease–S2 increase–S3 decrease,” with a more significant increase in construction land under the natural development and economic development scenarios compared to the ecological protection scenario. (3) The sensitivity of carbon storage to land use changes varies across scenarios. In the natural development scenario, carbon storage is most affected by forest reduction and construction land expansion. In the ecological protection scenario, it is more responsive to increases in non-construction land. In the economic development scenario, the expansion of construction land leads to the most significant decrease in carbon storage. Therefore, when formulating future territorial spatial planning policies and urban development strategies, it is essential to consider ecological protection and economic development scenarios comprehensively, taking into account carbon sequestration capabilities. This approach will ensure effective conservation and restoration of damaged ecosystems while safeguarding the robust development of urban economies and societies.