Smart management of urban space is an important way to achieve the goal of sustainable urban development. Unmanned aerial vehicles (UAVs) have been widely used in urban space management work and have greatly improved the level of it. UAV technology assisting urban space management involves many technical details and has generated a number of problems. Therefore, a systematic review of the applications of UAVs in urban spatial management work is very necessary and can provide a comprehensive reference for relevant researchers. This is conducive to the generation of more new insights, methods, and applications. However, according to our research, there is a lack of relevant systematic investigation. We screened and researched a large number of relevant literatures (about 230) with the help of search tools such as Web of Science and IEEE Explore, and combined with our own working experience to review and summarize the field in an all-round way. Taking the definition, needs, and challenges of urban spatial management as an entry point, this paper systematically summarizes the task flow, working paradigm, technical system, and application direction of UAV-assisted urban spatial management. It also takes our recently developed UAV urban management system as an example to provide an introduction on how to integrate advanced technologies such as UAV and artificial intelligence. Finally, this paper summarizes several concluding findings and proposes several future research directions. The research in this paper shows that UAV technology has already played a great role in urban spatial management work, but it is still far from realizing automation and intelligence, and it needs to continue to make efforts in terms of methods, systems, applications, and policies. In order to achieve these goals, UAV technology can be further integrated with advanced technologies such as deep learning, more types of UAV industry applications can be carried out, more functional UAS can be developed, and better management policies can be formulated.

One of the fundamental tasks in autonomous driving is environment perception for pedestrian detection, where the fused pedestrian detection using camera and light detection and ranging (LiDAR) information imposes challenges since the data alignment, compensation, and fusion between different data modes are challenging and the simultaneous acquisition of data from two different modalities also increases the difficulty. This work addresses the above challenges from both of the hardware and software dimensions. First, a multimodal pedestrian data acquisition platform is designed and constructed using an RGB camera, sparse LiDAR, and data processing module including hardware connection and deployment, sensor distortion correction and joint calibration, and data acquisition synchronization. Pedestrian data from multiple scenes are then collected using this platform to produce and form a dedicated multimodal pedestrian detection dataset. Further, a two-branch multimodal multilevel fusion pedestrian detection network (MM-Net) is proposed, which includes a two-branch feature extraction module and a feature-level data fusion module. Extensive experiments are performed on the multimodal pedestrian detection dataset and KITTI dataset for the comparison with the existing models. The experimental results demonstrate the superior performance of MM-Net.

Soil elements refer to different types of soil with unique colors, textures, and particle sizes. Their interpretation is essential for agriculture, ecological environment and land permeability assessment. This typically requires experts with dual knowledge in geology and remote sensing. With the increasing volume of remote sensing data, the traditional “visual interpretation" and “field survey" technique is no longer sufficient to meet the demands. Because of the challenges such as the fine structure of soil, complex and variable natural scenes, and strong spatial variability, there remains a considerable gap between the accuracy of deep learning-based methods and expert interpretation. To improve the accuracy of intelligent soil elements interpretation, this study proposes a soil interpretation framework coupling implicit knowledge with multispectral image (SIFCIM). This framework quantifies implicit knowledge, such as interpretation symbol and terrain feature, into matrix data (interpretation symbol distance field and digital elevation model). To align with the SIFCIM, an Implicit-Knowledge-Guided Adaptive Feature Fusion Network (IAFFNet) is constructed, which enhances the utilization efficiency of auxiliary features through an adaptive implicit feature fusion module and a global feature dependence module. Experimental results demonstrate that IAFFNet outperforms interpretation methods with single remote sensing image, achieving approximately 4.34% and 6.62% improvements in overall pixel accuracy and mean intersection over union, respectively. These results validate the effectiveness and robustness of the implicit-knowledge-guided approach in soil elements interpretation. To our knowledge, this work is the first to apply the concept of implicit knowledge to soil elements interpretation, providing a novel insight for related research.

The survey and monitoring of natural resources in complex and hazardous areas with rugged terrain and insufficient infrastructure is a challenging issue in the industry. Currently, ground vehicles, unmanned aerial vehicles (UAVs), quadruped robots, and other unmanned systems are widely used in fields related to natural resource survey and monitoring. However, the application scenarios and practical needs for resource survey and monitoring in complex and hazardous areas have not been fully considered. Additionally, the integration of multidimensional, heterogeneous equipment platforms to achieve a comprehensive and 3-D monitoring capability has yet to be fully reached. In this article, a “Vehicle–Air–Ground” 3-D survey and monitoring vehicle system LandExplorer-1 has been developed for natural resources survey and monitoring in complex and hazardous areas. This system enables the organic combination of ground vehicles, UAVs, and quadruped robots, breaking the limitations of single-platform systems and significantly enhancing data collection efficiency. It addresses the challenges of data acquisition difficulties, high operational risks, and high costs in complex environments.

Cultivated land (CL) is a critical foundation for ensuring food security and sustainable development. However, in recent years, driven by factors, such as population growth and economic expansion, cultivated land has faced threats, including illegal occupation. Advanced technologies and equipment are essential for the protection and monitoring of cultivated land. Although satellite remote sensing technologies can periodically monitor cultivated land changes on a large scale, their timeliness and flexibility are limited by revisit cycles and weather conditions. Uncrewed aerial vehicles (UAVs) provide high-resolution imagery and a wide field of view in field surveys. However, current UAV-based systems often lack automated data processing and sufficient mobility, which limits operational efficiency. To address these issues, this article proposes and implements LandExplorer-CL, an integrated vehicle–UAV–cloud system for monitoring and verifying suspected illegal cultivated land occupation. The system integrates a ground vehicle with off-road mobility and an automated UAV docking station. Together, these components form a highly mobile and rapidly deployable intelligent operation platform. Through the design of a specialized target detection model, the system achieves high-precision detection of suspected illegal occupation targets in cultivated land. In addition, an intelligent land-cover change analysis framework enhanced with retrieval-augmented generation and large multimodal models is utilized to reduce hallucinations and dependence on massive labeled samples. Extensive experimental results demonstrate the practical effectiveness of this system in monitoring cultivated land change polygons in large-scale and complex rural environments.