The Space-Air-Ground Integrated Network utilizes integrated densing, communication, and computation (ISCC) technology to address 6G users’ demands, but as the ISCC services expand, resource allocation and interference management become new challenges. To address these questions, a NOMA-MIMO-based space-air-ground ISCC system is proposed which include unmanned aerial vehicles (UAVs) integrated sensing, communication, and computation functions. Communication and sensing between the ground layer and UAVs are achieved through NOMA-MIMO technology, maximizing computation offloading capacity and suppressing interference between communication and sensing. Low Earth orbit satellite in the space layer can communicate with UAVs, providing ample computational resources for task processing. To minimize the system’s weighted energy consumption, a joint non-convex optimization problem is formulated and decomposed into sub-problems: beamforming design, offloading ratio optimization, and computation resource allocation optimization. An algorithm is proposed to solve these sub-problems using fractional programming based on quadratic transformation, weighted minimum mean square error, and successive convex approximation methods. Simulation results show that: i) The proposed system and algorithms significantly reduce system energy consumption compared to the benchmark scheme while ensuring sensing, communication, and computation performance, and ii) NOMA-MIMO can achieve effective interference management and improve resource efficiency.

Accurate detection of passable regions in images is important for ensuring the safe navigation of unmanned surface vehicles, especially in inland waterways with irregular waterlines and various obstacles. However, the existing methods are susceptible to environmental changes and produce high false-positive rates (FPRs) for confusable textures and complex edge details. We, therefore, propose a collision-free waterway segmentation network based on deep learning such that pixel-level classification results can be obtained. The segmentation accuracy for indistinguishable textures is improved by learning the context dependency of features through a modified context prior, and the detailed refinement of waterlines and small obstacles is achieved via an asymmetric encoder–decoder structure. To learn the features of waterways as comprehensively as possible, data integration and data augmentation are performed on three public datasets. In addition, a new annotated urban waterway dataset called the Dasha River dataset is proposed and made publicly available. The proposed model is tested and cross validated using multiple inland and maritime water segmentation datasets, the results of which show that the model achieves superior performance than the current state of the art with pixel accuracy (PA) of 97.43% and FPR of 1.37%.

The extensive coverage of satellite constellations has rendered the satellite–terrestrial integrated network (STIN) a pivotal solution for communication and computation services in internet of vehicles (IoVs) rescuing in remote or disaster areas with limited terrestrial networks. To optimise network resource utilisation and service quality, the integration of the service function chain (SFC) into STIN‐enabled IoV rescuing systems has become essential. However, traditional SFC‐based STIN systems encounter challenges in flow scheduling flexibility, stemming from the sequential execution of subtasks on satellites equipped with virtual network functions (VNFs). This leads to a trade‐off between data volume reduction and the additional communication and computation energy costs incurred in the orbit. To address this issue, this paper introduces a space ground collaborative SFC (SGC‐SFC) flow scheduling strategy. This strategy enables the execution of subtasks on either VNF‐equipped satellites or the ground vehicle formation, contingent on network conditions. Firstly, we carry out a computation–space–time graph (CSTG) model specifically for the STIN‐enabled IoV rescuing system with SFC. This model integrates the computational layer into the space–time graph (STG), accurately capturing the data volume reduction characteristics and sequential execution constraints of SFC in the STIN‐enabled IoV rescuing system. Secondly, a SGC‐SFC flow scheduling algorithm is designed to identify a set of feasible paths with minimal energy cost and maximum processable data volume. Simulation results validate the effectiveness and robustness of our proposed SGC‐SFC under diverse conditions.

Millimeter-wave (mmWave) technology is essential for meeting the reliable connectivity and high-capacity demands of autonomous driving applications. Vehicle-to-infrastructure (V2I) networks have been modeled and analyzed based on stochastic geometry (SG) in many studies. However, most studies focus only on two-dimensional (2D) antenna models and disregard a key characteristic of V2I networks, i.e., the rapid mobility of vehicles. In this work, a three-dimensional (3D) coverage and connectivity analysis framework is proposed for mmWave V2I downlink transmission based on SG. First, a realistic 3D system model is developed, which includes 3D transmission channel, blockage, and antenna array models. Then, exact expressions for the coverage probability, connectivity probability, and effective throughput of a typical vehicle are derived. Finally, the theoretical analysis is validated through simulation results, which also reveal that an optimal density of roadside units (RSUs) that maximizes spectral efficiency exists and that disregarding the effect of the vertical beam of a 3D antenna array can lead to inaccurate evaluations. Moreover, appropriately setting system parameters can mitigate the negative impact of high vehicular mobility on connectivity performance.