With the development of artificial intelligence technology, UAVs have the ability to perceive the environment. UAV combined with target detection technology for road environment perception has received extensive attention. However, the complexity and variability of real-world road environments pose challenges for target detection. To address these challenges, we propose a UAV small target detection algorithm AS-YOLOV5 with adaptive feature fusion and improved attention mechanism. In the feature extraction phase, AS-YOLOV5 employs soft pooling to bolster the feature extraction network, mitigating the loss of critical edge information of small targets inherent in standard down-sampling techniques. Our feature fusion method incorporates learnable parameters, effectively rebalancing feature layers to ensure small target information remains significant during the fusion process and is not obscured by large target features. The subspace attention module is optimized to enhance the representation of small target features while suppressing background interference. To ensure the detection branch captures essential shallow information about small objects, we introduce an additional feature extraction layer for feature fusion. Simulation results show that the proposed method outperforms the existing algorithms. AS-YOLOV5 achieved a mean average precision (mAP) of 56.36% on the BDD100K data set and an impressive 93.33% on the KITTI data set with an Intersection over Union (IoU) threshold of 0.5.

Image matching is a fundamental and critical task of multisource remote sensing image applications. However, remote sensing images are susceptible to various noises. Accordingly, how to effectively achieve accurate matching in noise images is a challenging problem. To solve this issue, we propose a robust multisource remote sensing image matching method utilizing attention and feature enhancement against noise interference. In the first stage, we combine deep convolution with the attention mechanism of transformer to perform dense feature extraction, constructing feature descriptors with higher discriminability and robustness. Subsequently, we employ a coarse-to-fine matching strategy to achieve dense matches. In the second stage, we introduce an outlier removal network based on a binary classification mechanism, which can establish effective and geometrically consistent correspondences between images; through weighting for each correspondence, inliers vs. outliers classification are performed, as well as removing outliers from dense matches. Ultimately, we can accomplish more efficient and accurate matches. To validate the performance of the proposed method, we conduct experiments using multisource remote sensing image datasets for comparison with other state-of-the-art methods under different scenarios, including noise-free, additive random noise, and periodic stripe noise. Comparative results indicate that the proposed method has a more well-balanced performance and robustness. The proposed method contributes a valuable reference for solving the difficult problem of noise image matching. The code is available at https://github.com/liyuan-repo/RMmodel.

Road object detection technology is a key technology to achieve intelligent assisted driving. The complexity and variability of real-world road environments make the detection of densely occluded objects more challenging in autonomous driving scenarios. This study proposes an occluded object detection algorithm, RE-YOLOv5, based on receptive field enhancement to assist with the difficult identification of occluded objects in complex road environments. To efficiently extract irregular features, such as object deformation and truncation in occluded scenes, deformable convolution is employed to enhance the feature extraction network. Additionally, a receptive field enhancement module is designed using atrous convolution to capture multi-scale contextual information and better understand the relationship between occluded objects and their surrounding environment. Considering that the ordinary non-maximum suppression method in dense occlusion scenarios will incorrectly suppress the prediction box of the occluded object, EIOU was used to optimize the non-maximum suppression method. Experiments were conducted on two benchmark datasets, KITTI and CityPersons. The proposed method achieves a mean average precision (mAP) of 82.04% on KITTI, representing an improvement of 2.34% over the baseline model. For heavily occluded objects on CityPersons, the Log Average Miss Rate (${\mathrm{MR}}^{-2}$) is reduced to 40.31%, which is a decrease of 9.65% compared to the baseline. These results demonstrate that the proposed method significantly outperforms other comparative algorithms in detecting occluded objects across both datasets.

Stricken areas are shut off from the world, as large-scale infrastructures (e.g. bridges, roads and power equipments) have been destroyed after earthquakes, floods, and other disasters. Large-scale and cross-regional communication in the disaster area is difficult to achieve due to the harsh communication environment, such as unstable communication links and limited network resources, especially for remote isolated areas. Delay tolerant networks (DTNs) use the way of a “store-carry-forward” to transfer messages, which is suitable for the large transmission delay and intermittent link communication. In this paper, the DTNs based on regional center node and Unmanned Aerial Vehicle (UAV) is proposed to build the post-disaster emergency communication network. Further, a region-based message selective delivery routing policy is proposed for the emergency communication network. The received messages are classified according to its destination address at the regional center node and the UAV ferry node. In this way, the data packets can be accurately delivered to the corresponding area, and redundant data packets will be reduced in the network. The effect of the routing policy on network performance is evaluated. Simulation results show that the policy can effectively improve the data delivery rate, reduce the overhead ratio and significantly reduce the transmission delay.

Aiming at the problem of how to improve the requirement satisfaction of multi-point target imaging reconnaissance tasks and the utilization efficiency of satellite resources, a multi-point target imaging reconnaissance requirement fusion method based on genetic optimization is proposed in this paper. Firstly, the basic constraints that can be fused between multi-point targets are analysed, and on this basis, a point-target synthetic observation model is constructed. Secondly, considering the constraints of observation time window, observation angle and transition time between synthetic tasks, a genetic algorithm-based multi-point target requirements fusion method is designed. Finally, through the simulation analysis, it is concluded that with the continuous increase of user requirements, the fusion method based on genetic optimization can still achieve better task satisfaction to the user’s imaging requirements, which greatly improves the use efficiency of imaging satellites.