While coordination among multiple flying vehicles improves aerial logistics efficiency, safe and orderly operation requires robust detection and collision-avoidance capabilities. These requirements apply to passenger aircraft as well as to urban traffic and maritime environments, including emerging underwater flying vehicles. However, existing detection methods often fail under challenging conditions such as low illumination or cluttered backgrounds. Their progress is further constrained by the lack of large-scale benchmarks and the high computational and memory costs required to achieve high accuracy, which limits their deployment in resource-constrained scenarios, such as air-to-air collision avoidance in aerial vehicles. To address this gap, we introduce FT55k, an open-source benchmark comprising over 55,000 annotated RGB and infrared images across diverse environments. We further provide baseline approaches tailored for platforms with different computational demands. Extensive experiments on FT55k and three public datasets demonstrate the superior accuracy and efficiency of our methods compared with state-of-the-art approaches. Notably, our approach is the first flying vehicle detection method with a computational cost below 0.5 BFLOPs, achieving real-time performance at 62.3 FPS on an edge-computing device. This work presents the first comprehensive benchmark for flying vehicle detection in complex environments, establishing a practical and scalable foundation for future research and deployment in intelligent transportation safety. Our datasets is publicly accessible athttps://github.com/chriszxk/Flying-Vehicle-Detection

This paper proposes SANet, a small but accurate detector for aerial flying objects. The detector introduces an attention module into the feature extraction module (FEM) for enhancing the accuracy. This FEM with fewer convolutional kernel channels can reduce the parameters, speed up the inference time, and mitigate the computational burden. Furthermore, we optimize the Spatial Pyramid Pooling (SPP) module to enhance both the accuracy and speed. By analyzing the structure characteristic of the ResNet and RepVGG network that are usually utilized to extract features, a feature fusion module named RepNeck is designed to comprehensively fuse features extracted by the FEM, further enhancing the speed and accuracy. Eventually, we develop a neural network with an impressively small model size of only 4.5M. This network can achieve the state-of-the-art performance on three challenging datasets. Apart from its superior performance, our approach enjoys a real-time detection speed of 14.8 frames per second (fps) and power consumption of only 2.9W while the CPU and GPU temperatures are maintained below 50◦C even on an edge-computing device, highlighting the practicality of our approach for long-duration flying object detection and monitoring tasks.

The misuse of drones can jeopardize public safety and privacy. The detection and catching of intruding drones are crucial and urgent issues to be investigated. This work proposes VDTNet, an accurate, lightweight, and fast network for visually detecting and tracking intruding drones. We first incorporate an SPP module into the first head of YOLOv4 to enhance detection accuracy. Model compression is utilized to shrink the model size and concurrently speed up inference. We then propose and insert an SPPS module and a ResNeck module into the neck, and introduce an effective attention module for the backbone to compensate for the accuracy drop brought on by compression. With the above strategies, we present the accurate and compact VDTNet with a model size of merely 3.9 MB, ensuring low computational cost and fast detection and tracking performance in real time. Extensive experiments on four challenging public datasets show that our proposed network outperforms state-of-the-art approaches. In real-world scenarios, the comparative ground-to-air detection testing proves the generalization ability of the VDTNet, and we further demonstrate the portability and practicability of the network by deploying it on drone onboard edge-computing devices for air-to-air real-time detection of the intruding drones.

Beyond programming robots to accomplish a single high-level task at a time, people also hope robots follow instructions and complete a series of tasks while meeting their requirements. This paper presents an interactive software system that consists of a multiple-task linear temporal logic (LTL) path planner and a human-machine interface (HMI). The HMI transforms human oral instructions into task commands that can be understood by the machine. The planner grows a rapid random exploring tree to search for solutions for multiple tasks. When switching tasks, the search tree is re-initialized and reconnected to utilize the information gathered during the exploration of the workspace. The feasibility of the improved planner is theoretically guaranteed, and profiling in simulation shows an acceleration in planning. An experiment with a quadcopter is conducted to show that the combination of the multiple-task LTL planner and the HMI results in a synergistic effect in real-world applications.

In this paper, we present LCM-MVSNet, a novel multi-view stereo (MVS) network with learnable cost metric (LCM) for more accurate and complete depth estimation and dense point cloud reconstruction. To adapt to the scene variation and improve the reconstruction quality in non-Lambertian low-textured scenes, we propose LCM to adaptively aggregate multi-view matching similarity into the 3D cost volume by leveraging sparse points hints. The proposed LCM benefits the MVS approaches in four folds, including depth estimation enhancement, reconstruction quality improvement, memory footprint reduction, and computational burden alleviation, allowing the depth inference for high-resolution images to achieve more accurate and complete reconstruction. Moreover, we improve the depth estimation by enhancing the propagation of shallow features via a bottom-up path and strengthen the end-to-end supervision by adapting the focal loss to reduce ambiguity caused by sample imbalance. Extensive experiments on two benchmark datasets show that our network achieves state-of-the-art performance on the DTU dataset and exhibits strong generalization ability with a competitive performance on the Tanks and Temples benchmark. Furthermore, we deploy our LCM-MVSNet into the real-world application for large-scale 3D reconstruction based on multi-view aerial images collected by self-developed UAV, demonstrating the robustness and scalability of our method. More detailed results are available in the Appendix11shorturl.at/rBG28

We propose a lightweight, effective, and efficient anti-drone network, namely ADMNet, for visually detecting and monitoring unfriendly drones with a constrained view field, flying against a complex environment. We merge an SPP module to the first head of YOLOv4 to improve accuracy and perform network compression to reduce inference latency and model size. To compensate for the accuracy loss caused by condensation, we propose an SPPS module and a ResNeck module for the neck of the network and implement an effective attention module for the backbone. Eventually, we present an accurate and compact ADMNet with barely 3.9 MB, ensuring low computational cost and real-time detection. Our method achieves state-of-the-art performance on three challenging real-world datasets (Average Precision @0.5IoU): Det-Fly 96.2%, NPS-Drones 92.0%, and TIBNet 89.7%. The throughput is higher than the prior work, in addition to its superior performance. The comparative testing in real-world scenarios proves that our method exhibits strong reliability and generalization ability. Deploying the network on drone onboard edge-computing devices enables real-time detection and monitoring of flying drones, highlighting the portability and viability of the ADMNet.