A Real-Time UAV Target Detection Algorithm Based on Edge Computing

Abstract

Small UAV target detection plays an important role in maintaining the security of cities and citizens. UAV targets have the characteristics of low-altitude flights, slow speeds, and miniaturization. Taking these characteristics into account, we present a real-time UAV target detection algorithm called Fast-YOLOv4 based on edge computing. By adopting Fast-YOLOv4 in the edge computing platform NVIDIA Jetson Nano, intelligent analysis can be performed on the video to realize the fast detection of UAV targets. However, the current iteration of the edge-embedded detection algorithm has low accuracy and poor real-time performance. To solve these problems, this paper introduces the lightweight networks MobileNetV3, Multiscale-PANet, and soft-merge to improve YOLOv4, thus obtaining the Fast-YOLOv4 model. The backbone of the model uses depth-wise separable convolution and an inverse residual structure to simplify the network’s structure and to improve its detection speed. The neck of the model adds a scale fusion branch to improve the feature extraction ability and strengthen small-scale target detection. Then, the predicted boxes filtering algorithm uses the soft-merge function to replace the traditionally used NMS (non-maximum suppression). Soft-merge can improve the model’s detection accuracy by fusing the information of predicted boxes. Finally, the experimental results show that the mAP (mean average precision) and FPS (frames per second) of Fast-YOLOv4 reach 90.62% and 54 f/s, respectively, in the workstation. In the NVIDIA Jetson Nano platform, the FPS of Fast-YOLOv4 is 2.5 times that of YOLOv4. This improved model performance meets the requirements for real-time detection and thus has theoretical significance and application value.

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

“…Autonomous flight methods are used in target searches with most UAVs. These include [ 3 , 16 , 17 , 18 , 19 ]. Chuang et al [ 3 ] addressed the problem of autonomous target estimation by using drones.…”

“…Rabah et al [ 18 ] studied a control method for a quadcopter that tracked a moving target. Cheng et al [ 19 ] proposed a method for detecting small UAV targets to maintain security in urban areas. Autonomous flight methods have the advantage of being able to optimize navigation by appropriately adjusting the route according to changes in the navigation environment.…”

Comprehensive Investigation of Unmanned Aerial Vehicles (UAVs): An In-Depth Analysis of Avionics Systems

“…Additionally, it achieves the real-time processing of DL-based object tracking tasks. This is mainly performed with assistance from both CPU as well as GPU integrated within Jetson TX2, showing high efficiency in target tracking based on 4K video streams captured by the UAV at an elevation of 50 m. Another model of NVIDIA Jetson SBCs, Jetson Nano, is found to be capable of embedding an improved version of YOLOv4, the Fast-YOLOv4 [207]. Figure 6 elaborates the conjunction of Jetson Nano with other components of the object detection system.…”

IEC-YOLOX:A Lightweight Object Detection Algorithm for UAV Target Detection

“…This approach was utilized to enhance the accuracy and efficiency of the detection process. Qianqing Cheng et al [24] utilized an enhanced soft-merge algorithm as a replacement for NMS (Non-Maximum Suppression). The soft-merge algorithm incorporates the confidence scores and coordinate information of all prediction boxes to construct a fused prediction box that is closer to the real target box, thereby it mitigates issues related to loss detection and error detection.…”