Deep learning assisted visual tracking of evader-UAV

Τσουκαλάς, Αθανάσιος; Xing, Daitao; Evangeliou, Nikolaos; Giakoumidis, Nikolaos; Tzes, Anthony

doi:10.1109/icuas51884.2021.9476720

Cited by 11 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Syed Samiul Alam et al proposed RF-supported deep learning-assisted UAV detection and identification [2]. Athanasios Tsoukalas et al proposed tracking evasive drones with deep learning assistance [3]. Sungtae Moon et al proposed realizing real-time monitoring of large areas on drones through image stitching [4].…”

Section: Introductionmentioning

confidence: 99%

UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm

Guo

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

With the progress of science and technology, artificial intelligence is widely used in various disciplines and has produced amazing results. The research of the target detection algorithm has significantly improved the performance and role of unmanned aerial vehicles (UAVs), and plays an irreplaceable role in preventing forest fires, evacuating crowded people, surveying and rescuing explorers. At this stage, the target detection algorithm deployed in UAVs has been applied to production and life, but making the detection accuracy higher and better adaptability is still the motivation for researchers to continue to study. In aerial images, due to the high shooting height, small size, low resolution and few features, it is difficult to be detected by conventional target detection algorithms. In this paper, the UN-YOLOv5s algorithm can solve the difficult problem of small target detection excellently. The more accurate small target detection (MASD) mechanism is used to greatly improve the detection accuracy of small and medium targets, The multi-scale feature fusion (MCF) path is combined to fuse the semantic information and location information of the image to improve the expression ability of the novel model. The new convolution SimAM residual (CSR) module is introduced to make the network more stable and focused. On the VisDrone dataset, the mean average precision (mAP) of UAV necessity you only look once v5s(UN-YOLOv5s) is 8.4% higher than that of the original algorithm. Compared with the same version, YOLOv5l, the mAP is increased by 2.2%, and the Giga Floating-point Operations Per Second (GFLOPs) is reduced by 65.3%. Compared with the same series of YOLOv3, the mAP is increased by 1.8%, and GFLOPs is reduced by 75.8%. Compared with the same series of YOLOv8s, the detection accuracy of the mAP is improved by 1.1%.

show abstract

Section: Introductionmentioning

confidence: 99%

UN-YOLOv5s: A UAV-Based Aerial Photography Detection Algorithm

Guo

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The use of Unmanned Aerial Vehicles (UAVs) towards autonomous task completion has received increased attention in the past decade. Indicative tasks include aerial manipulation in Gassner et al (2017) , Gkountas and Tzes (2021) , Nguyen and Alexis (2021) , Li et al (2021) , surveillance in Bisio et al (2021) , Tsoukalas et al (2021) , as well as Simultaneous Localization and Mapping (SLAM) in Papachristos et al (2019a) , Tsoukalas et al (2020) , Dang et al (2019) or inspection in Papachristos et al (2016) , Steich et al (2016) , Bircher et al (2015) ; these works necessitate the collaborating agents to exchange their relative pose (position and orientation).…”

Section: Introductionmentioning

confidence: 99%

Visual Collaboration Leader-Follower UAV-Formation for Indoor Exploration

et al. 2022

Self Cite

View full text Add to dashboard Cite

UAVs operating in a leader-follower formation demand the knowledge of the relative pose between the collaborating members. This necessitates the RF-communication of this information which increases the communication latency and can easily result in lost data packets. In this work, rather than relying on this autopilot data exchange, a visual scheme using passive markers is presented. Each formation-member carries passive markers in a RhOct configuration. These markers are visually detected and the relative pose of the members is on-board determined, thus eliminating the need for RF-communication. A reference path is then evaluated for each follower that tracks the leader and maintains a constant distance between the formation-members. Experimental studies show a mean position detection error (5 × 5 × 10cm) or less than 0.0031% of the available workspace [0.5 up to 5m, 50.43° × 38.75° Field of View (FoV)]. The efficiency of the suggested scheme against varying delays are examined in these studies, where it is shown that a delay up to 1.25s can be tolerated for the follower to track the leader as long as the latter one remains within its FoV.

show abstract

“…Visual Object Tracking (VOT) has attracted increasing attention in recent years, given its applications in several fields, including path planning [1], visual surveillance [2] and border security [3]. While extensive achievements have been made towards powerful object tracking methods, most of those trackers employ deep networks, complex structures, or online update mechanisms and require GPU acceleration to achieve real-time processing.…”

Section: Introductionmentioning

confidence: 99%