SafeSpace MFNet: Precise and Efficient MultiFeature Drone Detection Network

dil, mahnoor; khan, misha urooj; Alam, Muhammad Zeshan; Orakzai, Farooq Alam; Kaleem, Zeeshan; Yuen, Chau

doi:10.36227/techrxiv.21624585.v1

Cited by 3 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object detection with computer vision improved the categorization and localization of targets. Such as YOLOv5, Faster-RCNN [4], and CenterNet [15]. The authors of [16] created an artifactual data set of drones and birds by removing the target's background and merging them with other images.…”

Section: Literature Reviewmentioning

confidence: 99%

“…To effectively process the datasets, the CNN include a significant number of parameters, and to minimize them, CNN uses filters [1] [2]. Object detection [3] necessitates many feature maps, each of which has hundreds of channels, making the model bloated and enormous [4]. Therefore, model compression is necessary for rapid deployment on embedding devices with fewer parameters [23].…”

Section: Ghost Auto Anchor Network (Gaanet)mentioning

confidence: 99%

“…In comparison with GAANet, TFNet achieved lower precision, recall, and mAP of around 0.5%, 12.8%, and 13.6%, respectively. The MFNet-M model [4] performed UAV vs. bird detection using visual images. Their proposed MFNet-M model achieved 94% recall with 95.9% mAP on drone images, while GAANet has 98.3% recall with 97.4% mAP on drone IR images which are 4.3% and 1.5% high, respectively.…”

Section: Comparison With State-of-the Artmentioning

confidence: 99%

“…This advancement and its increasingly widespread use have raised serious concerns about the security of public places, as we have seen several instances where drones have caused damage to infrastructure [2] [3]. Therefore, effective detection systems are necessary for protection against malicious activities [4]. Advanced object detection and tracking systems are preferred over traditional object identification methods due to their less accurate target detection and high false alarm rate.…”

Section: Introductionmentioning

confidence: 99%

“…Hoffman et al investigated the radar detection of UAVs based on separating the Doppler signatures of distinct UAVs [8]. Mahnoor et al [4] demonstrated that visual images combined with deep learning algorithms solved the UAV detection problem with good precision. According to Zeeshan et al, [1] an acoustic array, unlike radar detection and optical detection approaches, does not rely on the size of the viewed item for detection but on the rotors' sound, and its prerequisite is a large sound dataset.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection

Khan¹,

Dil²,

Misbah³

et al. 2023

Preprint

View full text Add to dashboard Cite

The emergence of unmanned aerial vehicles (UAVs) raised multiple concerns, given their potential for malicious misuse in unlawful acts Vision-based counter-UAV applications offer a reliable solution compared to acoustic and radio frequency-based solutions because of their high detection accuracy in diverse weather conditions. The existing solutions work well on trained datasets, but their accuracy is relatively low for real-time detection. In this paper, we model deep learning-empowered solutions to improve the multi-class UAV's classification performance using single-shot object detection algorithms YOLOv5 and YOLOv7. The transfer learning is employed for performance improvement and rapid training with improved results. We customized a multi-class dataset containing multi-rotor, fixed-wing, and single-rotor UAVs in challenging weather conditions. Experiments show that the integration of transfer learning has achieved good results, with an overall best average-classification precision of 94\%, an average recall of 93.1\%, a mAP$@$0.5 average of 95.3\%, and an average F1 score of 92.33\%. The dataset and code are available as an open source: https://github.com/ZeeshanKaleem/YOLOV5-Large-vs-YOLOV7.git

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Ghost Auto Anchor Network (Gaanet)mentioning

confidence: 99%

Section: Comparison With State-of-the Artmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection

Khan¹,

Dil²,

Misbah³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

TF-Net: Deep Learning Empowered Tiny Feature Network for Night-Time UAV Detection

Misbah

Khan

Yang

et al. 2023

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Vision-based UAV Detection under Adverse Weather Conditions

Munir,

Siddiqui,

Anwar

et al. 2023

Preprint

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) detection in real-time is an emerging field of study that focuses on computer vision and deep learning algorithms. However, the increasing use of UAVs in numerous applications has generated worries about possible risks and misuse. The purpose of this research is to detect UAVs, under adverse weather conditions (such as rain) and image distortions (such as motion blur and noise). The goal is to examine how these adverse conditions affect UAV detection performance and to provide techniques to increase model robustness. To achieve this, a custom training dataset was constructed by combining multiple existing datasets, supplementing them with complex backgrounds. In addition, a custom testing dataset was generated containing UAV images affected by adverse conditions. On the proposed dataset, the performance of well-known object detection algorithms including YOLOv5, YOLOv8, Faster-RCNN, RetinaNet, and YOLO-NAS was investigated. In comparison to clean images, the results demonstrated a considerable performance decrease under adverse conditions. However, training the models on the augmented dataset containing samples of distorted and weather-affected images significantly enhanced the models’ performance under challenging settings. These findings highlight the importance of taking adverse weather conditions into account during model training and underscore the significance of data enrichment for improving model generalization. The work also accentuates the need for further research into advanced techniques and architectures to ensure reliable UAV detection under extreme weather conditions and image distortions. (Note: This is a pre-print of a paper submitted to IEEE for potential journal publication and final version may vary upon acceptance and publication)

show abstract

SafeSpace MFNet: Precise and Efficient MultiFeature Drone Detection Network

Cited by 3 publications

References 32 publications

TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection

TransLearn-YOLOx: Improved-YOLO with Transfer Learning for Fast and Accurate Multiclass UAV Detection

TF-Net: Deep Learning Empowered Tiny Feature Network for Night-Time UAV Detection

Vision-based UAV Detection under Adverse Weather Conditions

Contact Info

Product

Resources

About