Opportunistic Drone Detection Using CommSense

无人机 计算机科学 遗传学 生物
作者
Sandip Jana,Amit Kumar Mishra,Mohammed Zafar Ali Khan
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:74: 1-15 被引量:2
标识
DOI:10.1109/tim.2025.3545200
摘要

The rapid proliferation of drones has introduced significant privacy and security challenges, making it essential to develop robust and efficient detection systems. Traditional methods often face tradeoffs in accuracy and environmental robustness. Integrated sensing and communication (ISAC) allows wireless devices to perform both data transmission/reception and sensing using the same hardware. In this article, we introduce the CommSense system, based on the application-specific instrumentation (ASIN) framework, which leverages existing communication signals without needing dedicated transmitters. This makes CommSense a cost-effective, scalable, and regulation-free approach to drone detection. We first evaluated CommSense’s ability to detect environmental changes, achieving 97.7% accuracy in identifying scatterers (static objects). We then moved to a dynamic set-up and tested its performance in detecting a PixHawk drone in diverse environments—an academic building, lawn, parking lot, and playground—achieving good detection accuracies, ranging from 70% to 99.9% with varying distances. Receiver operating characteristic (ROC) curve analysis confirmed excellent performance, with AUC values exceeding 0.9 in most cases. We expanded our experiments by testing two more drones—DJI Mini 4 Pro and bigger PixHawk—at varying distances from 10 to 100 m. The DJI Mini 4 Pro’s accuracy ranged from 99.7% at 10 m to 83.8% at 100 m, while PixHawk’s accuracy ranged from 100% to 81.9%. AUC values also dropped slightly as distance increased, confirming the expected performance variation with range. These results highlight the robustness of CommSense across different environments, drone models, and distances. Its advantages over traditional methods, like audio- and vision-based sensing, demonstrate CommSense’s potential as a practical solution to the growing security threats posed by widespread drone use.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
CodeCraft应助月蚀六花采纳,获得10
刚刚
peng发布了新的文献求助10
1秒前
1秒前
Sea_U应助Ee采纳,获得10
1秒前
小黄瓜776关注了科研通微信公众号
1秒前
王晨昕完成签到,获得积分20
2秒前
羞涩的严青完成签到,获得积分20
2秒前
dunhuang完成签到,获得积分10
3秒前
4秒前
5秒前
5秒前
搞怪班发布了新的文献求助10
5秒前
6秒前
6秒前
6秒前
7秒前
快乐实验人完成签到,获得积分10
7秒前
dxtmm发布了新的文献求助20
7秒前
FashionBoy应助zhanglei05290426采纳,获得10
7秒前
8秒前
淡淡大山完成签到,获得积分10
8秒前
无花果应助你好呀采纳,获得10
8秒前
wind2631完成签到,获得积分10
9秒前
达到顶峰发布了新的文献求助10
9秒前
孤星发布了新的文献求助10
9秒前
lin发布了新的文献求助10
9秒前
yu发布了新的文献求助30
9秒前
简单复天应助niche9964采纳,获得200
10秒前
娜na完成签到,获得积分10
10秒前
10秒前
10秒前
木子发布了新的文献求助10
10秒前
10秒前
10秒前
11秒前
陶醉亦巧发布了新的文献求助30
11秒前
迷人迎南完成签到 ,获得积分10
11秒前
mnbvcxz完成签到,获得积分10
12秒前
jiayoujijin完成签到 ,获得积分10
12秒前
12秒前
高分求助中
Markov Chain Monte Carlo 10000
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Common Foundations of American and East Asian Modernisation: From Alexander Hamilton to Junichero Koizumi 5000
Pediatric Dermoscopy Trichoscopy & Onychoscopy 1000
悉尼大学博士学位论文,题目:Modelling and testing of one-sided stitched laminated composites. 作者:Kristopher P. Plain 700
Matrix Methods in Data Mining and Pattern Recognition Second Edition 610
Clinical effects of budesonide oxygen driving atomization on patients with chronic obstructive pulmonary disease at acute exacerbation phase 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7568301
求助须知:如何正确求助?哪些是违规求助? 9148127
关于积分的说明 19563697
捐赠科研通 7154174
什么是DOI,文献DOI怎么找? 3263004
关于科研通互助平台的介绍 2429055
邀请新用户注册赠送积分活动 2253123