Vision-based UAV detection and tracking using motion signatures

Prates, Pedro Alexandre; Mendonca, Ricardo; Lourenço, André; Marques, Francisco; Matos-Carvalho, J. P.; Barata, José

doi:10.1109/icphys.2018.8390752

Cited by 13 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The vision-based UAV detection based on video cameras [10], [11], [12], [20] has the same weakness as radar based techniques, as it also requires line-of-sight between the camera and UAV.…”

Section: Related Work a Uav Detection Mechanismsmentioning

confidence: 99%

“…3) MLE performance metric: We use mean squared error (MSE) metric to measure the performance of the parameters estimated by MLE. Considering an incoming traffic flowx(t k ) and letting τ i+1 for i = k, ..., n be the true packet inter-arrival time ofx(t k ), we have M SE p = 1 n − p n i=p (τ i+1 −τ i+1 ) 2 for p = k, ..., n (11) where M SE p denotes the mean square estimation error of packet inter-arrival time ofx(t k ) when pth packet arrives. 4) Estimated expected total cost function J: According to (1), the total cost function J is defined based on C 1 and C 2 which can be computed using (5) and (10), respectively.…”

Section: Algorithm 2 Delay-aware Uav Identificationmentioning

confidence: 99%

“…Then, we follow the step 2 in Algorithm 2 to estimate the packet inter-arrival time of each flow. Using (11), we evaluate the MLE-based estimation performance. Figure 8(c) shows the mean MSE between the true and estimated packet inter-arrival time with shaded area of one standard deviation.…”

Section: Mle Performance Evaluationmentioning

confidence: 99%

“…Although many traditional physical detection mechanisms, such as radar [6], [7], acoustic [8], [9], and vision [10], [11], [12], have been proposed for UAV detection, they cannot always work in practical scenarios, especially in a crowded urban environment. The identification accuracy of radar may be influenced by other small flying objects, such as birds.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification Over Encrypted Wi-Fi Traffic

Alipour-Fanid

Dabaghchian

Wang

et al. 2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

The consumer UAV (unmanned aerial vehicle) market has grown significantly over the past few years. Despite its huge potential in spurring economic growth by supporting various applications, the increase of consumer UAVs poses potential risks to public security and personal privacy. To minimize the risks, efficiently detecting and identifying invading UAVs is in urgent need for both invasion detection and forensics purposes. Given the fact that consumer UAVs are usually used in a civilian environment, existing physical detection methods (such as radar, vision, and sound) may become ineffective in many scenarios.Aiming to complement the existing physical detection mechanisms, we propose a machine learning-based framework for fast UAV identification over encrypted Wi-Fi traffic. It is motivated by the observation that many consumer UAVs use Wi-Fi links for control and video streaming. The proposed framework extracts features derived only from packet size and inter-arrival time of encrypted Wi-Fi traffic, and can efficiently detect UAVs and identify their operation modes. In order to reduce the online identification time, our framework adopts a re-weighted 1norm regularization, which considers the number of samples and computation cost of different features. This framework jointly optimizes feature selection and prediction performance in a unified objective function. To tackle the packet inter-arrival time uncertainty when optimizing the trade-off between the detection accuracy and delay, we utilize Maximum Likelihood Estimation (MLE) method to estimate the packet inter-arrival time. We collect a large number of real-world Wi-Fi data traffic of eight types of consumer UAVs and conduct extensive evaluation on the performance of our proposed method. Evaluation results show that our proposed method can detect and identify tested UAVs within 0.15-0.35s with high accuracy of 85.7-95.2%. The operation mode of UAVs can be accurately identified in the range of 88.5-98.2%.

show abstract

“…The vision-based UAV detection based on video cameras [10], [11], [12], [20] has the same weakness as radar based techniques, as it also requires line-of-sight between the camera and UAV.…”

Section: Related Work a Uav Detection Mechanismsmentioning

confidence: 99%

Section: Algorithm 2 Delay-aware Uav Identificationmentioning

confidence: 99%

Section: Mle Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification Over Encrypted Wi-Fi Traffic

Alipour-Fanid

Dabaghchian

Wang

et al. 2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…As a successful machine learning technology of artificial intelligent, deep learning can be introduced into USV video processing, bringing many interesting and innovative results and applications. For example, face recognition technology is used to locate the face and select the appropriate location to take photos, human recognition is used to track flight, and gesture recognition is used to carry out flight performances [7,8]. Due to the limitation of the computing power of embedded system in USV, the current artificial intelligence video processing methods are usually completed in notebook computers.…”

Section: Innovative Research Experiments Combining Artificial Intellimentioning

confidence: 99%

Innovative Talents Training Practice based on Quadrotor Unmanned Aerial Vehicle Experiments

Sun¹,

Du²,

Sun³

et al. 2019

Proceedings of the 1st International Symposium on Innovation and Education, Law and Social Sciences (IELSS 2019)

View full text Add to dashboard Cite

Experimental teaching is an important part of practical teaching. There are several problems in traditional experiments used to verify classroom knowledge. First, the contents are obsolete and too far away from the actual life of students. Second, the experimental equipment and content cannot meet the multi-level needs of different students. This paper discusses the practical experiment development process employing quadrotor unmanned aerial vehicle (UAV). The developed experiments in this paper not only can solve the problems existing in the current experiment course mentioned above, but also combine the simulation with the actual UAV system to meet the needs of the experiment course and the training of innovative talents. These beneficial successful practices can be used for reference in the construction of other experiments.

show abstract

Terrain Classification Using W-K Filter and 3D Navigation with Static Collision Avoidance

Matos-Carvalho¹,

Pedro²,

Campos

et al. 2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Vision-based UAV detection and tracking using motion signatures

Cited by 13 publications

References 11 publications

Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification Over Encrypted Wi-Fi Traffic

Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification Over Encrypted Wi-Fi Traffic

Innovative Talents Training Practice based on Quadrotor Unmanned Aerial Vehicle Experiments

Terrain Classification Using W-K Filter and 3D Navigation with Static Collision Avoidance

Contact Info

Product

Resources

About