Publication Type : Conference Paper
Publisher : 2017 Recent Developments in Control, Automation Power Engineering (RDCAPE),
Source : 2017 Recent Developments in Control, Automation Power Engineering (RDCAPE), IEEE, Noida, India (2017)
Url : https://ieeexplore.ieee.org/document/8358297
ISBN : 9781509039784
Keywords : Artificial intelligence, autonomous aerial vehicles, breach detection, Cameras, closed circuit television, CNN, control system security, Convolution, Convolutional neural network, Convolutional neural networks, Deep learning, Deep Neural Network, Drones, feedforward neural nets, Fixed CCTV cameras, Image processing, invading drone, Jamming, Mobile robots, Object Detection, physical security, Signal Jammer system, Signal jamming, surveillance drones, Training, UAV, Unmanned aerial vehicles
Campus : Amritapuri
School : School of Engineering
Center : Cyber Security
Department : CISAI, cyber Security, Electrical and Electronics
Year : 2017
Abstract : Unmanned Aerial Vehicles (UAV) has become ubiquitous. While there are several applications for UAV, it is also considered as a threat to the privacy and physical security. In this work we attempt to detect the invading UAV's with a goal of disabling them when they are invading a physical space. Identification of the UAV is performed by analyzing the live video feeds from cameras that are from Fixed CCTV cameras and surveillance drones. We propose to use image processing using convolutional neural network (CNN) for detecting the presence of the drones. Once the invading drone is identified, the information is sent to the Signal Jammer system. Our prototype shows very promising results that encourages us to pursue in building a real-world system.
Cite this Research Publication : N. Shijith, Poornachandran, P., Sujadevi, V. G., and Meher Madhu Dharmana, “Breach detection and mitigation of UAVs using deep neural network”, in 2017 Recent Developments in Control, Automation Power Engineering (RDCAPE), Noida, India, 2017.