Sparse representation and its applications to airborne platforms

Abstract

This thesis would not be what it is without the guidance, keen inputs and support of my supervisor, Prof Anamitra Makur. He has been ever willing to offer his help with suggestions and will always be someone I look up to for his calm demeanour and patience. I am eternally indebted to my co-supervisor, Dr. Asha Vijayakumar for being extremely supportive, kind and being there always to lift me up when my spirits fell. Conversations with her spanning the entire spectrum from technical discussions to light-hearted chats will always be my cherished memories. I have been fortunate to have been guided by the most patient and encouraging supervisors.I am extremely grateful to the Economic Development Board (EDB), Singapore for sponsoring this Industrial PhD Programme (IPP) and enabling me to work towards this. I am thankful to Airbus for having given me the opportunity to undertake this Industrial PhD Programme (IPP) with NTU. I am thankful to Cyrille, Francois and Julian at Airbus for their support and push to see this thesis through. Special thanks to Roger for having been the kind person that he is and being understanding of the time-sharing I needed to do for the research and the project work. Thanks to Supriti and Archana for the happy times at Airbus. I am thankful to Mukund, Sathiya and Sujit for the most interesting and helpful discussions on Compressed Sensing and more.My eternal pillars of support and strength, Porna, Puppy, Tree and Gee, thank you for always being there for me! Much love and thanks to my other family at Smule, Vimmo and i Nisha for being the stress-buster the last 3 years with their music and love! My dearest family, Appa, Amma, Sivaram, Sarada and the newest entrant, Ahaana -there is never a dull moment with all of you, thanks for all the love and the faith in me! No amount of thanks can suffice for Ravi and my darling daughter, Kavya for giving me the space and time to deal with the stress and the pressure to complete this. Special love to Kavya for having tolerated me these last few years while I was battling with work. Sometimes, all I needed was her smile at the end of the day to cheer me up! poses. Intrusion-detection schemes are of interest in every surveillance system. Mobile flying platforms such as drones are being used effectively as an autonomous surveillance system that can not only detect an intrusion on-board, but also make an informed decision to either track the intruder or transmit the required information to the ground station. Efficient techniques to implement a surveillance system on-board continue to be explored. A CS-based scheme for intrusion detection on-board the AR Parrot Drone is implemented. It is observed that a CS-based system can make efficient use of on-board resources by exploiting the properties of the compressed data space. It is also capable of efficient usage of the available bandwidth by transmitting frames to the ground station only if an intrusion is detected. Performance metrics, namely, encoding time and detection accuracy were evaluated. The detectio...