Download PDFOpen PDF in browser

A Machine Learning Based Adaptive Approach to Detect and Identify Drone Activities

EasyChair Preprint no. 9608

4 pagesDate: January 21, 2023


Drones or UAV are the flying object which are having size varying from a few cm to a few meter and payloads starting from a few gram to a few kilogram. The trend of using small drone is to execute different tasks as increased over last few years. At the same time, the threat caused by drone to the society, public security and personal privacy is also becoming increasingly high. From the security point of view, drones allow the attacker to reach any target in any location without risk to personnel and there is an ever-expanding domain of usage ranging from weapon carrier to spying tool. To mitigate and negate the impact of drone, there is a requirement to develop and deploy counter drone systems for detection of incoming drone threats. Before go in details, lets we understand why drone detection is such a challenging task. Considering the unique nature of drone in terms of speed, size, hovering and resemblance to birds no unique system in standalone will be able to provide sufficient detection, tracking and identification capability to guarantee a reliable and effective system against threats from drone. Therefore, a combination of several types of detection capabilities are required to detect and identify drone.

Keyphrases: Anti-drone, Artificial Intelligence, Defence, Drone, machine learning

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Ankush Agarwal and Shikha Verma},
  title = {A Machine Learning Based Adaptive Approach to Detect and Identify Drone Activities},
  howpublished = {EasyChair Preprint no. 9608},

  year = {EasyChair, 2023}}
Download PDFOpen PDF in browser