Drone Detection and Classification approaches based on ML algorithms

Drone detection has become an important field of research as drones are increasingly used in commercial and military applications. Drones, on the other hand, can be used for unlawful surveillance, reconnaissance, or even to carry out attacks on people or property. Anti-drone systems can identify and track drones, preventing them from entering regions where they may pose a safety hazard. A typical anti-drone system ensures drone detection, classification, and neutralization. Traditional detection methods, such as radar and acoustic sensors, have issues with detecting small, low-flying drones, necessitating the development of new alternatives. Because of their accuracy and effectiveness in detecting drones in a variety of contexts, machine learning (ML) algorithms have emerged as a promising solution for drone detection and classification. In this work, we find that machine learning-based classification of drones holds promise, supported by numerous successful individual contributions. However, it is worth noting that the majority of research conducted are experimental, making it challenging to directly compare the outcomes reported in different papers. Furthermore, the lack of standardized reference datasets hampers the evaluation and comparison of various solutions proposed in the field.