Autonomous target tracking of UAVs based on low-power neural network hardware

Abstract

Detecting and identifying targets in unmanned aerial vehicle (UAV) images and videos have been challenging problems due to various types of image distortion. Moreover, the significantly high processing overhead of existing image/video processing techniques and the limited computing resources available on UAVs force most of the processing tasks to be performed by the ground control station (GCS) in an off-line manner. In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate novel processing paradigms that can fulfill the real-time processing requirements, while fitting the size, weight, and power (SWaP) constrained environment. In this paper, we present a new autonomous target identification approach on UAVs, leveraging the emerging neuromorphic hardware which is capable of massively parallel pattern recognition processing and demands only a limited level of power consumption. A proof-of-concept prototype was developed based on a micro-UAV platform (Parrot AR Drone) and the CogniMem TM neural network chip, for processing the video data acquired from a UAV camera on the fly. The aim of this study was to demonstrate the feasibility and potential of incorporating emerging neuromorphic hardware into next-generation UAVs and their superior performance and power advantages towards the real-time, autonomous target tracking.

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

“…The CM1K chip was a fully parallel chip with 1024 silicon neurons that used either a RBF or K-nearest neighbor non-linear classifier to learn patterns up to 256 bytes. This chip has been used in several pattern recognition applications such as target tracking in unmanned aerial vehicle videos (Yang et al, 2014) and network intrusion detection (Payer et al, 2014). A neural-inspired architecture called the Golden Gate chip was developed by IBM under the DARPA Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) program (Merolla et al, 2011).…”