Hardware-Based Computational Intelligence for Size, Weight, and Power Constrained Environments

Wysocki, Bryant; McDonald, Nathan; Thiem, Clare; Rose, Garrett S.; Gómez, Mario

doi:10.1007/978-1-4614-7597-2_9

Cited by 1 publication

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiment, we choose λ 0 to be 2 which is good enough to gain high accuracy and fast tracking. Equations (1) and (2) are combined together to provide a high confidence evaluation over pixels in the area we select. With this high confidence, a set of trustable samples are collected for the training process of the neural network classifier.…”

Section: Object-background Separationmentioning

confidence: 99%

“…In order to achieve fast and autonomous target identification on UAVs, it is thus imperative to investigate alternative, novel processing paradigms that can fulfill the real-time processing requirements, while fitting in a size, weight, and power (SWaP) constrained environment. 2 Over the past few decades, neural networks have been successfully used in a wide variety of applications such as computer vision, pattern recognition, remote sensing, and intelligent control, 3 due to their ability to learn the complex nonlinear mapping between inputs and outputs. It has been well demonstrated that neural networks, which emulate the highly parallelized computing nature of the mammalian brain, are capable of solving fuzzy perception and classification problems, especially for a large amount of data with probable complex relationships.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2014

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Object-background Separationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%