Choosing the Best Embedded Processing Platform for On-Board UAV Image Processing

Hulens, Dries; Verbeke, Jon; Goedemé, Toon

doi:10.1007/978-3-319-29971-6_24

Cited by 14 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of embedded systems for sUAS image processing algorithms is presented in Hulens et al 106 Herein, we update this work to include current stateof-the-art hardware platforms. We compare these on the basis of the processor type, memory, power consumption, weight, as well as size and present the results in Table 3.…”

Section: Computational Platforms For Saa Systemmentioning

confidence: 99%

Sense and avoid for small unmanned aircraft systems: Research on methods and best practices

Skowron

Chmielowiec

Glowacka

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

In this study, we discuss recent advances and state-of-the-art sense-and-avoid solutions for small unmanned aircraft systems. The purpose of this paper is to equip the reader with the most up-to-date information on research and commercial efforts aimed at introducing autonomous small unmanned aircraft systems into the shared airspace. We present a broad overview of the regulatory environment, current abilities, and limitations of various sensor types as well as algorithmic and computational aspects of establishing a reliable sense-and-avoid platform. This paper reviews a substantial portion of the literature, focusing on developing reliable sense-and-avoid systems. It brings together information from various sources, including commercial drone and sensor manufacturers, regulatory agencies, as well as basic research performed in this regard. While academic and industrial research activities aimed at developing an effective sense-and-avoid system for small unmanned aircraft systems are intensifying, the current technology does not yet allow for a comprehensive solution that would enable autonomous flight. However, recent advances in hardware miniaturization, increases in computational power, and new algorithmic solutions allow us to remain optimistic about future developments.

show abstract

Section: Computational Platforms For Saa Systemmentioning

confidence: 99%

Sense and avoid for small unmanned aircraft systems: Research on methods and best practices

Skowron

Chmielowiec

Glowacka

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

show abstract

“…When it comes to choosing a UAV on-board embedded system for image detection, Hulens et al [10] present a survey of different platforms with their respective computing power and influence on system battery life. The paper mentions the Jetson TK1 (predecessor of our Jetson TX2) and rates its CPU performance below average.…”

Section: Embedded Platformmentioning

confidence: 99%

Embedded Real-Time Object Detection for a UAV Warning System

Tijtgat

Ranst²,

Volckaert

et al. 2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

show abstract

“…Usually torque constant is not given and has to be replaced with a known parameter. This parameter should be motor constant K V (rad/sV) and is related with torque constant with the relation presented in (11). Motor constant is given in the motor specifications.…”

Section: Equationmentioning

confidence: 99%

“…In [10], this problem has been investigated by introducing alternative methods for onboard vision such as FPGAs and ASICs that have shown encouraging results. Another interesting research has been presented in [11]. A framework for choosing the best possible embedded platform for UAS on-board image processing has been introduced by taking into consideration parameters such as algorithm complexity, UAS velocity, power consumption and flight time.…”

Section: Introductionmentioning

confidence: 99%

Towards a holistic performance evaluation framework for drone-based object detection

Petrides

Kyrkou

Kolios

et al. 2017

2017 International Conference on Unmanned Aircraft Systems (ICUAS)

View full text Add to dashboard Cite

Abstract-Recent advances in drone visual sensors and integration of complex vision algorithms, facilitate further potential, entirely disrupting in a positive way their applications and capabilities. In particular, real-time object detection, usually the initial necessary step in multiple computer vision and image processing applications, has been gaining momentum in drone-based applications. Whilst heavily researched in conventional systems, drone-based vision algorithms have to consider extrinsic parameters to measure their efficiency, as their performance is heavily impacted by various flying parameters such as altitude. Further, the parameters that directly impact the performance of the vision algorithms, also impact the duration of the flight (i.e. battery life), as the vision algorithmic performance is affected by the flying route and altitude as well. This paper therefore, presents a holistic performance evaluation framework for multi-rotor drone-based object detection applications, that considers various trade-offs such as flight duration, camera resolution, computational platform performance, drone battery performance, etc., in providing a thorough analysis of the various factors affecting the operation of object detection. The framework showcases indeed that the flying altitude, in combination with the camera resolution, vastly impacts the flight duration as well as the performance of the object detection algorithm, when targeting coverage of a specific area. The framework has been experimentally verified using a commercial grade state-of-the-art drone and high-resolution camera, as well as a high-end embedded processing platform that performs the detection algorithm.

show abstract

Choosing the Best Embedded Processing Platform for On-Board UAV Image Processing

Cited by 14 publications

References 7 publications

Sense and avoid for small unmanned aircraft systems: Research on methods and best practices

Sense and avoid for small unmanned aircraft systems: Research on methods and best practices

Embedded Real-Time Object Detection for a UAV Warning System

Towards a holistic performance evaluation framework for drone-based object detection

Contact Info

Product

Resources

About