Prototype of a Computer Vision-Based CubeSat Detection System for Laser Communications

Medina, I.; Hernández-Gómez, J. J.; Miguel, Christopher René Torres-San; Santiago, Luis; Couder-Castañeda, Carlos

doi:10.1007/s42405-020-00320-4

Cited by 7 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to the HERCULES OBC, some CubeSat projects used Raspberry Pi boards, such as in [7] to locate an optical ground station beacon. In this case, the OBC was a Raspberry Pi 3B developed without specific development and validation processes for critical systems.…”

Section: Comparison To Related Researchmentioning

confidence: 99%

Design and implementation of a real-time onboard system for a stratospheric balloon mission using commercial off-the-self components and a model-based approach

Pérez-Muñoz,

Gamazo-Real,

González-Bárcena

et al. 2023

Computers and Electrical Engineering

View full text Add to dashboard Cite

Section: Comparison To Related Researchmentioning

confidence: 99%

Design and implementation of a real-time onboard system for a stratospheric balloon mission using commercial off-the-self components and a model-based approach

Pérez-Muñoz,

Gamazo-Real,

González-Bárcena

et al. 2023

Computers and Electrical Engineering

View full text Add to dashboard Cite

“…Once the image is segmented by colours, a Canny filter is applied to detect all the existing edges of the scene. Then, the image is cleaned through the lock method, using the morphological operations of dilation and erosion to eliminate spurious pixels [13]. Finally, the detected area is assessed to determine if it corresponds to the expected size and (circular) geometry of the beacon signal emitted by the OGS.…”

Section: Artificial Vision System Proposalmentioning

confidence: 99%

“…Although the implementation of a LEO satellite OGS-based link would aid to increase data transmission rates, it does not completely replaces RF communications systems. Actually, the integration of both technologies in nano-satellites is necessary to achieve data downlinks at high speeds [13].…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, due to the divergence of lasers used for FSO, a circular area of 8.5 km is required to establish a communication link via optical [10] (altitude of 350 km [13]), yielding a precision of 0.25° for the alignment of devices, to achieve a 50 Mbps consistent data rate for a LEO-OGS link [9,10]. Artificial vision systems (AVSs) may take an important role in the detection of OGS from in orbit satellites, or viceversa.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial vision algorithm for earth station location from CubeSats in narrow beam optical communications

Medina

Santiago

Hernández-Gómez

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The use of CubeSats promises several advantages within a low economical budget margin for different missions. Nowadays, data transfer through optical channels (lasercom) is considered a potential technology for satellite wireless communications, providing several advantages in terms of data transfer rate with lower energy consumption. However, a main drawback is the location of the Optical Ground Station (OGS). Therefore, an artificial vision algorithm for the processing of images captured by the camera of a CubeSat is proposed in this work, in order to carry out the identification and recognition of an OGS by means of a beacon signal, to aid the Pointing, Acquisition and Tracking (PAT) onboard subsystem for the communication’s stage.

show abstract

“…With the development of aerospace technology, the payloads of satellites are pursuing low power consumption, small mass and small size, which impose power limitations and resources limitations on spaceborne computation devices [20]. In particular, micro-satellites (MicroSats) [21] and nano-satellites (NanoSats) [22] are strictly constrained in terms of cost, power, and resources due to their extremely small sizes and light weights. Arnold et al [23] pointed out that for a CubeSat, which is often used as a small remote sensing satellite, its power budget is only 2 to 8 Watts, and its weight is only a few kilograms.…”

Section: Introductionmentioning

confidence: 99%

Automatic Deployment of Convolutional Neural Networks on FPGA for Spaceborne Remote Sensing Application

Yan

Zhang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

In recent years, convolutional neural network (CNN)-based algorithms have been widely used in remote sensing image processing and show tremendous performance in a variety of application fields. However, large amounts of data and intensive computations make the deployment of CNN-based algorithms a challenging problem, especially for the spaceborne scenario where resources and power consumption are limited. To tackle this problem, this paper proposes an automatic CNN deployment solution on resource-limited field-programmable gate arrays (FPGAs) for spaceborne remote sensing applications. Firstly, a series of hardware-oriented optimization methods are proposed to reduce the complexity of the CNNs. Secondly, a hardware accelerator is designed. In this accelerator, a reconfigurable processing engine array with efficient convolutional computation architecture is used to accelerate CNN-based algorithms. Thirdly, to bridge the optimized CNNs and hardware accelerator, a compilation toolchain is introduced into the deployment solution. Through the automatic conversion from CNN models to hardware instructions, various networks can be deployed on hardware in real-time. Finally, we deployed an improved VGG16 network and an improved YOLOv2 network on Xilinx AC701 to evaluate the effectiveness of the proposed deployment solution. The experiments show that with only 3.407 W power consumption and 94 DSP consumption, our solution achieves 23.06 giga operations per second (GOPS) throughput in the improved VGG16 and 22.17 GOPS throughput in the improved YOLOv2. Compared to the related works, the DSP efficiency of our solution is improved by 1.3–2.7×.

show abstract

Prototype of a Computer Vision-Based CubeSat Detection System for Laser Communications

Cited by 7 publications

References 39 publications

Design and implementation of a real-time onboard system for a stratospheric balloon mission using commercial off-the-self components and a model-based approach

Design and implementation of a real-time onboard system for a stratospheric balloon mission using commercial off-the-self components and a model-based approach

Artificial vision algorithm for earth station location from CubeSats in narrow beam optical communications

Automatic Deployment of Convolutional Neural Networks on FPGA for Spaceborne Remote Sensing Application

Contact Info

Product

Resources

About