CloudSatNet-1: FPGA-Based Hardware-Accelerated Quantized CNN for Satellite On-Board Cloud Coverage Classification

Abstract

CubeSats, the nanosatellites and microsatellites with a wet mass up to 60 kg, accompanied by the cost decrease of accessing the space, amplified the rapid development of the Earth Observation industry. Acquired image data serve as an essential source of information in various disciplines like environmental protection, geosciences, or the military. As the quantity of remote sensing data grows, the bandwidth resources for the data transmission (downlink) are exhausted. Therefore, new techniques that reduce the downlink utilization of the satellites must be investigated and developed. For that reason, we are presenting CloudSatNet-1: an FPGA-based hardware-accelerated quantized convolutional neural network (CNN) for satellite on-board cloud coverage classification. We aim to explore the effects of the quantization process on the proposed CNN architecture. Additionally, the performance of cloud coverage classification by biomes diversity is investigated, and the hardware architecture design space is explored to identify the optimal FPGA resource utilization. Results of this study showed that the weights and activations quantization adds a minor effect on the model performance. Nevertheless, the memory footprint reduction allows the model deployment on low-cost FPGA Xilinx Zynq-7020. Using the RGB bands only, up to 90% of accuracy was achieved, and when omitting the tiles with snow and ice, the performance increased up to 94.4% of accuracy with a low false-positive rate of 2.23% for the 4-bit width model. With the maximum parallelization settings, the hardware accelerator achieved 15 FPS with 2.5 W of average power consumption (0.2 W increase over the idle state).

A Lightweight Detection Method for Remote Sensing Images and Its Energy-Efficient Accelerator on Edge Devices

“…Thanks to the development of deep learning and computer vision over the past few years, numerous high-precision object detection models based on convolutional neural networks (CNNs) have been proposed for remote sensing image processing, which has notably improved the efficiency of feature extraction from remote sensing images, and object detection from remote sensing images based on deep learning has also developed rapidly. It has been extensively employed in ship detection [ 1 , 2 , 3 ], meteorological environment detection [ 4 , 5 ], husbandry monitoring [ 6 , 7 ], road extraction [ 8 , 9 , 10 ], and other fields.…”