ON-BOARD INTELLIGENT PROCESSING FOR REMOTE SENSING IMAGES BASED ON 20KG MICRO-NANO SATELLITE

Micro-nano satellite has developed rapidly in recent years. It shares the advantages of small size, low power consumption, short development cycle, and the ability to complete complex space missions at a lower cost, which is important for scientific research, national defense and commercial fields. The great capacity of imaging data brings heavy pressure to the satellite-earth data transmission, therefore it is necessary and significant to develop intelligent processing on the satellite to transform remote sensing images into concerned information. In this paper, we introduce an integration technology on micro-nano satellite with high performance of resolution, coverage, intelligence, applicable flexibility and low cost. The designed micro-nano satellite is deployed with a small optical payload. The imaging capability is 5k pixels×5k pixels and the resolution is 1.6m@500km. We apply Commercial Off-The-Shelf (COTS) component equipped with deep learning algorithm to extract the information of target, including position, size, course, etc. We evaluate the proposed method on the ship detection task. The experimental results have indicated a great prospect for on-board intelligent processing on the micro-nano satellite.