A review of land observation satellite remote sensing application technology with new generation artificial intelligence

Abstract

With the rapid development of aerospace industry and remote sensing and the strong supporting from governments, various military and civilian commercial satellite systems have been developed. The establishment of a relatively complete satellite remote sensing data acquisition system injects new momentum for promoting the high-quality development of economy and society. At the same time, the rapid development of artificial intelligence has greatly improved the intelligence and precision of data analysis, and has brought new development opportunities for remote sensing big data analysis and application. In the context of Internet era, it is a general trend to combine advanced technologies such as artificial intelligence, big data, Internet of Things, and 5G to promote the development of remote sensing applications in the direction of intelligence, popularization, and industrialization.Based on the current development status and actual needs of intelligent remote sensing technology for land observation satellites, this review first briefly describes the development of earth observation satellite systems, such as Gaofen and Ziyuan. Second, this review classifies and introduces the development status and trends of artificial intelligence technology in the field of remote sensing. Furthermore, the application status of artificial intelligence-driven remote sensing technology in the fields of resource investigation, environmental monitoring, disaster monitoring, smart city, agriculture, forestry and fishery automation analysis are discussed. Finally, by analyzing existing remote sensing technologies, the challenging problems and development trends of AI in remote sensing is concluded. Different from previous reviews, this review has two major contributions. On one hand, it carefully reviewed the development status of existing AI based remote sensing methods. It is found that although AI has been successfully and widely applied in remote sensing, its performance is still not satisfactory and far behind the intelligence of remote sensing experts in many domains. In order to address this problem, the further development of new generation AI and the wider application of AI in remote sensing is the key of success. On the other hand, this work gives five typical and key future research directions of future AI based remote sensing technologies. The first is to study the rapid knowledge mining technology of remote sensing big data, realize the comprehensive perception and intelligent analysis of remote sensing with the support of AI technology. The second is to study the collaborative sensing technology of observation network constructed by multiple remote sensing satellites, so as to achieve more comprehensive, more accurate, and more efficient earth observations. The third is to study cross-modal multi-source remote sensing data fusion and recognition technology. By fusing multi-source remote sensing data of different types, such as visible light, multispectral, infrared, hyperspectral, microwave, etc., the performance of remote sensing image recognition and interpretation is expected to be dramatically improved. The fourth is to study the on-orbit intelligent processing technology of remote sensing data, including on-orbit processing hardware and software systems. The last is to study the human-machine hybrid enhanced intelligent remote sensing technology. In the future, humans and intelligent remote sensing systems are expected to be closely coupled and work together to form a stronger remote sensing intelligent sensing ability.