STAR.VISION AEROSPACE GROUP LIMITED, a Chinese space technology innovator, has recently won the second place in the Multimodal Learning for Earth and Environment (MultiEarth 2022) competition during the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022). They also topped the rankings in another track “CropHarvest 2022” which focuses on crop classification, using testing data set from Kenya, Togo and Brazil.
Organized by MIT Lincoln Laboratory, the MultiEarth 2022 competition focused on using machine learning to address global problems in earth and environmental monitoring such as the decline of the Amazon rainforest.
“Deforestation in the Amazon rainforest accounts for the largest share, contributing to reduced biodiversity, habitat loss, and climate change. Since much of the region is difficult to access, satellite remote sensing offers a powerful tool to track changes in the Amazon.” stated the organizers. The workshop aims to gather a wide audience of researchers in academia, industry, and related fields to leverage remote sensing images collected by multiple sensors for positive environmental impact.
The Chinese company won honors in two tracks of the MultiEarth 2022 competition, including the “matrix completion” and “multimodal image translation”, providing a new perspective for long-term monitoring of rainforest changes, and helping resolve frequently encountered “headaches” in optical satellite image acquisition due to dense cloud coverage.
Conference on Computer Vision and Pattern Recognition (CVPR), widely recognized as the world’s best known AI competition, is a technical event hosted by the Institute of Electrical and Electronics Engineers (IEEE) on yearly basis. Previous winners of championships include tech giants of Google, Alibaba and top research organizations across the world.
Headquartered in Hangzhou, Eastern China, and specializing in AI-driven remote sensing satellites R&D and business intelligence services, the company is dedicated to integrating state-of-the-art AI technology with the on-going revolutionized space industry.
Dr. Yashu Kang, head of STAR.VISION’s AI team, said that the company hopes to use space technology to “improve the earth from space”, adding that “as a space company, it is our first time to participate in a top-tier international competition along with many great AI companies and respective players. Achieving such a result is encouraging, which strengthens our determination of improving the remote sensing satellite and its service with AI technology.”