HANGZHOU, China (STAR.VISION AEROSPACE GROUP LIMITED PR) — STAR.VISION AEROSPACE GROUP LIMITED, a Chinese space technology innovator, recently won second place in the Multimodal Learning for Earth and Environment (MultiEarth 2022) competition at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022). They also topped the rankings in another “CropHarvest 2022” track which focuses on crop classification, using a test dataset from Kenya, Togo and Brazil.
Hosted by MIT Lincoln Laboratory, the 2022 MultiEarth competition focused on using machine learning to solve global earth and environmental monitoring challenges 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 for tracking changes in the Amazon. organizers said. The workshop aims to bring together a wide audience of researchers from academia, industry and related fields to leverage remote sensing images collected by multiple sensors for positive environmental impact.
The Chinese company won top honors in two strands of the MultiEarth 2022 competition, including “matrix completion” and “multimodal image translation,” offering a new perspective for long-term monitoring of rainforest change and helping to solve the “headaches” frequently encountered in optics. acquisition of satellite images due to dense cloud cover.
The Conference on Computer Vision and Pattern Recognition (CVPR), widely recognized as the world’s best-known AI competition, is a technical event hosted annually by the Institute of Electrical and Electronics Engineers (IEEE). Previous winners of the championships include tech giants Google, Alibaba and top research organizations across the world.
Based in Hangzhou, eastern China, and specializing in the R&D of AI-based remote sensing satellites and business intelligence services, the company is dedicated to integrating AI technology cutting edge to the revolutionizing space industry.
Dr. Yashu Kang, leader of STAR.VISION’s artificial intelligence team, said the company hopes to use space technology to “improve the Earth from space”, adding that “as a space company, it is t is the first time that we have participated in a top-level international competition with many leading AI companies and their respective players. To achieve such a result is encouraging, which reinforces our desire to improve the remote sensing satellite and its service with AI technology.