STAR.VISION has the help of CVPR 2022 AI satellite in the space age

HANGZHOU, China, June 24, 2022–(BUSINESS WIRE)–STAR.VISION of China won two second prizes in the Multimodal Learning for Earth and Environment (MultiEarth 2022) Challenge at the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2022) on June 19. STAR.VISION won two second prizes in the Multimodal Learning for Earth and Environment (MultiEarth 2022) competition and was the only space company on the list.

CVPR, organized by the Institute of Electrical and Electronics Engineers (IEEE), is the international summit on computer vision and pattern recognition. The world’s greatest AI giants and unicorns, such as Ali, Shang Tang, and Megvii, have proven their prowess on CYPRUS. The computer vision event was held in New Orleans, USA.

Organized by MIT’s Lincoln Laboratory, the Earth and Environment Multimodal Challenge focuses on biodiversity change, habitat loss and climate change due to the decline of the Amazon rainforest. STAR.VISION came in second in two subtasks of the CVPR 2022 Earth and Environment Multimodal Challenge – Matrix Complementation and Multimodal Image Translation. Researchers struggle to access rainforest areas. Satellite remote sensing can be a powerful tool for tracking changes in the Amazon. However, seasonal weather, clouds, smoke and the inherent limitations of optical sensors present obstacles to obtaining continuous time series images. These two missions offer a new perspective on long-term tracking of changes in rainforests, bridging the gap where optical satellites are heavily affected by cloudy weather.

CVPR 2022’s Agriculture Vision Challenge aims to research and develop innovative and effective crop classification and identification algorithms using remote sensing images. This case uses a satellite-based global dataset of crop types provided by the University of Maryland and NASA Harvest. STAR.VISION’s groundbreaking Time-Gated Convolutional Neural Network (TGCNN) algorithm has efficiently and accurately achieved the classification of time series for Earth observation. It was provisionally ranked first in a test set of three countries – Kenya, Brazil and Togo. The algorithm was provisionally ranked first in the test set of three countries – Kenya, Brazil and Togo.

STAR.VISION is a high-tech company integrating AI technology with the aerospace industry. Industry commented on the division’s performance at CVPR 2022 – a remarkable breakthrough by an aerospace company in an advantaged area for software companies

dr. Yashu Kang, head of AI research and development at STAR.VISION, said the company hopes to use space technology to “improve the Earth from space.” “As a hard technology company making satellites, we are entering the top AI competition for the first time, which is full of traditional AI companies and full of outstanding players. As a hard technology company making satellites, our first entry into CVPR, the top AI event with many traditional AI companies and a strong field of participants is like a dark horse, this achievement confirms our direction to combine satellites and AI.”

“Never seen before, just for the view. Change often starts in unexpected places.” said the head of Titan. STAR.VISION’s innovative AI satellite products are changing the current process of satellite data and information acquisition by deploying an industry-leading AI platform directly on-board the satellite to complete the data acquisition, data processing and data analysis directly on-board the satellite.

STAR.VISION is transforming the business logic of the space industry by increasing market scale, reducing satellite costs and increasing application revenue. STAR.VISION allows satellites to be used for multi-purpose, multi-scenario, all-weather use in space awareness, use of space resources, Earth observation, communications and computing platforms. The division has entered the global market in more than 40 countries, with customers in China, the Middle East, North Africa, Southeast Asia and South America.

Check out the source version at


Contact person: Iris
Email: [email protected]
Phone: +86 18906719196
City: Hangzhou
Address: 4th Floor, Building A, Computing Power Town, Hangzhou

Leave a Comment