Computer vision is a rapidly developing and important branch of artificial intelligence (AI). It involves the creation of sensors to replace human eyes and computers to replace human brains for analyzing and understanding images. The most basic feature of machine vision is that it can improve the flexibility and intelligence of production. For some tasks that are not suitable for manual work, with various remote sensing images, robot vision is often used to replace human vision. At the same time, in the process of mass repetitive industrial production, robot vision technology can greatly improve the efficiency and automation of production.
UGA’s team studies various computer vision methods and robotics platforms, including both ground and aerial robots, to facilitate the development of crop, forestry and poultry agriculture. One project involves a lightweight mobile AI platform based on unsupervised deep neural networks for accurate and fast construction of 3D plant root systems and trait extraction that can be used for multiple crop species. Another uses unmanned aerial systems (UAS)-based precision agriculture solutions to monitor crop status through multispectral, thermal, LiDAR and other remote sensing imaging modalities.