Assoc Prof Adams Kong together with his student Li Xiaojie (left) and Prof Su Han (right), the collaborator of this project and a professor in Sichuan Normal University at Chengdu Research Base of Giant Panda Breeding.
Giant panda is a highly endangered animal. China government, in particular through Chengdu Research Base of Giant Panda Breeding (“PANDA BASE”), has put very significant effort to protect it. To measure effectiveness of protective schemes and know the population of giant pandas, accurately counting number of giant pandas in wild is an important task. The current approaches for population estimation include capture-recapture, and collection of DNA from hair or feces. These approaches require PANDA BASE researchers to go to the mountains and regions, where giant pandas live. It is very costly and dangerous. Because of these limits, giant pandas in wild can only be counted once per 10 years. If their population reduces significantly in a short period of time, it would be too late for recovering their population. In this collaboration, Chengdu Research Base of Giant Panda Breeding, Sichuan Normal University and NTU form a research team to develop AI techniques to count Giant Panda.