While facial recognition technology continues to facilitate many aspects of human life, it is now also being applied to animals, such as to aid the protection of giant pandas in China. A nature reserve in northwest China’s Gansu Province has built an AI-enabled video monitoring system to better protect wild giant pandas. Installed with some 300 infrared cameras, the monitoring system is helping ensure the health and safety of all 110 wild giant pandas in the reserve.
By equipping the AI-aided system to retain scores of archived photos of giant pandas and other wildlife, we can obtain a 98% success rate for species recognition. The success rate of recognising other wild animals can top 80%.
– Liu Xingming, Head of Administration, Reserve
The system can automatically recognise various wild animals caught in infrared cameras, allowing researchers to collect data on giant pandas and other wildlife while staying indoors. In 2021 alone, this monitoring system captured 2,896 photos of giant pandas and other rare animals and filmed 3,218 seconds of footage, showcasing the nature reserve’s sound ecological environment as well as a gradual rise in giant panda population there.
The monitoring system was put into operations more than two years ago, and it has since captured scores of photos and videos of giant pandas engaged in activities such as eating, resting and fighting for mates. Researchers used the system to not only observe the dynamics and health of the giant panda population but also to learn about changes in the natural and biological surroundings of their habitat.
The system provided scientific data to help us grasp the living conditions of wild giant pandas and formulate conservation strategies. More importantly, it also achieved real-time monitoring of the reserve, so that we can detect the threats to the wildlife as early as possible. The monitoring system has enabled systematic, scientific, and intelligent conservation of wildlife.
Moreover, Chinese entrepreneurs see an opportunity to apply this facial recognition technology agriculture as farms become bigger and more commercialised, and as the rural population ages, limiting the number of people able to do manual work.
For humans, facial recognition works by measuring distances between features like eyebrows and lips. But for cows, the software detects patterns and shapes on the animals’ faces and hides. With 50 photographs from different angles, the software can differentiate each cow.
Farmers load information such as health conditions, insemination dates and pregnancy test results into the system, which syncs up with cameras installed above troughs and milking stations. If everything works, farmers can amass valuable data easily. Signs of illness or unusual behaviour can be detected using artificial intelligence and treated quickly by a human, rather than relying on farmers to inspect the herd for potential problems.
Intelligent farming is beginning to change how the agricultural sector operates, and China’s technological giants are getting in on the action. A big tech company has been developing voice recognition technology for pigs to try to detect if the animals are in pain or trouble, while the online retailer has been working on an AI-powered system to develop feeding plans for individual pigs.
There are obvious constraints — like the technology working properly on a farm, appropriately validating what is being monitored, and data handling — but these challenges are worth tackling if they bring animal welfare benefits.
While farmers in other parts of the world are increasingly turning to technology to offset ageing populations and labour shortages, China is mainly motivated to produce more domestically. China feeds 22% of the world’s population with only 10% of the world’s arable land. That creates an extra incentive for China to improve food standards and production, including through the use of advanced technology, including facial recognition technology.