AI Powers Next Gen Wildlife Monitoring in Italy

WatchEDGE Project Launches AI-Powered Wildlife Monitoring Experiments

A groundbreaking initiative, the WatchEDGE project, operating under the RESTART program, has officially launched its experimental phase. Nestled within the San Rossore Park in Pisa, Italy, researchers are now closely observing wild boar, fallow deer, and wolves. This crucial stage leverages a powerful combination of artificial intelligence, next-generation sensors, and cutting-edge connectivity solutions to revolutionize wildlife monitoring.

Addressing Rural Challenges Through Technology

The primary aim of WatchEDGE is to equip companies and workers in rural areas, from farmers to national park managers, with sophisticated tools. These tools will help control a range of phenomena, from destructive forest fires to pervasive plant pests. The project is developing a robust technology infrastructure capable of supporting surveillance applications that rely on AI image processing. The goal is to create an efficient and sustainable system with diverse applications in agriculture, forestry, and environmental protection.

The Growing Need for Smart Animal Management

Managing wild animal populations is an increasingly critical need, especially in rural landscapes. These animals often cause damage to agriculture and can spread diseases among livestock. They can also negatively impact the environment; for example, an overabundance of fallow deer can significantly slow down or even prevent the regeneration of the flora they depend on for food.

Integrating Advanced Technologies for Real-Time Insights

The WatchEDGE project focuses on seamlessly integrating processing, storage, and communication capabilities. This creates intelligent networks that can process data in real time as it traverses the network. The first series of tests took place in the Pineta and Torre Riccardi areas of San Rossore Park between March 3 and 5.

For decades, large mammals in this park have been continuously monitored using traditional census methods. The park administration is highly interested in the new tools and methodologies being studied by WatchEDGE, recognizing their potential to facilitate these operations in the future.

Technology in Action: First Field Tests

For these initial tests, WatchEDGE deployed innovative photo traps. These traps are based on prototype smart cameras equipped with artificial intelligence for immediate animal classification and counting, effective both during the day and at night. The animals' speeds and movements were meticulously analyzed using multi-frequency Doppler radar. Furthermore, they were monitored from an aerial perspective using drones equipped with multispectral and thermal cameras. These drones were also utilized to examine the condition of the vegetation below.

Tackling Connectivity in Remote Environments

A 5G Nomad solution was selected for establishing wireless connections in the field between edge computing nodes and smart sensors. Given that private 5G networks require an authorized operator, Wi-Fi alternatives were tested in the interim. During these tests, thousands of videos were collected and analyzed to refine and better train the AI algorithms. In addition, nomadic edge computing prototypes were tested, including one integrated into the 5G Nomad system and another developed by Italtel.

One of the key focuses of WatchEDGE is the testing of SD-WAN technology. This technology enables stable network connections even in remote areas by integrating different types of networks, such as Wi-Fi, 4G, 5G, and satellite. This capability makes it possible to collect and transmit large amounts of data reliably and cost-effectively.

A Collaborative Effort for Innovation

The experimentation phase brings together the varied know-how of partners within the consortium, all under the aegis of the NRRP RESTART program. This program is coordinated by the Politecnico di Milano and includes three other universities (University of Pisa, University of Catania, University of Milano-Bicocca), three companies (Italtel, Nextworks, Sensor ID), and a research center (CNIT RaSS in Pisa). This collaborative effort is conducted in partnership with the Tuscany Region Migliarino, San Rossore, Massaciuccoli Regional Park Authority.

Future Vision: AI Enhancements and Broader Applications

In the coming months, the development of the service orchestration system is expected to be completed. This system will enable distributed training of AI models, utilizing techniques like Federated Learning and Continual Learning, to improve performance without the need to transfer large numbers of images across the network.

The final integration of the system will allow for new experiments to be carried out in San Rossore Park. The ultimate goal of WatchEDGE is to transform cutting-edge research into tangible technological solutions that can also be applied effectively in industrial settings.

Insights from Project Leaders

"WatchEDGE was designed to direct basic research towards high-impact solutions for a specific and important economic sector," says Guido Maier, coordinator and Professor of Telecommunications at the Politecnico di Milano. "All eight partners shared this approach. The three industrial partners were able to identify opportunities in the project to transfer technology to potential new products. The academic partners, meanwhile, are studying advanced engineering solutions that can be integrated and tested in the proposed system. Our collaboration with San Rossore Park is essential both for testing our solutions in the field and for the mutual exchange of ideas and experiences. The first experimental campaign will be followed by other on-site activities until the end of the project and hopefully beyond."

Stefano Giordano, Professor of Telecommunications at the University of Pisa, explained, "The development of artificial intelligence applications for environmental monitoring cannot disregard interaction with the network. However, the network infrastructure consists of a variety of technologies that must increasingly be able to integrate and interact with each other. As part of the WatchEDGE project, the University of Pisa oversaw the interaction between the satellite network, 5G network, edge computing and low-energy peripheral networks for remote camera communication in the field. In the future, the goal of our research is to make these functions—which have now been tested statically—more and more dynamic, striving for what we have called completely fluid artificial intelligence."

Claudia Principe, vice-president of the Migliarino San Rossore Massaciuccoli Regional Park Authority, stated, "Our park is open to science and experiments that lead to greater environmental awareness, and to the development of new techniques to improve coexistence between human activities and nature. This cutting-edge activity joins other ongoing projects relying on NRRP funds that help us to design a better, eco-sustainable future."

Professor Nicola Blefari Melazzi, president of the RESTART Foundation, commented, "Under the RESTART program, the experimentation in the WatchEDGE project is an important example of what we aim to achieve by the end of three years of activity. Turning research into concrete technological solutions, with real impacts for key economic sectors such as agriculture, is what RESTART aims to ensure by putting technology at the service of a safer and more sustainable future."

WatchEDGE (Wide-area Agile and flying neTwork arCHitecture for AI-surveillance processing at the EDGE), an industry-focused project and part of the NRRP "RESTART" program, began in January 2023 and is scheduled to last three years.

Provided by Polytechnic University of Milan