Develop a sound classifier for autonomous tractors in the agriculture
The world population is growing steadily, and now it has reached around 7.9 billion people. To feed such a growing population, a substantial increase of global food production by 70 percent by 2050 is required. As a result, agriculture is facing a challenge, especially in combination with labor shortages and consumers asking for more sustainable food. To take on the food and labor challenges in the agriculture sector, significant interventions in arable farming and greenhouse horticulture are needed. One such innovation is an autonomous tractor and other implements for precision agriculture. These types of tractors can be controlled remotely currently but will be fully automated by using technologies such as vision, obstacle detection, and GPS soon. As RGB vision is depending on the light circumstances, an alternative could be the use of sound to identify anomalies early.
The task for this project is to investigate the current state-of-the-art AI algorithms which are able to classify an activity based on sound. As there has not been a data collection yet, data should be recorded by yourself including a repeatable setup and a thought about annotating the sounds. When the sound is recorded and annotated and the AI algorithms are trained, the performances of the algorithms need to be compared.
20% Theory, 20% data collection and annotation, 40% implementation, 20% writing report
Le Viet Duc, firstname.lastname@example.org