Farmers and nature conservationists have been reporting every year several cases where fawn and wildlife specimens, e.g., bird nests, deer’s, are found hidden in the tall grass. This situation has become a major problem for farmers when they are conducting agricultural management tasks, such as mowing and harvesting with heavy machinery. When conducting field management on the field many animals die because the farmers cannot see them. Moreover, farmers feel frustrated because it’s not feasible to scan the field beforehand due to the large size of the fields, because this agricultural management tasks are usually constrained to short time windows, and because animals can move.
A potential solution to this problem, is to use a UAV shipped with RGB/thermal cameras to detect the fawn and wildlife specimens in real-time while the famer steers the machines over the field. This real-time sense-and-avoid scheme could be combined with the machines motions and navigation to save wildlife. An interesting challenge is how to design such add-on tool for the machinery and easy to use by famers.
This thesis will be organized as follow:
- Literature review about wildlife protection via UAV imagery
- Design of a sense-and-avoid strategy to be adopted by farmers
- Selection machine vision algorithm for detection/classification/tracking
- Field tests
- Analyse the results
- Jamemo, A. 2002: Roe deer Capreolus capreolus fawns and mowing - mortality rates and countermeasures. - Wildl. Biol. 8: 211-218.
- Cukor, Jan et al. “Use of aerial thermography to reduce mortality of roe deer fawns before harvest.” PeerJ vol. 7 e6923. 10 May. 2019, doi:10.7717/peerj.6923
- Christiansen, P.; Steen, K.A.; Jørgensen, R.N.; Karstoft, H. Automated Detection and Recognition of Wildlife Using Thermal Cameras. Sensors 2014, 14, 13778-13793.
- UAV enthusiast
- Willing to learn cutting edge technology for great causes
- Wildlife lover
Theme(s): Sensing & measuring