Spotted wing drosophila (SWD, Drosophila suzukii) has become a serious pest in Europe attacking many soft-skinned crops such as several berry species and grapevine since its spread in 2008 to Spain and Italy. An efficient and accurate monitoring system to identify the presence of SWD in crops and their surroundings is essential for the prevention of damage to economically valuable fruit crops. Existing methods for monitoring SWD are costly, time and labour-intensive, prone to errors, and typically conducted at a low spatial resolution. To overcome current monitoring limitations, we are developing a novel system consisting of photographable traps, which are monitored by means of unmanned aerial vehicles (UAVs) and an image processing pipeline that automatically identifies and counts the number of SWD per trap location. To this end, we are currently testing the approach using high-resolution RGB imagery of SWD traps taken from both a static position (tripod) and from a UAV. These are then used as input to train deep learning models. Preliminary results show that a large part of the SWD can be correctly identified using a ResNet-18-based model. An autonomous UAV platform will be programmed to capture imagery of the traps under field conditions. The collected imagery will be transferred directly to cloud-based storage for subsequent processing and analysis to identify the presence and count of SWD in near real time. This data will be used as input to a decision support system (DSS) to provide valuable information for farmers.
|Number of pages||8|
|Publication status||Published - 1 Jun 2021|
- Deep learning
- Pest monitoring