I recently oriented my resarch interest to computer vision to developp a methodology to study animal communities and the role of natural ennemies in the conservational biological control. In collaboration with William Puceh and Régis Graptin (LIRMM), we first adapt the Inception-v3 classifier to the recognition of ants in digital images. Next, using a sliding window method, we use heat map to the detection of the ants.
Figure 1. Detection of Messor barbarus workers using the Inception-v3 classifier and a sliding window algorithm.
I am working on the system detectors YOLO (Redmon et al. 2014) to train detection models on ants, weevils, spiders and seeds. This method allow to know the identity and number of agents that are present on an digital images (Figure 2 & 3). With Paul Tresson, William Puech and Philippe Tixier, we begin to work on the combination of sentinel prey experiments with the develoment of an event detection model to study trophic an non-trophic interactions in agrosystems.
Figure 2. Detection of Cosmopolites sordidus using YOLOv3.
Figure 3. Detection of Messor barbarus using YOLOv3.
Page affichée 46 fois. Dernière visite le 2018-11-15 02:54:11
Dernière modification de cette page le 2018-10-25 19:20:14