Segmentation of Fruits and Leaves in Olive Branch Image Using AI Based Approach: Toward Yield Estimation

In this study, we propose an innovative approach to segment images of olive tree branches taken by smartphones to detect olives and leaves. The methodology relies on the self-creation of a labelled database (e.g., olives, leaves, and others) using Grounding-Dino and SAM for detection and segmentation, respectively. We exploit the performance of DINOv2 to compute embeddings for each class. These embeddings are then used to train a Support Vector Machine (SVM) that classifies objects in photos (olives/leaves). Finally, the image is segmented into objects using SAM, and each object is classified by the trained SVM to determine their respective classes. The proposed approach not only ensures the automatic construction of our specific database but also demonstrates high performances that surpass RESNET50.