This paper aims to study the segmentation demands of vineyard images using Convolutional Neural Networks (CNNs). To this end, eleven CNN models able to provide semantic segmented images are examined as part of the sens-ing subsystem of an autonomous agricultural robot. The task is challenging due to the similar color between grapes, leaves and image’s background. Moreover, the lack of controlled lighting conditions results in varying color representation of grapes and leaves. The studied CNN model architectures combine three different feature learning sub-networks, with five meta-architectures for segmentation purposes. Investigation on three different da-tasets consisting of vineyard images of grape clusters and leaves, provided segmentation results, by mean pixel intersection over union (IU) perfor-mance index, of up to 87.89% for grape clusters and 83.45% for leaves, for the case of ResNet50_FRRN and MobileNetV2_PSPNet model, respectively. Comparative results reveal the efficacy of CNNs to separate grape clusters and leaves from image’s background. Thus, the proposed models can be used for in-field applications for real-time localization of grapes and leaves, towards automation of harvest, green harvest and defoliation agricultural ac-tivities by an autonomous robot. |
*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.