A Pyramid CNN for Dense-Leaves Segmentation

Automatic detection and segmentation of overlapping leaves in dense foliage can be a difficult task, particularly for leaves with strong textures and high occlusions. We present Dense-Leaves, an image dataset with ground truth segmentation labels that can be used to train and quantify algorithms for leaf segmentation in the wild. We also propose a pyramid convolutional neural network with multiscale predictions that detects and discriminates leaf boundaries from interior textures. Using these detected boundaries, closedcontour boundaries around individual leaves are estimated with a watershed-based algorithm. The result is an instance segmenter for dense leaves. Promising segmentation results for leaves in dense foliage are obtained. Keywords-Leaf segmentation; CNN; Dense foliage; Boundary detection;