Abstract

Determining the types of vegetation present in an image is a core step in many precision agriculture tasks. In this paper, we focus on pixel-based approaches for classification of crops versus weeds, especially for complex cases involving overlapping plants and partial occlusion. We examine the benefits of multi-scale and content-driven morphology-based descriptors called Attribute Profiles. These are compared to state-of-the art keypoint descriptors with a fixed neighbourhood previously used in precision agriculture, namely Histograms of Oriented Gradients and Local Binary Patterns. The proposed classification technique is especially advantageous when coupled with morphology-based segmentation on a max-tree structure, as the same representation can be re-used for feature extraction. The robustness of the approach is demonstrated by an experimental evaluation on two datasets with different crop types. The proposed approach compared favourably to state-of-the-art approaches without an increase in computational complexity, while being able to provide descriptors at a higher resolution.