Comparative analysis of texture descriptors in maize fields with plants, soil and object discrimination

Precision Agriculture aims to apply selective treatments and tasks at localized areas concerning crop fields. Robotized and autonomous tractors, equipped with perception, decision-making and actuation systems, can apply specific treatments as may be required. Correct plant identification through the perception system, including crops and weeds, is an important issue. Additionally, it is well known that, in autonomous vehicles, safety is a major challenge, where unexpected obstacles in the working area must be conveniently addressed in order to guarantee the security and the continuity of the process. The objective of this study was to design a tri-class Support Vector Machine classifier for identifying plants (crops and weeds), soil and objects in maize fields based on unsupervised learning. For this, a strategy for automatic sample selection was designed to obtain elements of the three involved classes for the training process. In this context, the identification of obstacles for safe navigation makes an important contribution. A comparative analysis of different texture descriptors and local patterns was carried out with the aim of determining the best for characterizing the classes under study; results have shown that the Speeded-Up Robust Features descriptor is the most appropriate to discriminate between plants, soil and objects. The development of an object detection algorithm for agricultural images proved the effectiveness of the tri-class classifier with an accuracy of 94.3%.