Vision intelligence for an autonomous vehicle based on an artificial neural network, a fuzzy logic and a genetic algorithm

Abstract

The purpose of the study was to develop an intelligent vision system for autonomous vehicle field operations. Fuzzy logic was used to classify the crops and weeds. A Genetic Algorithm (GA) was used to optimize and tune the fuzzy logic membership rules. Field study confirmed that the method developed was able to accurately classify crop and weeds through the entire growing period. After segmenting out the weed, an artificial neural network (ANN) was used to estimate the estimates the crop height and width. The r2 for estimation of the crop height showed 0.92 for the training data, and 0.83 for the test data. Finally, a geographic information system (GIS) was used to create a crop growth map.