Real Time Weed Detection using a Boosted Cascade of Simple Features

Abstract

Weed detection is a crucial issue in precision agriculture. In computer vision, variety of techniques are developed to detect, identify and locate weeds in different cultures. In this article, we present a real-time new weed detection method, through an embedded monocular vision. Our approach is based on the use of a cascade of discriminative classifiers formed by the Haar-like features. The quality of the results determines the validity of our approach, and opens the way to new horizons in weed detection.