Apple detection in natural tree canopies from multimodal images

In this work we develop a real time system that rec ognizes occluded green apples within a tree canopy using infra-red and color images in order to achieve automated harvesting. Infra-red provides clues regarding the physical structure and location of the apples based on their temperature (leaves accumulate less heat and radiat e faster than apples), while color images provide evidence of circular shape. Initially the o ptimal registration parameters are obtained using maximization of mutual information. Haar feat ures are then applied separately to color and infra-red images through a process called Boosting, to detect apples from the background. A contribution reported in this work, is the voting s cheme added to the output of the RGB Haar detector which reduces false alarms without affecti ng the recognition rate. The resulting classifiers alone can partially recognize the on-tr ees apples however when combined together the recognition accuracy is increased.