Paper Search Console

Home Search Page About Contact

Journal Title

Title of Journal: Precision Agric

Search In Journal Title:

Abbravation: Precision Agriculture

Search In Journal Abbravation:

Publisher

Springer US

Search In Publisher:

DOI

10.1002/jcb.240230109

Search In DOI:

ISSN

1573-1618

Search In ISSN:
Search In Title Of Papers:

Low and highlevel visual featurebased apple dete

Authors: J P Wachs H I Stern T Burks V Alchanatis
Publish Date: 2010/10/14
Volume: 11, Issue: 6, Pages: 717-735
PDF Link

Abstract

Automated harvesting requires accurate detection and recognition of the fruit within a tree canopy in realtime in uncontrolled environments However occlusion variable illumination variable appearance and texture make this task a complex challenge Our research discusses the development of a machine vision system capable of recognizing occluded green apples within a tree canopy This involves the detection of “green” apples within scenes of “green leaves” shadow patterns branches and other objects found in natural tree canopies The system uses both thermal infrared and color image modalities in order to achieve improved performance Maximization of mutual information is used to find the optimal registration parameters between images from the two modalities We use two approaches for apple detection based on low and highlevel visual features Highlevel features are global attributes captured by image processing operations while lowlevel features are strong responses to primitive partsbased filters such as Haar wavelets These features are then applied separately to color and thermal infrared images to detect apples from the background These two approaches are compared and it is shown that the lowlevel featurebased approach is superior 74 recognition accuracy over the highlevel visual feature approach 5316 recognition accuracy Finally a voting scheme is used to improve the detection results which drops the false alarms with little effect on the recognition rate The resulting classifiers acting independently can partially recognize the ontree apples however when combined the recognition accuracy is increasedThis research was supported by Research Grant No US371505 from BARD The United States—Israel Binational Agricultural Research and Development Fund and by the Paul Ivanier Center for Robotics Research and Production Management BenGurion University of the Negev


Keywords:

References


.
Search In Abstract Of Papers:
Other Papers In This Journal:


Search Result: