נגישות
menu      
חיפוש מתקדם
תחביר
חפש...
הספר "אוצר וולקני"
אודות
תנאי שימוש
ניהול
קהילה:
אסיף מאגר המחקר החקלאי
פותח על ידי קלירמאש פתרונות בע"מ -
A robotic sonar system for yield assessment
Year:
2015
Source of publication :
Authors :
בכר, אביטל
;
.
Volume :
Co-Authors:

Roee Finkelshtain,  Gabor Kosa, School of Mechanical Engineering, Tel Aviv University, Israel

Yossi Yovel, Faculty of Life Sciences, Tel Aviv University, Israel

Facilitators :
From page:
0
To page:
0
(
Total pages:
1
)
Abstract:

Yield assessment is an important tool in agriculture for planning crop revenues, budget, packinghouses and warehouses store capacity and compensation calculations. In several crops, fruit thinning is done based of the yield estimation. However, the present techniques for yield assessment are labor intensive and hence tend to be expensive. Moreover, the process is inaccurate as it is carried out manually by workers and is based on crops sampling in small quantities. There is an obvious tradeoff between the amount of time invested in sampling the crops and the accuracy given the inhomogeneous nature of crops distribution. (Moonrinta, Chaivivatrakul et al. 2010) developed a vision based pineapple mapping algorithm with a detection success rate of80%. Another vision based yield estimation work was presented by (Nuske, Achar et al. 2011) who managed to detect 50 − 70% of the visible berries and predict the amount of crop mass with an error of 9%. Sonar sensing is a remote sensing technology that acquires information by transmitting high frequency sounds at objects, recording and analyzing the echo returns from them. As the time it takes to sound waves to propagate is proportional to distance - sonar sensors are popular as proximity sensors. Another use for sonar sensors is for target classification (Akbarally and Kleeman 1995) used sonar sensing for indoor geometrical based classification and localization of walls, edges by analyzing the time of flight from two receivers. (Lim, Kwon et al. 2012) improved this method by adding more receivers and developing a statistical measure for classification.

Note:
Related Files :
Agricultural engineering
agricultural machinery and equipment
Robotics
robots
Sonar
עוד תגיות
תוכן קשור
More details
DOI :
Article number:
0
Affiliations:
Database:
גוגל סקולר
Publication Type:
מאמר
;
.
Language:
אנגלית
Editors' remarks:
ID:
37260
Last updated date:
02/03/2022 17:27
Creation date:
16/09/2018 10:16
You may also be interested in
Scientific Publication
A robotic sonar system for yield assessment

Roee Finkelshtain,  Gabor Kosa, School of Mechanical Engineering, Tel Aviv University, Israel

Yossi Yovel, Faculty of Life Sciences, Tel Aviv University, Israel

Yield assessment is an important tool in agriculture for planning crop revenues, budget, packinghouses and warehouses store capacity and compensation calculations. In several crops, fruit thinning is done based of the yield estimation. However, the present techniques for yield assessment are labor intensive and hence tend to be expensive. Moreover, the process is inaccurate as it is carried out manually by workers and is based on crops sampling in small quantities. There is an obvious tradeoff between the amount of time invested in sampling the crops and the accuracy given the inhomogeneous nature of crops distribution. (Moonrinta, Chaivivatrakul et al. 2010) developed a vision based pineapple mapping algorithm with a detection success rate of80%. Another vision based yield estimation work was presented by (Nuske, Achar et al. 2011) who managed to detect 50 − 70% of the visible berries and predict the amount of crop mass with an error of 9%. Sonar sensing is a remote sensing technology that acquires information by transmitting high frequency sounds at objects, recording and analyzing the echo returns from them. As the time it takes to sound waves to propagate is proportional to distance - sonar sensors are popular as proximity sensors. Another use for sonar sensors is for target classification (Akbarally and Kleeman 1995) used sonar sensing for indoor geometrical based classification and localization of walls, edges by analyzing the time of flight from two receivers. (Lim, Kwon et al. 2012) improved this method by adding more receivers and developing a statistical measure for classification.

Scientific Publication
You may also be interested in