Precision agriculture is a management philosophy that meets spatial variability found in agricultural landscapes. Precision agriculture techniques could be used to improve economic and environmental sustainability in crop production and management [1]. Performance evaluation is an important task in the management of agricultural product. The current manual based performance assessment is time-consuming, labor intensive and inaccurate [2]. To address this challenge, we propose a computer vision based system for automated, rapid and accurate assessment of performance. In this paper an overview of previous research and systems to count the number of agricultural products and the yield estimate is conducted and their limitations are discussed. The computer vision techniques are presented to automate the process of counting. A new approach for counting of overlapped agricultural product is described. The paper is concluded with results for counting of gerbera flowers by means of HSV (hue saturation and value) color space and erosion process which reduces the problem of overlapping and giving an accuracy of 89. 86% under polyhouse conditions.

1. Syal, A. Garg, D. , and Sharma, S. 2013. A survey of computer vision methods for counting fruits and yield prediction. International Journal of Computer Science Engineering (IJCSE). 2. 346-350
2. Wang, Q. , Nuske, S. , Bergerman, M. and Singh, S. 2012. Automated crop yield estimation for apple orchards. 13th International Symposium on Experimental Robotics (ISER 2012). 1-15.
3. Sarkate, R. S. , Kalyankar, N. V. and Khanale P. B. 2013. Application of computer vision and color image segmentation for yield prediction precision. IEEE International Conference on Information Systems and Computer Networks (ISCON). 9-13.
4. Kohan, A. , Borghaee, A. M. , Yazdi, M. , Minaei, S. and Sheykhdavudi, M. J. 2011. Robotic harvesting of rosa damascena using stereoscopic machine vision. World Applied Sciences Journal. 231-237.
5. Jimenez, A. R. , Ceres, R. , and Pons, J. L. 2000. A survey of computer vision methods for locating fruit on trees. Transaction of the ASAE. 43. 3-23.
6. Annamalai, P. , Lee, W. S. , and Burks, T. F. 2004. Color vision system for estimating citrus yield in real time. ASAE/CSAE Annual International Meeting, Ottawa, Canada. 1-9.
7. Cointault, F. and Gouton, P. 2007. Texture or color analysis in agronomic images for wheat ear counting. Third International IEEE Conference on Signal-Image Technologies and Internet-Based System. 696-701.
8. Wijethunga, P. , Samarasinghe, S. , Kulasiri, D. and Woodhead, I. 2008. Digital image analysis based automated kiwifruit counting technique. 23 International Conference on Image and Vision Computing New Zealand. 1-6.
9. Harmsen, S. R. and Koenderink, N. J. J. P. 2009. Multi-target Tracking for Flower Counting using Adaptive Motion Models. Computers and Electronics in Agriculture. 65. 7-18.
10. Moonrinta, J. , Chaivivatrakul, S. and Dailey, M. N. 2010. Fruit detection, tracking, and 3D reconstruction for crop mapping and yield estimation. IEEE 11th International Conference on Control Automation Robotics & Vision (ICARCV). 1181-1186.
11. Nuske, S. , Achar, S. , Bates, T. , Narasimhan, S. and Singh, S. 2011. Yield estimation in vineyards by visual grape detection. International Conference on Intelligent Robots and Systems. 2352-2358.
12. Akin, C. , Kirci, M. , Gunes, E. O. and Cakir, Y. 2012. Detection of the Pomegranate Fruits on Tree Using Image Processing. IEEE International Conference on Agro-Geoinformatics (Agro-Geoinformatics).
13. Dey, D. , Mummer, L. and Sukthankar, R. 2012. Classification of Plant Structures from Uncalibrated Image Sequences. Proceedings of IEEE workshop on application of computer vision (WACV). 329-336
14. Patel, H. N. , Jain, R. K. and Joshi M. V. 2012. Automatic segmentation and yield measurement of fruit using shape analysis. International Journal of Computer Applications. 45. 19-24.
15. Linker, R. , Cohen, O. and Naor, A. 2012. Determination of the number of green apples in RGB images recorded in orchards. Computers and Electronics in Agriculture. 81. 45–57.
16. Diago, M. P. , Sanz-Garcia, A. , Millan, B. , Blasco, J. and Tardaguila, J. 2014. Assessment of Flower Number per Inflorescence in Grapevine by Image Analysis under Field Conditions. Journal of the Science of Food and Agriculture. 94. 1981-1987.
17. Dorj, U. O. , Lee, M. and Senthilkumar, S. 2013. A novel technique for Tangerine yield estimation via flower detection. 2nd International Conference on Information Science and Technology. 7. 405-412.
18. Sengupta, S. and Lee, W. S. 2014. Identification and Determination of the Number of Green Citrus Fruit under Different Ambient Light Conditions. Journal of Agricultural Engineering Research. 117. 51-61.
19. Sural, S. , Gang, Q. and Pramanik, S. 2002. Segmentation and histogram generation using the HSV color space for image retrieval. International Conference on Image Processing. 2. II-589-II-592.

Computer Vision Counting Algorithm Yield Prediction