Estimation of the Number of Apples in Color Images Recorded in Orchards
This work presents an algorithm for estimating the number of apples on trees using images acquired with a standard color CCD camera. The pro-posed system is capable of correctly identifying and localizing more than 85％ of the apples in the images. To achieve this high detection rate, color and tex-ture analyses are combined together with shape analysis. In the first step, pixels with a high probability of belonging to an apple object are detected according to their color and texture. In the second step, seed areas consisting of con-nected sets of pixels with a high probability of belonging to an apple object are detected. Each seed area is then extended to cover the entire visible area of the apple to which it belongs. Finally, each blob is segmented into simple compo-nents that can either be combined into circles or are discarded, so that each of the resulting circles corresponds to an apple.
artificial vision imagine processing yield estimation
Oded Cohen Raphael Linker Amos Naor
Faculty of Civil and Environmental Engineering, Technion - Israel Institute of Technology,Haifa, 320 Golan Research Institute P. O. Box 97 Katzrin, 12900, Israel
国际会议
南昌
英文
630-642
2010-10-22（万方平台首次上网日期，不代表论文的发表时间）