A survey of computer vision methods for locating fruit on trees

A review of previous studies to automate the location of fruit on trees usi ng computer vision methods was performed The main features of these approac hes are described. paying special attention to the sensors and accessories utilized for capturing tree images, the image processing strategy used to d etect the fruit, and the results obtained in terms of the correct/false det ection rates and the ability to detect fruit independent of its maturity st age. The majority of these works use CCD cameras to capture the images and use local or shape-based analysis to detect the fruit. Systems using local analysis, like intensity or color pixel classification, allow for rapid det ection and were able to detect fruit at specific maturity stages, i.e., fru it with a color different from the background. However systems based on sha pe analysis were more independent of hue changes, were not limited to detec ting fruit with a color different from the color of the background; however their algorithms were more rime consuming. The best results obtained indic ate that more than 85% of visible fruits are usually detectable, although w ith CCD sensors there were a number of false detections that in most cases were above >5%. The approaches using range images and shape analysis were c apable of detecting fruit of any color did nor generate false alarms, and g ave precise information about the fruit three-dimensional position. In spit e of these promising results, the problem of total fruit occlusion limits t he amount of fruit that can be harvested, ranging from 40 to 100% of total fruit, depending on fruiting and viewing conditions. This fact seriously af fects the feasibility of future harvesting robots relying on images that do not contain a high percentage of visible fruit. Therefore, new techniques to reduce total occlusion should be studied in order to make the process fe asible.