Abstract: Fruit and vegetables suffer different manipulations from the field to the final consumer. These are basically oriented towards the cleaning and selection of the product in homogeneous categories. For this reason, several research projects, aimed at fast, adequate produce sorting and quality control are currently under development around the world. Moreover, it is possible to find manual and semi- automatic commercial system capable of reasonably performing these tasks.However, in many cases, their accuracy is incompatible with current European market demands, which are constantly increasing. IVIA, the Valencian Research Institute of Agriculture, located in Spain, has been involved in several European projects related with machine vision for real-time inspection of various agricultural produces. This paper will focus on the work related with two products that have different requirements: fruit and olives. In the case of fruit, the Institute has developed a vision system capable of providing assessment of the external quality of single fruit to a robot that also receives information from other senors. The system use four different views of each fruit and has been tested on peaches, apples and citrus. Processing time of each image is under 500 ms using a conventional PC. The system provides information about primary and secondary color, blemishes and their extension, and stem presence and position, which allows further automatic orientation of the fruit in the final box using a robotic manipulator. Work carried out in olives was devoted to fast sorting of olives for consumption at table. A prototype has been developed to demonstrate the feasibility of a machine vision system capable of automatically sorting 2500 kg/h olives using low-cost conventional hardware. !12
展开▼
机译：摘要：水果和蔬菜从田间到最终消费者都受到不同的操纵。这些原则上是针对同类产品的清洁和选择。因此，目前正在全球范围内开展一些旨在快速，充分地进行产品分类和质量控制的研究项目。此外，有可能找到能够合理执行这些任务的手动和半自动商业系统。但是，在许多情况下，其准确性与当前不断增长的欧洲市场需求不符。位于西班牙的巴伦西亚农业研究所IVIA参与了多个与机器视觉相关的欧洲项目，以实时检查各种农产品。本文将重点介绍与两种具有不同要求的产品有关的工作：水果和橄榄。就水果而言，研究所开发了一种视觉系统，该系统能够向还从其他传感器接收信息的机器人提供对单个水果外观质量的评估。该系统使用每种水果的四个不同视图，并已在桃子，苹果和柑橘上进行了测试。使用常规PC，每个图像的处理时间在500 ms以下。该系统提供有关原色和副色，瑕疵及其延伸，茎的存在和位置的信息，从而允许使用机械手在最终包装盒中进一步自动定位水果。在橄榄中进行的工作致力于快速分类橄榄以供餐桌食用。已经开发了一个原型，以演示能够使用低成本常规硬件自动分拣2500 kg / h橄榄的机器视觉系统的可行性。 ！12
展开▼
