![]() ![]() Therefore, more attention has been focused on using different image acquisition devices and means to obtain useful images and favorable characteristic evidence to support the determination of fruit. This is due to various factors, especially variable light, and proximal color background. However, challenges still remaining in the implementation of robotic harvesting in regard to fruit recognition. Many studies have been conducted to recognize the fruit of horticultural crops automatically, such as sweet peppers, cucumbers, citrus, mangos, tomatoes, and apples. Īccurate fruit recognition is one of the crucial steps necessary for the commercialization of robotic harvesting. While research has been conducted on the production of harvesting robots, the commercialization of robotic harvesting has been hindered by technical and economic factors. The main advantages of robotic picking are its ability to facilitate selective harvesting and its potential to reduce the dependence on the labor force. Robotic picking is one of the promising approaches to automate fruit harvesting. The industry needs technological innovations, which can assist growers in maintaining a competitive position in the global marketplace. Harvesting, in particular, is threatened mostly by the uncertain availability of labor. This intense seasonal labor demand is creating a significant risk for growers not having a sufficient supply of labor to conduct farm tasks. Currently, hand picking is the only commercial harvesting method for fresh market apples, which is labor intensive and costly, accounting for more than 30% of production costs. The results indicated that the developed algorithm based on MSX imaging was effective for fruit recognition and could be suggested as a potential method for the automation of orchard production.Īpples are the second most valuable fruit grown in the United States after oranges. The average processing time for each image was less than 1 s. Recognition precision and sensitivity of these complete fruit regions were both above 92%, and those of incomplete fruit regions were not lower than 72%. The algorithm was applied to 506 training and 340 evaluating images, including a variety of fruit and complex backgrounds. An effective algorithm was developed for locking potential fruit regions, which was based on the pseudo-color and texture information from MSX images. In view of its imaging mechanism, the optimal timing and shooting angle for image acquisition were pre-analyzed to obtain the maximum contrast between fruit and background. In this study, images with fruit were acquired with a Forward Looking Infrared (FLIR) camera based on the Multi-Spectral Dynamic Imaging (MSX) technology. ![]() However, challenges still occur in the implementation of this goal due to various factors, especially variable light and proximal color background. Many researchers have investigated a variety of image analysis methods based on different imaging technologies for fruit recognition. The ability to accurately recognize fruit on trees is a critical step in robotic harvesting.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |