Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

Sorghum (Sorghum bicolor (L.) Moench) has been cultivated for cereal grain which has been traditionally used for steaming with rice in Korea. Various Korean sorghum varieties have been developed and distributed for farmers and consumers to meet their needs. Korean sorghum grains have been mostly sold at higher price in the market than sorghum grains imported from abroad. However, no varietal identification method was established to support fair trade in the cereal market. The objective of this study is to develop the identification method of Korean sorghum varieties using a multiplexed fingerprinting platform of SSR markers. One marker for the waxy allele and nine SSR markers were carefully selected based on their product sizes for the multiplexing. A robust multiplexed combination was revealed from serially designed experiments for the optimization of multiplex PCR. Five varieties and two elite breeding lines could be separated with their unique fingerprinting pattern from other sorghum individuals collected over the world. The platform separated most of individuals tested in this study, remaining three genotypes contained two or three identical individuals. The technique may be applied to detect closely-related individuals including full sibling progeny