• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1358-1368
• /
• 2021

A research on agricultural automation is a main issues to overcome the shortage of labor in Korea. A sweet persimmon farmers need much time and labors for classifying profitable sweet persimmon and ill profitable products. In this paper, we propose a mixed two-step synthetic neural network model for efficiently classifying sweet persimmon images. In this model, we suggested a surface direction classification model and a quality screening model which constructed from image data sets. Also we studied Class Activation Mapping(CAM) for visualization to easily inspect the quality of the classified products. The proposed mixed two-step model showed high performance compared to the simple binary classification model and the multi-class classification model, and it was possible to easily identify the weak parts of the classification in a dataset.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.769-782
• /
• 2022

A study on agricultural automation became more important. In Korea, sweet persimmon farmers spend a lot of time and effort on classifying profitable persimmons. In this paper, we propose and implement an efficient grading algorithm for persimmons before shipment. We gathered more than 1,750 images of persimmons, and the images were graded and labeled for classifications purpose. Our main algorithm is based on EfficientDet object detection model but we implemented more exquisite method for better classification performance. In order to improve the precision of classification, we adopted a machine learning algorithm, which was proposed by PyCaret machine learning workflow generation library. Finally we acquired an improved classification model with the accuracy score of 81%.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.22-31
• /
• 2021

This report introduces a definition for robot task intelligence and explains the basis of the challenges associated with implementing robot task intelligence in real-world problems. Two fundamental elements of this intelligence, robot manipulation and navigation, are introduced herein. We describe the existing trends and industrial applications of the robot task intelligence in logistics and agricultural automation. Furthermore, as an underpinning technology for this intelligence, we review the existing three-dimensional position estimation techniques and summarize the difficulties associated with applying pure SLAM technology to real-world applications. Finally, we discuss the prospects of the robot task intelligence research and its potential for solving real-world problems.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.689-698
• /
• 2015

Currently, the itemized box loading operation at the Agriculture Products Processing Center which distributes agricultural products for the region is carried out manually. The process of loading agricultural products requires great manpower and had been resolved through the part-time employment of the residents of farm villages. However, recently it has become quite difficult to secure manpower as the aging within the rural community has been intensified. Hence, the necessity for countermeasures such as facility automation or use of robots have become necessary. This study suggests an automatic robot system for the itemized loading of apple boxes at the Agriculture Products Processing Center. The suggested method is to design and develop equipment such as a conveyer, robot, and bar code reader. In addition, a sorting plan, operational control, generation of control information, and software module that could monitor the inside of the Agriculture Products Processing Center is needed. After test-operating and evaluating the developed system, the existing manual work would be replaced with the automated robot system in order to enhance work efficiency and resolve safety issues.

• Journal of Biosystems Engineering
• /
• v.20 no.1
• /
• pp.73-86
• /
• 1995

The automatic control system in the greenhouse have to be developed to the direction of considering various factors the variables such as condition of the cultivation and greenhouse, the properties and types of products. Therefore, it is more important to set up variables appropriately than the problems of automatic control system itself, and the automatic control system which satisfy these problems should be simplified in the aspect of operation. In addition, even the individual automations are not perfect yet, so more studies are required for the development of comprehensive automatic system in korea. This study was carried out to automatize environment control systems for greenhouse, especially from most intensive labor requiring parts such as watering, irrigating liquefied fertilizer, spraying chemicals, mixing and ventilation system, etc. The results are summarized as follows. 1. Control type tensiometer was expected to be desirable in the automation of watering system, therefore, a new tensiometer was designed and developed through this study. 2. The chemical spraying system developed through this study was found to be excellent in the aspect of operation. 3. When pulse type water discharge meter was used in the mixing of liquefied fertilizer and chemical solution, the error of mixing were range $\pm$0.1~0.15%. 4. The water level switch of electrod type used for controlling water level was found to be affective in both control performance and operation cost. 5. The water and level control system can be omitted if each tank size are standardized in accordance with greenhouse size, therefore, the installation cost might be significantly reduced. 6. The developed general controller was excellent in hardware parts, but still remained to be improved in software parts.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.47 no.2
• /
• pp.79-89
• /
• 2023

This paper is about the development results of an automatic silkworm breeding system to reduce labor and time by automatically performing the works for silkworm droppings changing and feed its food. It consists of an automatic guided vehicle and a processing unit. The automatic guided vehicle transports a silkworm dropping changing frame mounted on a silkworm tray stand, and the processing unit takes over the dropping changing frame on it, removes excrement contained the droppings changing frame and feeds silkworm food. In the case of the current silkworm farming, because the breeding period for large silkworms (4 to 5 stage) is short to 14 days and the supply of mulberry leaves takes 98% of the total amount of mulberry leaves needed for breeding silkworms at this time, labor concentration is intensive, and all breeding works depends on manpower. Therefore, it was difficult to breed large silkworms on a large scale. Moreover, silkworms are bred by adding Silkworm bed (Seop) and mulberry in the silkworm tray, and their droppings changing is to separate silkworms and excrement by moving silkworm trays one by one, and the production cost increases due to the high-cost manpower for silkworm breeding. To solve this problem, technology for automating silkworm breeding has also been developed. However, there is still a limitation that silkworm feeding and droppings changing works are not suitable for mass breeding because a lot of labor and time are spent depending on manual work. Therefore, a new silkworm breeding system for breeding silkworm automatically is needed and so we developed an Automatic Silkworm Breeding System applying the droppings change frame, the inverting unit, the feeding silkworm food device and automatic guided vehicle.

• Korean Journal of Agricultural Science
• /
• v.30 no.1
• /
• pp.76-88
• /
• 2003

This study exploits the robot system which is necessary in gene study, bio-technology industry. As well, it can achieve the job of DNA chip manufacturing whose use rate has been increased recently. The robot consists of DNA spotting device for spotting DNA on the silylated slide and well plate, bed for fixing well-plate, washing & drying device of washing and drying the pin part of DNA spotting device, distillation-water vessel, and discharge vessel of wash water. We made the term of sticking DNA to the pin on well plate to be 15 seconds. The spot size of DNA was set to be 0.28 mm on the average by bringing the slide into contact with pin for 1 second. At this rate, if DNA is spotted in the minimum space possible of about 0.32mm, it can stick about 8,100 DNA spots on the well plate. Analyzing the procedure: Movement starts. Pin washes, dries, and smears DNA on the well plate. Spots DNA onto 12 chips takes 2 minutes and 50 seconds.

• Journal of Bio-Environment Control
• /
• v.3 no.1
• /
• pp.42-51
• /
• 1994

Visual features of a mushromm(Lentinus Edodes L.) are critical in sorting and grading as most agricultural products are. Because of its complex and various visual features, grading and sorting of mushrooms have been done manually by the human expert. Though actions involved in human grading look simple, it decision making underneath the simple action comes from the result of the complex neural processing of visual image. Recently, an artificial neural network has drawn a great attention because of its functional capability as a partial substitute of the human brain. Since most agricultural products are not uniquely defined in its physical properties and do not have a well defined job structure, the neuro -net based computer visual information processing is the promising approach toward the automation in the agricultural field. In this paper, first, the neuro - net based classification of simple geometric primitives were done and the generalization property of the network was tested for degraded primitives. And then the neuro-net based grading system was developed for a mushroom. A computer vision system was utilized for extracting and quantifying the qualitative visual features of sampled mushrooms. The extracted visual features of sampled mushrooms and their corresponding grades were used as input/output pairs for training the neural network. The grading performance of the trained network for the mushrooms graded previously by the expert were also presented.

• Journal of Biosystems Engineering
• /
• v.26 no.1
• /
• pp.21-28
• /
• 2001

Major deficiencies of current automation scheme including various robots for bioproduction include the lack of task adaptability and real time processing, low job performance for diverse tasks, and the lack of robustness of take results, high system cost, failure of the credit from the operator, and so on. This paper proposed a scheme that could solve the current limitation of task abilities of conventional computer controlled automatic system. The proposed scheme is the man-machine hybrid automation via tele-operation which can handle various bioproduction processes. And it was classified into two categories. One category was the efficient task sharing between operator and CCM(computer controlled machine). The other was the efficient interface between operator and CCM. To realize the proposed concept, task of the object identification and extraction of 3D coordinate of an object was selected. 3D coordinate information was obtained from camera calibration using camera as a measurement device. Two stereo images were obtained by moving a camera certain distance in horizontal direction normal to focal axis and by acquiring two images at different locations. Transformation matrix for camera calibration was obtained via least square error approach using specified 6 known pairs of data points in 2D image and 3D world space. 3D world coordinate was obtained from two sets of image pixel coordinates of both camera images with calibrated transformation matrix. As an interface system between operator and CCM, a touch pad screen mounted on the monitor and remotely captured imaging system were used. Object indication was done by the operator’s finger touch to the captured image using the touch pad screen. A certain size of local image processing area was specified after the touch was made. And image processing was performed with the specified local area to extract desired features of the object. An MS Windows based interface software was developed using Visual C++6.0. The software was developed with four modules such as remote image acquisiton module, task command module, local image processing module and 3D coordinate extraction module. Proposed scheme shoed the feasibility of real time processing, robust and precise object identification, and adaptability of various job and environments though selected sample tasks.

• Journal of Biosystems Engineering
• /
• v.43 no.1
• /
• pp.72-80
• /
• 2018

Purpose: A modern greenhouse consists of various Information and Communications Technology (ICT) components e.g., sensor nodes, actuator nodes, gateways, controllers, and operating softwarethat communicate with each other. The interoperability between these components is an essential characteristic for any greenhouse control system. A greenhouse control system could not work unless the components communicate via common interfaces. The TTAK.KO-06.0288 is an interface standard consisting of four parts. Notably, TTAK.KO-06.0288-Part3, which describes the interface between a greenhouse operating system (GOS) and a greenhouse control gateway (GCG), is the core standard of TTAK.KO-06.0288. The objectives of this study were to analyze the TTAK.KO-06.0288-Part3 standard, to suggest alternative solutions for identified issues, and to develop a library as a proof of the alternative solutions. Methods: The "data field" was analyzed using a comparative analysis method, since it is a data transmission unit of TTAK.KO-06.0288-Part3. It was compared with other parts of TTAK.KO-06.0288 in terms of definition, format, size, and possible values. Although TTAK.KO-06.0288-Part1 and TTAK.KO-06.0288-Part2 do not use a "data field," they have a similar data structure. That structure was compared with the "data field" of TTAK.KO-06.0288-Part3. Results: Twenty-one issues were identified across four categories: inter-standard issues, intra-standard issues, operational issues, and misprint issues. Since some of the issues can raise interoperability problems, 16 alternative solutions were suggested. In order to prove the alternative solutions, an open-source communication library called libtp3 was developed. The library passed 14 unit tests and was adapted to two research. Conclusions: Although TTAK.KO-06.0288-Part3 is an interface standard for communication between a GOS and a GCG, it might not communicate between different implementations because of the identified issues in the standard. These issues could be solved by the alternative solutions, which could be used to revise TTAK.KO-06.0288. In addition, a relevant organization should develop a program for compatibility testing and should pursue test products for smart greenhouses.