• Journal of Biosystems Engineering
• /
• v.25 no.2
• /
• pp.141-150
• /
• 2000

This study was carried out to de develop a control strategy of a fruit harvesting redundant robot. The method of generating a safe trajectory, which avoids collisions with obstracles such as branches or immature fruits, in the 3D(3-dimension) space using artificial potential field technique and virtual plane concept was proposed. Also, the method of setting reference velocity vectors to follow the trajectory and to avoid obstacles in the 3D space was proposed. Developed methods were verified with computer simulations and with actual robot tests. Fro the actual robot tests, a machine vision system was used for detecting fruits and obstacles, Results showed that developed control method could reduce the occurrences of the robot manipulator located in the possible collision distance. with 10 virtual obstacles generated randomly in the 3 D space, maximum rates of the occurrences of the robot manipulator located in the possible collision distance, 0.03 m, from the obstacles were 8 % with 5 degree of freedom (DOF), 8 % with 6-DOF, and 4% with 7-DOF, respectively.

• Journal of Biosystems Engineering
• /
• v.25 no.4
• /
• pp.287-292
• /
• 2000

The herbicide penetration on weed leaves was spatially analyzed by using chlorophyll fluorescent emission and machine vision technique. Velvetleaf and metribuzin were used as experimental materials in the study. The herbicide spray images were obtained by a combinaton of a fluorescent dye and a UV lighting system. The herbicide penetration was analyzed by means of detecting chlorophyll fluorescent emission under blue-green lighting. According to the experiment results, the number and the size of spray droplets decreased with coverage increasing. The herbicide penetrated mainly along leaf veins and the time for complete penetration over the whole leaf was approximately 100 minutes after herbicide spraying. When the coverage of herbicide droplets on the surface of leaves increased, the speed of herbicide penetration also increased. This study suggested a way of characerizing herbicide spatial penetration and distribution in leaves.

• Journal of Biosystems Engineering
• /
• v.22 no.3
• /
• pp.317-324
• /
• 1997

This study was conducted to develope a machine vision system for a robotic transplanter for bedding plants. Specific objectives of this study were 1) to get coordinates of the healthy seedlings in high-density plug tray, and 2) to get the angle of the leaves of the healthy seedlings to avoid the damage to seedlings by gripper. Results of this study were summarized as follows. (1) The machine vision system of a robotic transplanter was developed. (2) Success rates of detecting empty cell and bad seedlings for 72-cell and 128-cell plug-trays were 98.8% and 94, 9% respectively. (3) Success rates of calculating the angle of leaves fer 72-cell and 128-cell plug-trays were 93.5% and 91.0% respectively.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.231-234
• /
• 2003

This paper describes the structure, operation, image processing, and decision making techniques of a color machine vision system designed for the automatic sorting of soybeans. The system consists of feeder, conveyor belt, line-scan camera, lights. ejector, and a PC Unlike manufactured goods, agricultural products including soybeans have quite uneven features. The criteria for sorting good and bad beans also vary depending on inspectors. We tackle these problem by letting the system learn the inspecting parameters from good samples selected manually by a machine user before running the system for sorting. Real-time processing has another importance In the design. Four parallel DSPs are employed to increase the processing speed. When the designed system was tested with real soybeans and the result was successful.

• Journal of Biosystems Engineering
• /
• v.25 no.1
• /
• pp.55-62
• /
• 2000

Autonomous farm operation needs to be developed for safety, labor shortage problem, health etc. In this research, an autonomous tractor for tillage was investigated using machine vision and a fuzzy logic controller(FLC). Tractor heading and offset were determined by image processing and a geomagnetic sensor. The FLC took the tractor heading and offset as inputs and generated the steering angle for tractor guidance as output. A color CCD camera was used fro the image processing . The heading and offset were obtained using Hough transform of the G-value color images. 15 fuzzy rules were used for inferencing the tractor steering angle. The tractor was tested in the file and it was proved that the tillage operation could be done autonomously within 20 cm deviation with the machine vision and the FLC.

• Journal of Biosystems Engineering
• /
• v.22 no.2
• /
• pp.217-226
• /
• 1997

This study was to develop a machine vision system to detect and to discriminate 5 kinds of apple surface defectbruise, decay. fleck, worm hole and scar. To detect the defects from an image of apple, thresholding technique was applied to images on various frames (R, G, B, H, S and I) of the color machine vision and an image of near infrared (NIR). To discriminate the detected region of defect, various features of the 5 kind defect regions were extracted from the 4 kinds of images selected above. The features were size of area, roundness, axes length ratio, mean and valiance of pixel values, standard deviation of real part of amplitude spectrum in frequency domain obtained by Fourier transform of pixel data and mean and standard deviation of power spectrum obtained by the same transform of pixel data. Routines to discriminate the defects from the features of image were developed and tested to prove their validity. The test resulted that I-frame and NIR images were the most desirable. Accuracies of the two images to discriminate the defects were noted as 76% and 77%, respectively.

• Korean Journal of Plant Resources
• /
• v.19 no.3
• /
• pp.401-404
• /
• 2006

In order to select the seeding machine for mechanizing cultivation of rapeseed in southern areas of Korea, three different seeding machines, ridge rotary, power tiller ridge rotary, tractor ridge rotary were used for sowing one of the high yielding rapeseed cv. Hybrid with five different seeding methods. Seeding of ridge rotary was reduced the seeding effort with 45% and yield components such as plant height, ear length, number of branches and pods, pod length and seed setting rate were higher. The seeding of ridge rotary also was showed highest seed yield. On the basis of time requirement for seeding, vegetative and yield parameters ridge rotary seeding machine was a suitable seeding machine for rapeseed cultivation at the southern area of Korea.

• 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%.

• Journal of Biosystems Engineering
• /
• v.25 no.6
• /
• pp.503-510
• /
• 2000

To improve the milling condition of brown rice a continuous type conditioning equipment was developed. To validate the performance of this machine the experimental operation was done at Sa-cheon RPC(Rice Processing Complex) using short grain rough. The initial moisture contents of brown rice were 15.0∼16.5%(w.b) and the flow rate of brown rice passing through the conditioner were 4,370kg per hour. The moisture content differences of brown rice between conditioned and non-conditioned were showed within 0.5%(w.b) This results means that the water injected to brown rice were absorbed to the surface of brown rice evenly. The moisture contents of conditioned treated milled rice were showed slightly higher than that of non-conditioned ones but it was considered that the conditioning process did not affected the weight increasing of milled rice by water supply. For initial moisture contents of 15.0∼16.5%(wb) brown rice it was found that the proper water supply rate was 0.115(cc-water)/(kg·%-brown rice) and the increments of whole rice were 2.2% compared to the non-conditioned ones. it was considered that the conditioning process did not influenced the whiteness of milled rice because the whiteness differences between conditioned and non-conditioned milled rice were negligible. About 18% of electric power which drives the abrasive type rice milling machine was saved at 0.115(cc-water)/(kg·%-brown rice) of water supply rate.

• Journal of Biosystems Engineering
• /
• v.32 no.6
• /
• pp.395-402
• /
• 2007

This study was carried out as basic researches to develop the leaf vegetable harvester. This study was conducted to investigate physical and rheological properties of bundled leaf vegetables with stem (Chinese leek, Crown daisy and Chamnamul) as test materials held and picked-up by a machine. Stress-strain behavior, stress relaxation, and strain recovery for the bundled materials were analyzed using simple Maxwell model. Physical and rheological properties of the materials were investigated by measuring rupture load, deformation and stress experimentally. Also, strain recovery time when unloading was measured using super high speed camera. Recorded recovery time for stress-strain behavior was0.026 s for Chinese leek with liner strain recovery, 0.046 s for Crown daisy and 0.05 s for Chamnamul with non-linear strain recovery. Furthermore, the strain recovery time for permanent deformation was 0.026 s, 0.046 s, and 0.05 s for Chinese Leek, Crown daisy and Chamnamul, respectively. Finally, strain recovery time and strain recovery ratio for the test materials were 0.17 s, 60.4% in Chinese leek, 0.12 s, 55.3% in Crown daisy, 0.15 s, 58.7% in Chamnamul. Here strain recovery time means that how fast the test materials are recovered from initial deformation and strain recovery ratio means how much the test materials are recovered from initial deformation. The above results show that the test materials can be held enough and moved by the belts.