Tateshi Fujiura

Fruit harvesting robots in Japan

We have developed harvesting robots for tomato, petty-tomato, cucumber and grape in Japan. These robots mainly consist of manipulators, end-effectors, visual sensors and traveling devices. These mechanisms of the robot components were developed based on the physical properties of the work objects. The robots must work automatically by themselves in greenhouses or fields, since we are considering for one operator to tend several robots in the production system. The system is modeled after Japanese agriculture which is commonly seen to produce many kinds of crops in greenhouses and in many small fields intensively. Bioproduction in space is somewhat similar to the agricultural system in Japan, because few operators have to work in a small space. Employing robots for bioproduction in space is considered desirable in near future. The following is a description of the harvesting robots.

Basic constitution of a robot for agricultural use

Many studies on agricultural robots and on robot components such as manipulators, visual sensors, end-effectors and traveling devices have been performed to solve problems when robots work in fields or in greenhouses. In addition, productivity should also be considered in the agricultural production system in the case that the cultivation method and plant training system are changed so that the robot can work without trouble. In this study, a tomato harvesting robot is described as a example of an agricultural robot. First, the basic mechanism of the robot and the details of the robot components are developed based on the physical properties of the tomato plant and on the environmental conditions. Secondly, a cherry tomato harvesting end-effector is also developed so that the robot can harvest not only normal size tomatoes but also cherry tomatoes by changing the end-effector to make it a multi-purpose robot. Lastly, horticultural methods such as suitable cultivation methods and plant training methods for...

Estimation of Serum Vitamin A Level by Color Change of Pupil in Japanese Black Cattle

Abstract Color change of pupil area was investigated in Red, Green, Blue (RGB) and Hue, Saturation, Intensity (HSI) color models from July to November in 2010 and from May to December in 2011 to estimate the serum vitamin A level of Japanese black cattle during their vitamin A controlled stage. A 2CCD camera was used to acquire the eye images. The results showed lower vitamin A level cattle usually accompanied with higher red component value, lower saturation in their eye images. An estimation model was built based on red and green component ratio. The estimation error is about 10 IU/dL. The reasonable result shows the feasibility to estimate the vitamin A level by color change of pupil area in Japanese black cattle.

Vision System for Cucumber-Harvesting Robot

Abstract A vision system was made and experimented for a cucumber-harvesting robot that harvests fruits on the cucumber plants trained along the inclined poles. The fruit was detected by specular-reflection sensors while the robot was traveling. The detected fruit was scanned by a 3-D vision sensor. Image recognition experiment was carried out using cucumber models that were made based on a real cucumber. The location and the size of the fruit could be recognized.

Effects of Low Serum Vitamin A Level on Pupillary Light Reflex in Japanese Black Cattle

Abstract Four parameters of pupillary light reflex were investigated from May to December in 2011 to study the effects of low serum vitamin A level on pupillary light reflex in Japanese black cattle during their vitamin A controlled stage. A 2CCD camera was used to acquire the pupillary light reflex images. Constriction amplitude in 1 second, maximum constriction velocity, maximum velocity time and initial pupil roundness were used for pupillary light reflex analysis. Cattle in low vitamin A level period had larger constriction amplitude in 1 second ( p =0.001), higher maximum constriction velocity ( p =0.016) and thinner resting pupil ( p =0.003). This result showed pupillary light reflex analysis can be used as indicators for cattle management during vitamin A controlled stage.

Machine vision based prediction of serum vitamin A level in Japanese Black Cattle by pupillary light reflex analysis

To increase the BMS (Beef Marbling Standard) score of Japanese Black Cattle, keeping the cattle serum vitamin A at a low level (30–40 IU/dl) during fattening age is an effective way. The traditional method of monitoring the serum vitamin A level is blood assay. However, it is costly, time-consuming and makes cattle stressful. A new approach by using 2CCD camera is proposed in this study. Pupil reflex of cattle with different vitamin A level was analyzed by image processing.

The relationship between serum vitamin A level of Japanese black cattle and light reflection on the pupil

In order to make better beef with high marbling score, breeders need to control serum vitamin A level from 30 IU/dl to 50 IU/dl during the middle fatting phase. Today, serum vitamin A level of beef cattle is usually measured by blood assay. However, blood assay has some disadvantages such as it is cost and time-consuming. For establishment of new method for prediction of serum vitamin A level, this study examined the relationship between serum vitamin A level of Japanese black cattle and the light reflection on pupil. Light reflection measurement was carried out by image processing. This study showed that B in RGB components around halation area on cattles pupil of color images has possibility of correlation with serum vitamin A level.

Correlation between serum vitamin A level and pupil color of beef cattle

Farmers usually control cattles serum vitamin A level to improve beef meat fat quality. They sometimes conduct blood tests, but that is invasive and another measurement system is desirable. The objective of this study was to investigate the relationship between serum vitamin A level and pupil colors of beef cattle for developing a vitamin A monitoring system by machine vision. Images of cattle eyes were collected and chromaticity values of pupil color were calculated. Although the values had variability, it was found that serum vitamin A had a negative correlation with red component, while it had a positive correlation with blue component.

Gait Control by Genetic Algorithm for Agricultural Hexapod Walking Robot

Abstract The bio-production of the orchard and the ravine part is done in the inclination ground and unleveled land. The hexapod walking robot, which is stabilized in these field, is suitable for many production works. This study had aimed to develop hexapod walking robots for agriculture. First of all, a small walking robot was made for trial, to form flexible gait that adjusted to unleveled land. Next, straight advancement and turn gait of this robot was formed with genetic algorithms.