Tetsuhiro Sumimoto

Machine vision for detection of the rescue target in the marine casualty

In marine rescue, the detection of the target such as life rafts depends on the visual search by man as yet. However, human eyes are sometimes inadequate owing to a long flight and wide views. In order to carry out the prompt rescue of human life, development of the searching system in place of the human eyes is surely required. This paper deals with a new search method for detection of the rescue target using image processing techniques. To detect the small target in the wide views over the sea, we have proposed a new method including the image processing techniques based on the color information and the composite image sensor which increases about the measurement accuracy and the image processing speed at actual field. At the first step of the study, we attempt to extract the image data of the rescue target with the orange color in an experimental sea.<<ETX>>

3-D shape measurement of free-form machined surfaces by optical ring imaging system

The purpose of this paper is to develop an advanced 3-D profile sensor system which will be able to accurately measure 3-D free-form machined metal surfaces. The proposed sensor system has many advantages as compared with conventional measuring systems. First, a new detecting system of optical ring images utilized by the rotating image detector is developed to measure 3-D profiles in the long measuring range with high accuracy. Second, processing time can be shortened within 0.5 second by using the proposed detecting system. Third, the speckle noise is eliminated effectively by the rotating mechanism. Finally, it is concluded that this sensor system makes it possible to measure the profiles within an accuracy of /spl plusmn/50 /spl mu/m in the measuring range of 100 mm. In this paper, the measurement principle of the proposed sensor system is analyzed and the performance of the system is experimentally measured and discussed not only for both diffuse reflection surface and specular reflection surface, but also for reduction of the laser speckle noise which has direct influence on the measurement accuracy.

Development of Image Processing Technique for Detection of the Rescue Target in the Marine Casualty

When a marine casualty occurs, the detection of the rescue target such as life rafts depends on the visual search of humans eye. It is predicted, however, that human eye sometimes loses its sight and ability of detection falls down owing to the long flight and the nasty weather. For a practical purpose of the prompt rescue of human life, development of searching support system in place of human eye is surely required. To realize the detection of the small rescue target in the wide sea, we propose a new searching system using image processing techniques based on the color information. The searching system consists of a visual sensor, an equipment of image processing and a knowledge database. Integration of these parts enables us to detect the rescue target accurately no matter how bad the condition is. At the first step of our study, we attempt the development of image processing techniques to detect accurately the rescue target under the various weather conditions.

Automatic identification of conveyer-transferred parts through image data processing

To automate assembly lines, we have tested and evaluated various methods on part discrimination for a model conveyer line. An advanced method is developed on tracking and picking up a specified part among a variety of parts on a moving conveyer. The method consists of a part shape discrimination analysis following the image processing of CCD camera shots for on-conveyer parts. The fuzzy inference method has been founded to be the best one for the part discrimination. The arm control without stopping the conveyer line has been realized only by giving the timings of the arm start-up from waiting position and the arm deceleration to keep the same speed of the conveyer.<<ETX>>

Noncontact 3D shape inspection based on optical ring imaging system

The purpose of this paper is to develop a non-contact profile sensor system which will be able to accurately measure 3D free-form machined metal surfaces. The proposed sensor system has many advantages as compared with conventional measuring systems. First, a new detecting system of optical ring images utilized by rotating image detector is developed to measure 3D profiles in the long measuring range with high accuracy. Second, processing time can be shortened within 0.5 second by using the proposed detecting system. Third, the speckle noise is eliminated effectively by the rotating mechanism. Finally, it is concluded that this sensor system makes it possible to measure the profiles within an accuracy of +/- 50 micrometers in the measuring range of 150 mm. In this paper, the measurement principle of the proposed sensor system is analyzed and the performance of the system is experimentally measured and discussed not only for both diffuse reflection surface and specular reflection surface, but also for reduction of the laser speckle noise which has direct influence on the measurement accuracy.