Kozo Ohtani

An Identification Approach for Object Shapes and Materials Using an Ultrasonic Sensor Array

From the viewpoint of environmental protection, the recycling of wastes becomes ever more important. In such a field, there is the manner of recycling or reuse, we need to develop a simple technique on advertising to promote recycling and reuse based on the local autonomy. Especially, the field of sorting for reuse requires a simple sensor system that identifies the materials, shape and size of an object without contact with the target. We propose a new identification system using an ultrasonic sensor array and neural networks. The method sorts by the shape and the material of an object based on ultrasonic pressure distribution and acoustic impedance. We have done some experiments with a prototype sensor system. The experimental results showed the practical applicability of the identification method in a shapes and materials sorting system

Shape recognition for transparent objects using ultrasonic sensor array

Ultrasonic sensors are often utilized for perceiving the outside world. In this paper, we propose the construction of a new ultrasonic recognition system for identification of transparent object. The proposed recognition system consists of an ultrasonic transmitter, an ultrasonic receiver, and a recognition unit. The systems receiver is made up of plural ultrasonic sensor array. The receiver outputs the peak values and the positions of ultrasonic sound pressure waves. Their values and positions are input in to recognition unit, which consists of the neural networks for object identification and the neural networks (NNs) for the measurement of the objects position. We have designed and built a prototype system for identification and position measurement for polyethylene terephthalate bottle (Pet bottle). We tested this system by attempting to identify and measure the positions of seven kinds of Pet bottle. The experimental results showed perfect identification and an accuracy of about 5 mm.

3D shape recognition system by ultrasonic sensor array and genetic algorithms

This paper describes 3D shape recognition system using ultrasound pressure data and a Genetic Algorithm. The ultrasonic 3D shape recognition system using has commonly used a Neural Network (NN). However, a NN perform poorly when lacking learned data. In order to overcome this problem when using a NN, we here attempt to replace the NN with a Genetic Algorithm (GA). Unlike a NN, the GA can recognize shapes without depending on learned data. Experimental results demonstrate that the recognition ratios of the proposed recognition system using the GA are higher than that of a conventional 3D shape recognition system using a NN. Therefore, it is shown that our ultrasonic 3D shape recognition system is effective for many industrial applications.

A Simple Identification Method for Object Shapes and Materials Using an Ultrasonic Sensor Array

From the viewpoint of environmental protection, the recycling of wastes becomes ever more important. In such a field, there is the manner of recycling or reuse, we need to develop a simple technique on advertising to promote recycling and reuse based on the local autonomy. Especially, the field of sorting for reuse requires a simple sensor system that identifies the materials, shape and size of an object without contact with the target. Here, we propose a new identification system using an ultrasonic sensor array and neural networks. The method sorts by the shape and the material of an object based on ultrasonic pressure distribution and acoustic impedance. We have done some experiments with a prototype sensor system. The experimental results showed the practical applicability of the identification method in a shapes and materials sorting system

A method for traffic sign detection and recognition based on genetic algorithm

This paper presents a method for detection and recognition of traffic signs. We proposed a new recognition approach of traffic signs, which has the feature of introducing Genetic Algorithm (GA). We designed and built a prototype system by implementation of C++ and OpenCV library. The experimental results show that our approach could have good prospects for automatic detection and recognition of traffic signs.

Thermal Deformation Prediction in Machine Tool Model by Using Transfer Functions with Time Delay

The purpose of this paper is to estimate thermal deformation of machine tool model by using transfer function with time delay. The prediction method of thermal deformation based on frequency domain is constructed from transfer function between specified surface temperatures and the relative displacement in cutting area. The relative displacement in cutting area is predicted using two specified surface temperatures near heat source in machine tool model. As a result, the method can be predicted with enough certainty at what rate the temperature changes the most rapidly on machines startup transient behavior. The method proposed in this paper is remarkably effective to estimate thermal deformation and confirm that the error between experimental and estimated values will be remarkably reduced.

Shape recognition by network configuration of ultrasonic sensor array and CCD image sensors

Although optical sensors have been generally used for perceiving the external world, ultrasonic sensors are often utilized in situations in which optical sensors cannot be used. However, ultrasonic sensors have the severe drawbacks of low resolution and inherent weakness in the form of external noise. In order to improve the performance of the shape recognition with ultrasonic sensors, we here proposed a shape recognition system by network configuration of ultrasonic sensor array and CCD image sensors. The sensor network system allows application in situations in which it is difficult to identify an objects shape using ultrasonic sensor array alone or CCD image sensor alone. The basic concept of the approach is to fuse the shape recognition information, which is acquired using the sensor network, by Genetic algorithms (GAs).

Evaluation of Surface Shape and Refractive Index of a Transparent Plate Based on Light Path Analysis

Many practical tasks in industry require the simultaneous determination of 3-D shape and refractive index of a transparent object. We have formulated an approach to evaluating the surface shape and refractive index by light path analysis. The effectiveness of the proposed method was confirmed from experimental results.

Recovering Shape of a Specular Object in the Presence of Interreflection

Active triangulation methods assume that points in a scene are only illuminated by the sources of light. However, this assumption is valid when the light is reflected at one time from a single convex surface. Actual objects often include concave surfaces where points reflect light between themselves. In the presence of these interreflections, active triangulation methods produce erroneous estimates of shape. In this paper, an approach is proposed to recover the shape of a specular object in the presence of interreflection, with prior knowledge on the shape information of the specular object or not. Both simulation and experiment results proved that the proposed approach was effective.

DETECTION AND EVALUATION OF DELAMINATION USING ACOUSTIC EMISSION METHOD IN THERMALLY SPRAYED COATING UNDER TENSILE STRESS

AE was measured under a static tensile load for the thermally sprayed ceramic coating in order to investigate the relationship between the detected m-value and the destruction (delamination) of the sprayed coating. This was an effective method to detect and evaluate the delamination of a sprayed coating based on the m-value, because changes of the m-value were closely related in thermally sprayed coatings. Stress level of the delamination analyzed by AE method was almost the same as that predicted by the ESPI method. The generation of delamination was confirmed by cross-section observation of the coating using both stress levels. Therefore, the ESPI method seems to be an effective way to define and evaluate the delamination of sprayed coating determine.