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 object´s 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).