AN ULTRASONIC VISUAL SENSOR FOR 3-DIMENSIONAL OBJECT RECOGNITION USING NEURAL NETWORKS

By combining ultrasonic imaging with neural networks, we have developed a new 3-D object recognition system for use in robotic vision. Ultrasonic imaging is used to calculate the initial 3-D images of the objects. These images are then passed to neural networks that 1) identify object categories, 2) estimate object locations, and 3) improve 3-D images. In this paper, we explain the 3-D ultrasonic imaging method, propose three neural network structures for 3-D image analysis, and demonstrate the practicability of the system through experimental results, which show that quick and accurate recognition can be achieved using only a small set of transducers.