Real-time Image Processing System by Using FPGA for Service Robots

Service robots assist human beings, typically by performing a job that is dirty, dull, distant, dangerous, or repetitive, including household chores. They typically are autonomous and/or operated by a built-in control system, with manual override options. In simpler words, A service robot is a robot which operates semi- or fully autonomously to perform services useful to the well-being of humans and equipment, they exclude manufacturing operations, and they are capable of making decisions and acting autonomously in real and unpredictable environments to accomplish determined tasks. Following the past years, there has been a lot of research and development into autonomous mobile robots in both industry and academia. Autonomous mobile robots need the ability of spatial recognition and various detective functions to carry out their work. As a result of Japan’s aging society with fewer children in the future, autonomous mobile robots are expected to be useful for security applications such as watching and surveillance. In this paper, a real-time video communication system using a networked FPGA board and real-time extension of Linux OS is introduced. The image capture circuit is made by hardware description language on the FPGA. The stepper motor control circuit is integrated with the image recognition. In addition, dedicated Linux OS with hard real-time extension manages the peripheral devices on the FPGA. Furthermore, a CMOS camera module is attached to the pan-tilt mechanism for tracking moving target objects.

In this paper, the real-time image processing system for robot vision system is presented by the FPGA implementation. The robot vision system detects and tracks a moving object smoothly. Moreover this robot vision system detects the corridor boundaries between floors and walls, and judges its position and orientation in the passage environment. This robot vision system is small enough and requires low power consumption for various robot applications. For example, a patrol service robot for finding a suspicious person or indoor surveillance of elderly people would be considered as useful applications. The integration of hardware and software platform for real-time image processing could be applicable to various purposes. For the next stage, the FPGA implementation for image processing to detect stereo disparity would be desirable for measuring the distance to objects.