This paper discusses a practical system which, when incorporated in an autonomous mobile robot moving indoors, can determine the position of the robot and detect obstacles so that the robot can navigate appropriately. We have developed new real-time, reliable techniques using correlation operations to achieve vision-based localization and obstacle detection. These techniques include a landmark detection technique that assures stable detection even under variable brightness and an obstacle measurement technique that combines obstacle region segmentation with stereo vision. Our experiments have proven that these techniques can make the necessary measurements in 100 ms, assure stable measurement in environments of varying brightness, and are sufficient for mobile robots.

This paper describes the design and the implementation of a high-speed visual tracking system based on local correlation matching. The system consists of only two PC board modules, which conform to VME bus specifications. The video module is used to input and output video signals, while the tracking module is used to perform visual tracking with the local correlation method. The tracking module contains three frame memories, an image flow controller, a DMA controller for image data transfer, and a dedicated LSI to perform the correlation matching of 8-bit gray-scale images. The processing time is 110 microseconds for an 8/spl times/8 pixel template and 290 microseconds for a 16/spl times/16 pixel template. This paper also describes some of our experimental implementations, including human tracking, recognition of hand movements and signs, and traffic monitoring. Compared to conventional general-purpose image processing systems, our hardware system is compact and inexpensive. This high-performance system can be used for a wide variety of motion analysis applications.

The authors developed a small, lightweight rangefinder system which can be mounted on the wrist of a robot. Ranging takes place using a binary-coded projection method based on the principle of triangulation. The head of the range finger comprises a multi-slit projector with an infrared semiconductor laser, a nematic-cholesteric phase-transition (NCPT) liquid crystal shutter, and a small CCD camera. A head size of 170 mm/spl times/80 mm/spl times/50 mm and a weight of 230 grams were achieved. A dedicated image processor was developed to speed up range data generation. The time required to produce a range image is about 0.5 second. The system was tested on a real scene of a mechanical part, which is used in truss assembly in space.

A hardware system for emulating microgravity for an on-the-ground space manipulator is described. The manipulator is suspended by wires, kept vertical by the suspension arms controlled to follow the manipulator's motion. The manipulator base is supported by a six-degree-of-freedom mechanism, with which free floating is emulated based on the numerical integration of the dynamic and kinematic equations for the manipulator. The gravitational force acting on the manipulator is thus canceled by the combination of the contact force on the base and the upward tensile forces through the wires. Optimizing the manipulator's suspension keeps the values of individual tensions acting on it constant, whatever the manipulator's attitude. Experiments show that the suspension system is sensitive enough to emulate the vertical free-floating motion of a suspended object, and can be tuned to initiate a microgravity environment of at least 0.01 g under restricted conditions.>

A hand-eye system with 3-D vision system and a microgripper has been developed for handling, forming and inserting flexible wires in electronic assembles. The hand-eye system performs its task based on visual sensor and force sensor data. The vision system uses a camera, a laser-multiplanar light projector, and a videorate image processor to measure the 3-D geometry of flexible wires within one robot cycle. The measurement accuracy is better than 1 mm perpendicular to the plane for a depth of 500 mm. The microgripper has three-axis sensors capable of detecting three kinds of forces; grasping, pulling, and pushing. The dynamic range of the grasping force is 0.5 to 60 gf. This system has been used for wire assembling in magnetic-disk slider manufacture. Using recovery function, the success ratios for measurement, grasping and upper insertion were 100%. The design concepts, the 3-D measurement, the hand-eye system, and the wire-assembling application are discussed.>

A motion stereo algorithm for measuring straight lines three-dimensionally is presented. The three-dimensional information is obtained by moving a single camera linearly and processing the resulting sequential multiple images. The algorithm utilizes spherical mapping, which is a transformation from a point to a great circle on a sphere. This algorithm makes it possible to process an image from a fisheye lens, which has a wide field of view. A straight line composed of several pixels is concentrated at a single point on a two-dimensional image. A three-dimensional image measurement is then performed by use of the above point. This yields high measurement accuracy and reliability. The measurement accuracy can be improved by lengthening the span of the camera movement and by increasing the number of frames. The measurement reliability can also be improved by increasing the number of frames. The basic algorithm is described, and its characteristics relating to accuracy and reliability are tested.>

The Hough transform method for recognition can cope effectively with noisy backgrounds and gaps in boundaries. However, long computation time and large memory requirements have prevented it from being used in real-time applications. An architecture devised to solve those problems, with a focus on detecting straight lines, is presented. Examples are given of the use of an experimental hardware model for automatic inspection and measurement of objects in factories and laboratories. It took less than one second from picture input to straight line parameter reproduction for these examples.>

We have developed a processor with dedicated hardware for performing high-speed Hough transforms, to enable real time inspection and measurement of linear boundaries in gray scale images. The Hough transform method for recognition can cope effectively with noisy backgrounds and gaps in boundaries. However, long computation time and large memory requirements have been preventing it from being used in real time applications. This paper presents an architecture devised to solve those problems. It also provides examples of application to automatic inspection and measurement of objects in factories and laboratories. It took less than one second from picture input to straight line parameter reproduction for these examples.