Abstract: A system and method for simultaneously obtaining a plurality of images of an object or pattern from a plurality of different viewpoints is provided. In an exemplary embodiment, proper image contrast is obtained by replacing the light sources of earlier systems with equivalent light sensitive devices and replacing the cameras of earlier systems with equivalent light sources. With such a system, bright-field images and dark-field images may be simultaneously obtained. In one aspect of the invention, a light source is positioned to illuminate at least a portion of an object. A plurality of light guides having input ends are positioned to simultaneously receive light reflected from the object and transmit the received light to a plurality of photodetectors. The light guides are arranged such that their respective input ends are spaced substantially equally along at least a portion of a surface of an imaginary hemisphere surrounding the object.

Abstract: A method and apparatus are disclosed for identifying a speaker in an audio-video source using both audio and video information. An audio-based speaker identification system identifies one or more potential speakers for a given segment using an enrolled speaker database. A video-based speaker identification system identifies one or more potential speakers for a given segment using a face detector/recognizer and an enrolled face database. An audio-video decision fusion process evaluates the individuals identified by the audio-based and video-based speaker identification systems and determines the speaker of an utterance in accordance with the present invention. A linear variation is imposed on the ranked-lists produced using the audio and video information. The decision fusion scheme of the present invention is based on a linear combination of the audio and the video ranked-lists. The line with the higher slope is assumed to convey more discriminative information.

Abstract: A system for simultaneously obtaining a plurality of images of an object or pattern from a plurality of different viewpoints is provided. Proper image contrast is obtained by replacing the light sources of earlier systems with equivalent light sensitive devices and replacing the cameras of earlier systems with equivalent light sources. Bright-field and dark-field images may be simultaneously obtained. In another aspect, a light source is positioned to illuminate at least some of an object. A plurality of light guides are positioned to simultaneously receive light reflected from the object and transmit it to a plurality of photodetectors. The light guides are arranged so their respective input ends are spaced substantially equally along at least a portion of a surface of an imaginary hemisphere surrounding the object. The signals from the photodetectors are processed and a plurality of images are formed. Another aspect provides generating composite images from simultaneously obtained images.

Abstract: A presence of a polarization altering substance on a specular surface is detected by transmitting light from a single strobed light source to the surface over a transmitting path and receiving the transmitted light from the surface. An intensity of the light is measured in both an optical non-isolator state and an isolator state by a same detector by delaying the non-isolated return light for a definite period of time before measuring it with the detector. The measured isolated and non-isolated intensities are converted to logarithmic form, range corrected, and compared to reference data established for the specific specular surface being investigated to detect the presence or absence of the polarization altering substance. Attenuation and backscattering effects of scattering and/or absorbing interference in the transmitted light are compensated so that the reference table is entered at the correct point. Using different intensities of transmitted light increases the dynamic range of the system.

Abstract: A presence of a polarization altering substance on a specular surface is detected by transmitting light from a single strobed light source to the surface over a transmitting path and receiving the transmitted light from the surface. An intensity of the light is measured in both an optical non-isolator state and an isolator state by a same detector by delaying the non-isolated return light for a definite period of time before measuring it with the detector. The measured isolated and non-isolated intensities are converted to logarithmic form, range corrected, and compared to reference data established for the specific specular surface being investigated to detect the presence or absence of the polarization altering substance. Attenuation and backscattering effects of scattering and/or absorbing interference in the transmitted light are compensated so that the reference table is entered at the correct point. Using different intensities of transmitted light increases the dynamic range of the system.

Abstract: An arrangement for steering the laser beam, in an active optical triangulation method based on three-dimensional sensors, along paths which are sensitive to the context of the scene of interest, and alleviating the need to undergo a search path by the sensor. A conventional video camera is used to preview the scene of interest and the resultant intensity image is processed to locate the desired path based on the scene context. The sensory system is modeled to enable determination of the instantaneous angular deflections of the laser beam along with the translation of the laser source that can shift the nominal or actual data acquisition path to the desired data acquisition path.

Abstract: A method and apparatus for fusion of three dimensional data due to an active optical triangulation based vision sensor, and two-dimensional data obtained from an independent TV camera. The two sensors are aligned so that their view volumes are partially overlapped. In the course of a calibration process, a planar target is placed and depressed through the common view volume of the two sensors. The illuminant of vision sensor projects a stripe onto the target. As the stripe is traversed across the target incrementally, it is imaged at every position not only by the camera of the vision sensor, but also by the independent TV camera. The calibration process yields a table which connects the resolution cells of the TV camera to a set of rays whose equations are established in the coordinate measurement system of the three dimensional vision sensor. The calibration table is subsequently used to inter-relate points in either sensory space via their connecting rays.

Abstract: A stream calibration arrangement for visually determining the position and orientation of a sprayed material stream. Use of a stream calibration fixture to determine adjustments to an adjustable spray gun mount to realign a spray stream without altering the taught path of a robot carrying the spray gun. Alternatively, the stream is realigned by altering the taught robot path and requiring no gun mount adjustment. Stream realignment is also carried out automatically with and without gun mount adjustments. Machine vision is used for automatic stream realignment.