Abstract: Apparatuses, systems, and techniques to generate one or more confidence values associated with one or more objects identified by one or more neural networks. In at least one embodiment, one or more confidence values associated with one or more objects identified by one or more neural networks are generated based on, for example, one or more neural network outputs.

Abstract: An interactive display system and method of operating the same including a remote pointing device for controlling items displayed at a display, in which movement of the device is adjusted according to distance from the display. Distance of the device from the display is determined, and a sensitivity reduction factor corresponding to that distance is calculated. Physical movement of the device is interpreted as movement of a cursor position at the display, with the extent of that movement adjusted according to the sensitivity reduction factor. An additional sensitivity reduction factor corresponding to the speed of movement of the device may also be incorporated into the adjustment of the cursor position.

Abstract: An interactive display system including a wireless pointing device, and positioning circuitry capable of determining absolute and relative positions of the display at which the pointing device is aimed. An error value between the absolute position and an estimated or actual relative position at the point in time of the absolute position is determined, and a compensation factor is determined from this error value that is applied to subsequent relative positioning results.

Abstract: An interactive display system including a wireless pointing device, and positioning circuitry capable of determining absolute and relative positions of the display at which the pointing device is aimed. The pointing device captures images displayed by the computer, including one or more human-imperceptible positioning targets. The positioning targets are presented as patterned modulation of the intensity (e.g., variation in pixel intensity) in a display frame of the visual payload, followed by the opposite modulation in a successive frame. At least two captured image frames are subtracted from one another to recover the positioning target in the captured visual data and to remove the displayed image payload. Motion of the pointing device between the two frames is detected by relative motion sensors, and used to align the positions of the positioning targets in the captured images for those frames to improve the fidelity of the recovered positioning target following the subtraction.

Abstract: An interactive display system including a wireless pointing device, and positioning circuitry capable of determining absolute and relative positions of the display at which the pointing device is aimed. The pointing device captures images displayed by the computer, using a rolling shutter, the images including one or more human-imperceptible positioning targets. The positioning targets are presented as patterned modulation of the intensity (e.g., variation in pixel intensity) in a display frame of the visual payload, followed by the opposite modulation in a successive frame. At least two captured image frames are subtracted from one another to recover the positioning target in the captured visual data and to remove the displayed image payload. The capturing of images at the pointing device is synchronized with the release of image data to the display, to avoid errors in the positioning operation.

Abstract: A method for disparity cost computation for a stereoscopic image is provided that includes computing path matching costs for external paths of at least some boundary pixels of a tile of a base image of the stereoscopic image, wherein a boundary pixel is a pixel at a boundary between the tile and a neighboring tile in the base image, storing the path matching costs for the external paths, computing path matching costs for pixels in the tile, wherein the stored path matching costs for the external paths of the boundary pixels are used in computing some of the path matching costs of some of the pixels in the tile, and computing aggregated disparity costs for the pixels in the tile, wherein the path matching costs computed for each pixel are used to compute the aggregated disparity costs for the pixel.

Abstract: An interactive display system including a wireless pointing device, and positioning circuitry capable of determining absolute and relative positions of the display at which the pointing device is aimed. The pointing device captures images displayed by the computer, including one or more human-imperceptible positioning targets. The positioning targets are presented as patterned modulation of the intensity (e.g., variation in pixel intensity) in a display frame of the visual payload, followed by the opposite modulation in a successive frame. At least two captured image frames are subtracted from one another to recover the positioning target in the captured visual data and to remove the displayed image payload. Motion of the pointing device between the two frames is detected by relative motion sensors, and used to align the positions of the positioning targets in the captured images for those frames to improve the fidelity of the recovered positioning target following the subtraction.

Abstract: A system and method are provided for actively illuminating and capturing images of an object, such as a driver of a vehicle to reduce glare. The system includes a video imaging camera orientated to generate images of the subject object (e.g., eye(s)) in successive video frames. The system also includes first and second light sources operable to illuminate the object one at a time. The system further includes a processor for processing the image by performing pixel-wise min operation to combine multiple frames into a single frame to reduce glare in the image. The system may remove glare caused by the illuminators and caused by external energy sources.

Abstract: Real-time video images of a human subject's face are processed by a plurality of classification algorithms developed in an off-line training process to determine the open vs. closed eye state of the subject. The off-line training process utilizes a genetic programming loop embedded within an adaptive boosting loop, and forms the classification algorithms and weighting factors for combining their classification scores. In the real-time process, the individual classification scores are combined and compared to a threshold to determine the open vs. closed eye state.

Abstract: A method of detecting the state of an operator of a vehicle utilizes a low-cost operator state detection system having no more than one camera located preferably in the vehicle and directed toward a driver. A processor of the detection system processes preferably three points of the facial feature of the driver to calculate head pose and thus determine driver state (i.e. distracted, drowsy, etc.). The head pose is generally a three dimensional vector that includes the two angular components of yaw and pitch, but preferably not roll. Preferably, an output signal of the processor is sent to a counter measure system to alert the driver and/or accentuate vehicle safety response.

Abstract: An iterative process involving both genetic programming and adaptive boosting is used to develop a classification algorithm using a series of training examples. A genetic programming process is embedded within an adaptive boosting loop to develop a strong classifier based on combination of genetically produced classifiers.

Abstract: Real-time video images of a human subject's face are processed by a plurality of classification algorithms developed in an off-line training process to determine the open vs. closed eye state of the subject. The off-line training process utilizes a genetic programming loop embedded within an adaptive boosting loop, and forms the classification algorithms and weighting factors for combining their classification scores. In the real-time process, the individual classification scores are combined and compared to a threshold to determine the open vs. closed eye state.

Abstract: A system and method are provided for actively illuminating and capturing images of an object, such as a driver of a vehicle to reduce glare. The system includes a video imaging camera orientated to generate images of the subject object (e.g., eye(s)) in successive video frames. The system also includes first and second light sources operable to illuminate the object one at a time. The system further includes a processor for processing the image by performing pixel-wise min operation to combine multiple frames into a single frame to reduce glare in the image. The system may remove glare caused by the illuminators and caused by external energy sources.

Abstract: A method of detecting the state of an operator of a vehicle utilizes a low-cost operator state detection system having no more than one camera located preferably in the vehicle and directed toward a driver. A processor of the detection system processes preferably three points of the facial feature of the driver to calculate head pose and thus determine driver state (i.e. distracted, drowsy, etc.). The head pose is generally a three dimensional vector that includes the two angular components of yaw and pitch, but preferably not roll. Preferably, an output signal of the processor is sent to a counter measure system to alert the driver and/or accentuate vehicle safety response.

Abstract: An object awareness determination system and method of determining awareness of a driver of a vehicle to an object is provided. The system includes an object monitor including an object detection sensor for sensing an object in a field of view and determining a position of the object. The system also includes an eye gaze monitor including an imaging camera oriented to capture images of the vehicle driver including an eye of the driver. The gaze monitor determines an eye gaze vector. The system further has a controller for determining driver awareness of the object based on the detected object position and the eye gaze vector.

Abstract: A customer compatible software is electronically provided to a customer based on a customer specification provided through a web interface. In one embodiment, the specification is checked for input errors and the customer is prompted to correct any detected errors, before proceeding. In another embodiment, a specification file is created by a common gateway interface (CGI) program based on the received customer specification. A customer compatible executable is then created by first selecting generic source code from a library (based on the specification file). Next, the generic source code is modified (based on the specification file). Then, the modified generic source code is compiled and linked to create an executable. Finally, the executable is converted to a customer compatible executable and provided with documentation to the customer via e-mail.

Abstract: An object awareness determination system and method of determining awareness of a driver of a vehicle to an object is provided. The system includes an object monitor including an object detection sensor for sensing an object in a field of view and determining a position of the object. The system also includes an eye gaze monitor including an imaging camera oriented to capture images of the vehicle driver including an eye of the driver. The gaze monitor determines an eye gaze vector. The system further has a controller for determining driver awareness of the object based on the detected object position and the eye gaze vector.