Abstract: A real time video analytic processor that uses a trained convolutional neural network that embodies algorithms and processing architectures that process a wide variety of sensor images in a fashion that emulates how the human visual path processes and interprets image content. Spatial, temporal, and color content of images are analyzed and the salient features of the images determined. These salient features are compared to the salient features of objects of user interest in order to detect, track, classify, and characterize the activities of the objects. Objects or activities of interest are annotated in the image streams and alerts of critical events are provided to the user. Instantiation of the cognitive processing can be accomplished on multi-FPGA and multi-GPU processing hardware.

Abstract: The Hy-ALERT processing system operates simultaneously on the data streams from visible and thermal imaging sensors and from hyperspectral imaging sensors. The visible and thermal image processing uses cognitive-inspired processing techniques that determine the salient content of the imagers based on the system user definition of salient content. The hyperspectral image processing uses anomaly detection and template matching techniques to determine the salient materials content of the observed scenes. Cross-correlation processing of the salient content of the various image and hyperspectral data streams enables the sensor systems to adapt their operating characteristics to optimize effectiveness in near real-time.

Abstract: A real time video analytic processor that uses a trained convolutional neural network that embodies algorithms and processing architectures that process a wide variety of sensor images in a fashion that emulates how the human visual path processes and interprets image content. Spatial, temporal, and color content of images are analyzed and the salient features of the images determined. These salient features are compared to the salient features of objects of user interest in order to detect, track, classify, and characterize the activities of the objects. Objects or activities of interest are annotated in the image streams and alerts of critical events are provided to the user. Instantiation of the cognitive processing can be accomplished on multi-FPGA and multi-GPU processing hardware.

Abstract: The Hy-ALERT processing system operates simultaneously on the data streams from visible and thermal imaging sensors and from hyperspectral imaging sensors. The visible and thermal image processing uses cognitive-inspired processing techniques that determine the salient content of the imagers based on the system user definition of salient content. The hyperspectral image processing uses anomaly detection and template matching techniques to determine the salient materials content of the observed scenes. Cross-correlation processing of the salient content of the various image and hyperspectral data streams enables the sensor systems to adapt their operating characteristics to optimize effectiveness in near real-time.

Abstract: An invention is disclosed for a real time video analytic processor that embodies algorithms and processing architectures that process a wide variety of sensor images in a fashion that emulates how the human visual path processes and interprets image content. spatial, temporal, and color content of images are analyzed and the salient features of the images determined. These salient features are then compared to the salient features of objects of user interest in order to detect, track, classify, and characterize the activities of the objects. Objects or activities of interest are annotated in the image streams and alerts of critical events are provided to users. Instantiation of the cognitive processing can be accomplished on multi-FPGA and multi-GPU processing hardwares.

Abstract: An invention is disclosed for a real time video analytic processor that embodies algorithms and processing architectures that process a wide variety of sensor images in a fashion that emulates how the human visual path processes and interprets image content. spatial, temporal, and color content of images are analyzed and the salient features of the images determined. These salient features are then compared to the salient features of objects of user interest in order to detect, track, classify, and characterize the activities of the objects. Objects or activities of interest are annotated in the image streams and alerts of critical events are provided to users. Instantiation of the cognitive processing can be accomplished on multi-FPGA and multi-GPU processing hardwares.

Abstract: Current rehabilitative treatment of balance disorder requires long and intensive processes. The development of a wearable device for use in clinic as well as at home and during daily routine activities would enable continuous treatment outside of specialized training settings and accelerated relieve of balance disorder. The patent describes a wearable device that utilizes inertial sensors and sensor fusion processing to measure body posture and provide real-time feedback to alert the wearer to remain in the region of stability, and that utilizes wireless communication to support therapy and training providers.

Abstract: A method for processing sensor data representative of a scene of interest. A plurality of sensor data outputs representative of the scene is selected from the group consisting of visible, VNIR, SWIR, MWIR, LWIR, far infrared, multi-spectral data, hyper-spectral data, SAR data, and 3-D LIDAR sensor data. The data is input to a plurality of graphics processing elements that are configured to independently execute separate image processing filter operations selected from the group consisting of spatial filtering, temporal filtering, spatio-temporal filtering, and template matching. A cross-correlation operation is performed on the filter outputs based on predetermined filter output characteristics which may then be used to annotate the scene with regions of interest (ROI) for display to a user.

Abstract: The invention comprises a lip reading device having a capacitive array for enhanced portable speech recognition. The capacitive array of the invention produces a sequence of signal frames or signal data sets (i.e., digitized output) representative of the proximity and motion of a user's lips at a predetermined sample rate and resolution. The sequence of signal data sets is stored in a first electronic memory and are compared against a reference data set representative of a predetermined acoustic signal stored in a second electronic memory. The attributes of signal data set are compared against the reference data set for likely data matches based on predetermined criteria.