Abstract: A method comprises receiving an image of the area, the image representing the area in a first color space; converting the received image to at least one second color space to produce a plurality of converted images, each converted image corresponding to one of a plurality of color sub-spaces in the at least one second color space; calculating upper and lower thresholds for at least two of the plurality of color sub-spaces; applying the calculated upper and lower thresholds to the converted images corresponding to the at least two color sub-spaces to segment the corresponding converted images; fusing the segmented converted images corresponding to the at least two color sub-spaces to segment the received image; and updating the segmentation of the received image based on edge density data in the received image.

Abstract: A speech recognition system and a personal speech profile data (PSPD) storage device that is physically distinct from the speech recognition system are provided. In the speech recognition system, a PSPD interface receives voice training data, which is associated with an individual and the operating conditions of an aircraft, from the PSPD storage device. A speech input module produces a digital speech signal derived from an utterance made by a system user. A speech processing module accesses voice training data stored on the PSPD storage device through the PSPD interface, and executes a speech processing algorithm that analyzes the digital speech signal using the voice training data, in order to identify one or more recognized terms from the digital speech signal. A command processing module initiates execution of various applications based on the recognized terms. Embodiments may be implemented in various types of host systems, including an aircraft cockpit-based system.

Abstract: A multi-sensor method and system for imaging and inspecting a storage tank that holds a liquid. The system includes an infrared sensor including a scanning vertical mount positioned outside the storage tank, an ultrasonic sensor array positioned outside the storage tank, and at least one of an ultrasonic sensor positioned inside the storage tank and a phased array radar positioned inside the storage tank secured to an interior top surface of the storage tank. The system further includes a processor coupled to receive multi-sensor data from the infrared sensor, ultrasonic sensor array and at least one of the ultrasonic sensor in the tank and the phased array radar. The processor fuses the multi-sensor data to generate a sludge level image profile for sludge in the storage tank, a liquid level image for liquid in the storage tank, and optionally an integrity profile for a shell of the storage tank.

Abstract: A system for calibrating a thermal camera with a calibration target. The calibration target may have a pattern which can be seen on an infrared image captured by the camera. The pattern may be of various kinds. For example, the pattern may be a checkerboard with some, such as every other square, having one emissitivity and the remaining squares having a different emissitivity, or having infrared light sources placed at corners of the squares. A difference between the emmissitivities may be sufficient so that the checkerboard pattern appears in an infrared image captured by the camera for calibration. The calibration may aid in determining intrinsic and extrinsic parameters of the camera. The parameters may provide a basis for transforming camera pixel coordinates to a world coordinate system which allows measurement of real world entities by the thermal camera. Measurements may incorporate distances between objects, heights of objects, and so forth.

Abstract: Embodiments include a speech recognition system and a personal speech profile data (PSPD) storage device that is physically distinct from the speech recognition system. In the speech recognition system, a PSPD interface receives voice training data, which is associated with an individual, from the PSPD storage device. A speech input module produces a digital speech signal derived from an utterance made by a system user. A speech processing module accesses voice training data stored on the PSPD storage device through the PSPD interface, and executes a speech processing algorithm that analyzes the digital speech signal using the voice training data, in order to identify one or more recognized terms from the digital speech signal. A command processing module initiates execution of various applications based on the recognized terms. Embodiments may be implemented in various types of host systems, including an aircraft cockpit-based system.

Abstract: A method comprises receiving an image of the area, the image representing the area in a first color space; converting the received image to at least one second color space to produce a plurality of converted images, each converted image corresponding to one of a plurality of color sub-spaces in the at least one second color space; calculating upper and lower thresholds for at least two of the plurality of color sub-spaces; applying the calculated upper and lower thresholds to the converted images corresponding to the at least two color sub-spaces to segment the corresponding converted images; fusing the segmented converted images corresponding to the at least two color sub-spaces to segment the received image; and updating the segmentation of the received image based on edge density data in the received image.