Abstract: A method and apparatus for detecting tampering with an image capturing device. The method includes determining a change has occurred in average intensity if an image, determining a percentage area of a foreground mask, detecting related at least one edge and determining at least one edge weight, utilizing the average intensity, the percentage area of the foreground mask, and the at least one edge weight to determining offset of edge blocks of an image, and utilizing the determining offset of edge blocks to detect tampering with an image capturing device.

Abstract: For controlling operation of a vehicle, at least one camera captures an image of a screen on which a user places an object having features distinguishing the user. A controller detects the features in the image and analyzes the features to distinguish the user. In response to distinguishing the user, the controller outputs signals for controlling operation of the vehicle. A projector receives information from the controller and projects the information onto the screen, so that the information is displayed on the screen for viewing by the user.

Abstract: A method of camera pose estimation is provided that includes capturing a model image of a scene at a canonical camera pose, generating an image library from warped images of the model image and the model image, wherein each warped image is a transformation of the model image at a different pre-determined camera pose, capturing an image of the scene as a user moves the camera, reporting the current camera pose as a camera pose of the image when the image is acceptable, conditionally adding the first image to the image library when the first image is acceptable, and re-initializing the current camera pose to a camera pose selected from the image library when the first image is not acceptable.

Abstract: A first camera captures first images of first views. A second camera captures second images of second views. First visual features are detected and tracked in the first images. Second visual features are detected and tracked in the second images. A pose is estimated of the second camera in response to the second visual features. In response to determining that the second visual features have better sufficiency than the first visual features, content is displayed to have a fixed pose in response to the estimated pose of the second camera.

Abstract: A camera points in a first direction for capturing images of views. Visual features are detected and tracked in the images. A pose is estimated of the camera in response to the tracked visual features. A projector points in a second direction for projecting content to have a fixed pose in response to the estimated pose of the camera.

Abstract: A first camera captures first images of first views. A display device displays the first images on a screen of the display device. A second camera captures second images of second views. Visual features are detected and tracked in the second images. A pose is estimated of the second camera in response to the tracked visual features. On the first images on the screen, content is superimposed to have a fixed pose in response to the estimated pose of the second camera.

Abstract: Systems, methods, and devices relating to the provision of system control support in the form of reactive power support or voltage control support to power transmission or distribution networks using inverter based power generation facilities that are coupled to the power transmission or distribution networks. An inverter based power generation facility, such as a photovoltaic based solar farm or a wind farm, can task all or a portion of its inverter capacity to provide reactive power support or voltage control support to the power transmission or distribution network. This invention applies to the operation of PV solar systems anytime during the day (even during peak power generation times) and other inverter based DGs during the entire 24-hour period. The power generation facility disconnects at least one of its power generation modules from the power transmission or distribution network and makes available required inverter capacity for providing system control support.

Abstract: A method for touch detection is provided that includes receiving an image of an illuminated surface of an optical touch detection system, wherein the image is captured by a camera in the optical touch detection system, identifying highly saturated pixels in the image, identifying a set of candidate touch locations in the image, classifying the candidate touch locations in the set of candidate touch locations to generate a set of validated candidate touch locations, pruning the set of validated candidate touch locations based on the identified highly saturated pixels to generate a set of final touch locations, wherein a validated candidate touch location is not included in the set of final touch locations if the validated candidate touch location corresponds to a highly saturated pixel, and outputting the set of final touch locations.

Abstract: A method for wave gesture detection performed by a touch processor in an optical touch detection system is provided. The method includes receiving a sequence of images of an illuminated surface comprised in the optical touch detection system, wherein the images are captured by a camera comprised in the optical touch detection system, detecting a wave gesture performed in front of the illuminated surface by analyzing the sequence of images, and outputting an indication that a wave gesture has been detected.

Abstract: A method for touch detection performed by a touch processor in an optical touch detection system is provided that includes receiving an image of an illuminated surface included in the optical touch detection system, wherein the image is captured by a camera included in the optical touch detection system, subtracting a background model from the image to generate a mean-subtracted image, identifying a set of candidate touch locations in the mean-subtracted image, classifying the candidate touch locations in the set of candidate touch locations to generate a set of validated candidate touch locations, and outputting a set of final touch locations determined from the set of validated candidate touch locations.

Abstract: A method for enabling physical controls in a digital system is provided that includes receiving an image of an illuminated surface in the digital system, wherein the image is captured by a camera in the digital system, determining a state of a physical control mounted on the illuminated surface by analyzing the image; and outputting an indication of the state of the physical control.

Abstract: A method for touch detection that is performed by a touch processor in an optical touch detection system is provided. The method includes receiving an image of an illuminated surface in the optical touch detection system, wherein the image is captured by a camera in the optical touch detection system, identifying a set of candidate touch locations in the image, classifying the candidate touch locations in the set of candidate touch locations to generate a set of validated candidate touch locations, wherein classifying the candidate touch locations includes using a machine learning classifier to classify each candidate touch location as valid or invalid, wherein the machine learning classifier is trained to classify a candidate touch location based on a combination of features of the candidate touch location, and outputting a set of final touch locations.

Abstract: A method of processing a video sequence is provided that includes receiving a frame of the video sequence, identifying a plurality of blobs in the frame, computing at least one interior point of each blob of the plurality of blobs, and using the interior points in further processing of the video sequence. The interior points may be used, for example, in object tracking.

Abstract: A method of processing a video sequence is provided that includes tracking a first object and a second object for a specified number of frames, determining similarity between a trajectory of the first object and a trajectory of the second object over the specified number of frames, and merging the first object and the second object into a single object when the trajectory of the first object and the trajectory of the second object are sufficiently similar, whereby an accurate location and size for the single object is obtained.

Abstract: A method and apparatus for detecting at least one of a location and a scale of an object in an image. The method comprising distinguishing the trailing and leading edges of a moving object in at least one portion of the image, applying a symmetry detection filter to at least a portion of the image to produce symmetry scores relating to the at least one portion of the image, and identifying at least one location corresponding to locally maximal symmetry scores of the symmetry scores relating to the at least one portion of the image, and utilizing the at least one location of the locally maximal symmetry scores to detect at least one of a location and a scale of the object in the image, wherein the scale relates to the size of the symmetry detection filter.

Abstract: A method of processing a video sequence is provided that includes receiving a frame of the video sequence, identifying a plurality of blobs in the frame, computing at least one interior point of each blob of the plurality of blobs, and using the interior points in further processing of the video sequence. The interior points may be used, for example, in object tracking.

Abstract: A method and apparatus for depth-fill algorithm for low-complexity stereo vision. The method includes utilizing right and left images of a stereo camera to estimate depth of the scene, wherein the estimated depth relates to each pixel of the image, and updating a depth model with the current depth utilizing the estimated depth of the scene.

Abstract: A method of analyzing a depth image in a digital system is provided that includes detecting a foreground object in a depth image, wherein the depth image is a top-down perspective of a scene, and performing data extraction and classification on the foreground object using depth information in the depth image.

Abstract: A method of processing a digital video sequence is provided that includes detecting a foreground object in an image captured by a depth camera, determining three-dimensional (3D) coordinates of the foreground object, and comparing the 3D coordinates to a 3D video tripwire to determine if the foreground object has crossed the 3D video tripwire. A method of defining a 3D video tripwire is also provided.

Abstract: A method of clutter elimination in digital images is provided that includes identifying a foreground blob in an image, determining a depth of the foreground blob, and indicating that the foreground blob is clutter when the depth indicates that the foreground blob is too close to be an object of interest. Methods for obstruction detection in depth images such as those captured by stereoscopic cameras and structured light cameras are also provided.