Abstract: An object location method includes: analysing data including plural objects each including plural features, and extracting the features from the data; matching features stored in a database with those extracted from the data, and deriving a prediction of the object, each feature extracted from the data providing a vote for at least one prediction; expressing the prediction to be analysed in a Hough space, the objects to be analysed being described by n parameters and each parameter defining a dimension of the Hough space, n is an integer of at least one; providing a constraint by applying a higher weighting to votes which agree with votes from other features than those votes which do not agree with votes from other features; finding local maxima in the Hough space using the weighted votes; and identifying the predictions associated with the local maxima to locate the objects provided in the data.

Abstract: A method of comparing two object poses, wherein each object pose is expressed in terms of position, orientation and scale with respect to a common coordinate system, the method comprising: calculating a distance between the two object poses, the distance being calculated using the distance function: d sRt ? ( X , Y ) = d s 2 ? ( X , Y ) ? s 2 + d r 2 ? ( X , Y ) ? r 2 + d t 2 ? ( X , Y ) ? t 2 .

Abstract: A system for capturing 3D image data of a scene, including three light sources, each configured to emit light at a different wavelength to the other two sources and to illuminate the scene to be captured; a first video camera configured to receive light from the light sources which has been reflected from the scene, to isolate light received from each of the light sources, and to output data relating to the image captured for each of the three light sources; a depth sensor configured to capture depth map data of the scene; and an analysis unit configured to receive data from the first video camera and process the data to obtain data relating to a normal field obtained from the images captured for each of the three light sources, and to combine the normal field data with the depth map data to capture 3D image data of the scene.

Abstract: A method dividing an image into plural superpixels of plural pixels of the image. The method calculates an initial set of weights from a measure of similarity between pairs of pixels, from which a resultant set of weights is calculated for pairs of pixels that are less that a threshold distance apart on the image. The calculation calculates a weight for a pair of pixels as the sum over a set of third pixels of the product of initial weight of the first pixel of the pair of pixel with the third pixel and the weight of the third pixel with the second pixel. Each weight is then subjected to a power coefficient operation. The resultant set of weights and the initial set of weights are then compared to check for convergence. If the weights converge, the converged set of weights is used to divide the image into superpixels.

Abstract: A moving feature is recognized in a video sequence by comparing its movement with a characteristic pattern. Possible trajectories through the video sequence are generated for an object by identifying potential matches of points in pairs of frames of the video sequence. When looking for the characteristic pattern, a number of possible trajectories are analyzed. The possible trajectories may be selected so that they are suitable for analysis. This may include selecting longer trajectories that can be easier to analyze. Thereby where the object being tracked is momentarily behind another object a continuous trajectory is generated.

Abstract: A characteristic motion in a video is identified by determining pairs of moving features that have an indicative relationship between the motions of the two moving features in the pair. For example, the motion of a pedestrian is identified by an indicative relationship between the motions of the pedestrian's feet. This indicative relationship may be that one of the feet moves relative to the surroundings while the other remains stationary.

Abstract: According to one embodiment, a method of classifying a feature in a video sequence includes selecting a target region of a frame of the video sequence, where the target region contains the feature; dividing the target region into a plurality cells, calculating histograms of optic flow with the cells comparing the histograms of optic flow for pairs of cells; and assigning the feature to a class based at least in part on the result of the comparison.