Abstract: The present invention proposes to analyze movements of objects in video sequences (e.g. sport videos), by performing motion estimation to determine motion vectors at each frame. With the calculated motion vectors, the movements of the object(s) (e.g. athlete(s)) can be quantitatively measured. Based on this, movements in two videos can be compared at each individual frame of the video sequence. Different approaches (e.g., color coding) can be used to visualize and compare the movements. With motion estimation, intermediate frames can also be inserted to enable better movement comparison in two given videos.

Abstract: The present invention relates to a device (8) for determining tissue layer boundaries of a body (14), comprising a probe (10) for acquiring (S12) two or more ultrasound images (36) at adjacent positions of a surface (12) of the body (14), a converter (44) for converting (S14) said ultrasound images (36) separately to depth signals (46), wherein a depth signal (46) is obtained by summing intensities of one of said ultrasound images (36) along a line (66) of substantially constant depth in the body (14), a detector (48) for detecting (S16) a set of candidate tissue layer boundaries (50) for an ultrasound image (36) by thresholding the depth signal (46) obtained for said ultrasound image (36), a selection means (52) for selecting (S18) from a set of candidate tissue layer boundaries (50) a nearest candidate tissue layer boundary (54) that is nearest to the surface (12) of the body (14), and a processing means (56) for determining (S20) an actual tissue layer boundary (58) from the nearest candidate tissue layer

Abstract: The invention provides a system (102) for accurately detecting a patient's (114) movement during imaging procedures. The system comprises a camera (126) for providing a stream of camera images of a part of a patient's exterior (206). The system (102) furthermore comprises a fiducial element (116), which fiducial element (116) is mountable on said part of the patient's exterior (206), and which fiducial element (116) is detectable in the stream of camera images, and an image processor (128) for detecting a displacement of the fiducial element based on consecutive camera images comprised in at least the stream of camera images and for generating an output signal (129) indicative for said displacement. Herein, the fiducial element (116) has an in-plane stiffness which is substantially larger than an in-plane stiffness of said part of the patient's exterior. In addition, the fiducial element (116) and said part of the patient's exterior are provided with substantially equal outer in-plane dimensions.

Abstract: This invention relates to a method of selecting an optimal viewing angle position for a camera. A first quantitative score is determined for a first viewing angle position of the camera using pre-selected regions of interest as reference areas, the determining being performed in accordance to a pre-defined quantitative score rule. The angle position is adjusted from the first viewing angle position towards at least one second viewing angle position. For each at least one second viewing angle position a second quantitative score is determined in accordance to the pre-defined quantitative score rule, and finally a target viewing angle position is determined based on the determined quantitative scores.