Abstract:
There is provided a method for automatically altering a digital video stream including multiple video input frames, to automatically obtain output frames with a target composition, in which frame metadata relating to objects in one or more of the video input frames is analysed on a frame-by-frame basis and used by a processor to automatically alter one or more output frames to be more similar to, or to match, the target composition, wherein cropping is performed in 3D. A related system and a related computer program product are also provided.
Abstract:
Tracking pose of an articulated entity from image data is described, for example, to control a game system, natural user interface or for augmented reality. In various examples a plurality of threads execute on a parallel computing unit, each thread processing data from an individual frame of a plurality of frames of image data captured by an image capture device. In examples, each thread is computing an iterative optimization process whereby a pool of partially optimized candidate poses is being updated. In examples, one or more candidate poses from an individual thread are sent to one or more of the other threads and used to replace or add to candidate poses at the receiving thread(s).
Abstract:
An object detection apparatus includes a light illumination unit that emits illuminating light; an imaging unit that captures a first image of distant photographic subjects by detecting lights from the photographic subjects, captures a second image of foreign matter attached to a monitoring area by detecting the illuminating light reflected from the foreign matter, and generates an image frame; a target detection unit that detects a detection target among the distant photographic subjects based on the first image; a foreign matter detection unit that detects the foreign matter based on the second image; and an exposure amount change unit that changes an exposure amount of the imaging unit. The target detection unit detects the detection target using plural imaging frames with different exposure amounts. The foreign matter detection unit detects the foreign matter using the imaging frame other than the imaging frame with the greatest exposure amount.
Abstract:
Various methods for monitoring a target user by a drone include tracking the target user by the drone, detecting an object in the presence of the target user based on one or more detection criteria, determining whether the object is a potential threat to the target user based on one or more threat criteria, determining whether to notify the third party of the potential threat to the target user based on one or more notification criteria in response to determining that the object is a potential threat, notifying the third party of the potential threat to the target user in response to determining that the third party should be notified, receiving a response from the third party including a command, and performing an action based on the command.