Face detection, poses estimation and estimation of a distance from a camera with the use of an individual network

摘要

An apparatus, comprising:- Means for picking up of at least one image with the use of a camera, which is arranged on a device, the apparatus comprising a computer processor and a memory, wherein the at least one image comprises an image, which was taken up during subjects in the image with an illumination, which is arranged on the device, were illuminated;- Means for encoding, with the use of a coding module, which is arranged on the device, of the at least one image in order to produce the feature vectors, which features of patients in the image in a feature space define, wherein the feature space a plurality of regions, wherein each feature vector features for a region in the feature space defined;- Means for judging, of the produced feature vectors for each region in the feature space with the use of the computer processor, in order to determine whether a face is present in the region;- wherein, if the face is determined to be in the region, one or more properties of the face in the region to be assessed, wherein at least one of the properties of a distance from the camera from the face is in the region; and- Means for providing an output of the processor, if the face is present in the region, wherein the output, an indication that the face is present in the region, the estimated position of the face relative to the center of the region, the estimated pose of the face in the region, and the estimated distance from the camera from the face in the region.