A mobile terminal including a display configured to display a rotatable graphic interface; a Time of Flight (TOF) camera configured to obtain a depth image of an object; and a controller configured to control the TOF camera to enter a rotation detection mode based on the object included the depth image, obtain a relative rotation amount of a plurality of specific points of the object included in the depth image, and rotate the graphic interface on the display based on the obtained relative rotation amount.

Methods, devices, systems and computer software/program code products improve the reliability of scene reconstruction through the use of a persistent store or cache to retain scene information observed across one or more previous frames.

Methods, devices, systems and computer software/program code products improve the reliability of scene reconstruction through the use of a persistent store or cache to retain scene information observed across one or more previous frames.

An augmented reality, AR, system (100) for use in a medical procedure is disclosed. The AR system (100) comprises an AR headset (2), and a processor (12). The AR headset (2) comprises a camera (6a, 6b), a near eye display (4a, 4b) and a depth sensor (10a, 10b). The processor (12) is configured to adjust the position of the image obtained by the camera (6a, 6b) on the display (4a, 4b) throughout the medical procedure based on changes in the distance measured by the depth sensor (10a, 10b).

Disclosed in an embodiment is a camera module comprising: a housing; a lens module coupled to the housing; a holder disposed in the housing; an elastic member connecting the housing and the holder; a magnet part and an optical member that are coupled to the holder; and a coil part facing the magnet part, wherein the holder includes a first protrusion that extends in an optical axis direction so as to be coupled to the elastic member, and the elastic member includes a first coupling portion coupled to one surface of the first protrusion; the first protrusion includes a guide protrusion which protrudes from the one surface of the first protrusion in the optical axis direction, wherein the guide protrusion is disposed outside the elastic member and has a shape corresponding to at least a portion of the outer circumference of the first coupling portion.

Embodiments generally relate to a machine-implemented method of automatically adjusting the range of a depth data recording executed by at least one processing device. The method comprises determining, by the at least one processing device, at least one positions of a subject to be recorded; determining, by the at least one processing device, at least one spatial range based on the positions of the subject; receiving depth information; and constructing, by the at least one processing device, a depth data recording based on the received depth information limited by the at least one spatial range.

Embodiments generally relate to a machine-implemented method of automatically adjusting the range of a depth data recording executed by at least one processing device. The method comprises determining, by the at least one processing device, at least one positions of a subject to be recorded; determining, by the at least one processing device, at least one spatial range based on the positions of the subject; receiving depth information; and constructing, by the at least one processing device, a depth data recording based on the received depth information limited by the at least one spatial range.

A method for hand pose identification in an automated system includes providing map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.

A method for hand pose identification in an automated system includes providing map data of a hand of a user to a first neural network trained to classify features corresponding to a joint angle of a wrist in the hand to generate a first plurality of activation features and performing a first search in a predetermined plurality of activation features stored in a database in the memory to identify a first plurality of hand pose parameters for the wrist associated with predetermined activation features in the database that are nearest neighbors to the first plurality of activation features. The method further includes generating a hand pose model corresponding to the hand of the user based on the first plurality of hand pose parameters and performing an operation in the automated system in response to input from the user based on the hand pose model.

A digital photographing apparatus is provided. The digital photographing apparatus includes a first optical system configured to acquire a wide-angle image including a subject, a second optical system configured to acquire a telephoto image with the subject zoomed, and a processor configured to determine whether to generate a synthesized image of the wide-angle image and the telephoto image based on one or more of an illuminance of the subject and a distance between the digital photographing apparatus and the subject.