CPC Class H04N

A method comprising: automatically processing recorded first sensor data from a scene to recognise automatically a first user input from user action in the scene; in response to recognition of the first user input, automatically entering a learning state to enable: automatic processing of the first sensor data from the scene to capture an ad-hoc sequence of spatial events in the scene subsequent to the first user input and automatic processing of subsequently recorded second sensor data from the scene different to the first sensor data of the scene, to recognise automatically a sequence of spatial events in the subsequently recorded second video corresponding to the captured sequence of spatial events.

Disclosed herein are a method and a device for surveilling an abnormal behavior using 3D image information. The surveilling device converts depth information, which is the 3D image information, into a real world coordinate and uses the real world coordinate to calculate a plane reference distance value. The surveilling device uses the plane reference distance value to generate a background model and compares the background model with the plane reference distance value of a current image to detect a region of interest. Further, the surveilling device extracts the 3D feature information of the region of interest to determine an abnormal behavior of an object.

In some embodiments, systems, apparatuses, and methods are described herein including a shelf assembly that utilizes the accumulated weight of products stocked thereon to compress a compression member disposed within the assembly. An electronic imaging device can be mounted proximate to the assembly and can be oriented to capture an image of the compression member to determine whether a particular shelf needs to be restocked and avoid having to manipulate or remove products from a shelf to determine a current stock level.

Disclosed is an optical unit wherein a rotating reflector rotates about a rotation axis in one direction, while reflecting light emitted from a light source. The rotating reflector is provided with a reflecting surface such that the light reflected by the rotating reflector, while rotating, forms a desired light distribution pattern, said light having been emitted from the light source. The light source is composed of light emitting elements. The rotation axis is provided within a plane that includes an optical axis and the light source. The rotating reflector is provided with, on the periphery of the rotation axis, a blade that functions as the reflecting surface.

A method and/or system is able to provide driver fingerprint via metadata extraction managed by a driver rating (“DR”) model trained by a machine learning center (“MLC”) coupled to a cloud based network (“CBN”). In one embodiment, a DR system includes a set of outward facing cameras, a set of inward facing cameras, and a vehicle onboard computer (“VOC”). The set of outward facing cameras mounted on a vehicle is used to collect external images representing a surrounding environment in which the vehicle operates. The set of inward facing cameras mounted in the vehicle is used to collect internal images including operator body expression representing at least operator's attention. The VOC is configured to determine the identity of operator and current operating style in response to the collected internal images, the collected external images, and historical stored data.

A security camera system capable of reducing an amount of information without degrading useful information is provided. The security camera system includes a pixel array, an image signal processor that performs various types of image processing on raw data including each pixel value from the pixel array, and a pre-stage processing unit arranged between the pixel array and the image signal processor. The pre-stage processing unit includes an important area extraction circuit that receives raw data from the pixel array with respect to each frame and divides an effective pixel area of the frame into an important area and an unimportant area, and transmits the raw data of the important area to the image signal processor.

The purpose of the present invention is to create a color conversion table with good gradation using a plurality of inks from a printer. Provided is a method for creating a color conversion table, the method comprising: a virtual color value determination process in which a plurality of virtual color values at a lattice point in a color conversion table in a virtual color space are determined; and an ink amount determination process in which a combination of ink amounts at the lattice point in the color conversion table is determined on the basis of a predetermined conversion coefficient and the virtual color values. At least one of the virtual color value determination process and the ink amount determination process is executed using a cubic spline function that is defined from the plurality of virtual color values or the ink amounts.