G06V 10/10

Definition

(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)

The process of acquiring still images or video sequences for the purpose of subsequently recognising patterns in the acquired images.

Image capturing arrangements which visually emphasise those features of the objects that are relevant to the pattern recognition process.

Optimising the image capturing conditions, such as correctly placing the object with respect to a camera, choosing the right moment for triggering the image sensor, or suitably setting the parameters of the image sensor.

Devices for image acquisition including sensors that generate a conventional two-dimensional image irrespective of its nature (e.g. grey level image, colour image, infrared image, etc.), a three-dimensional point cloud, a sequence of temporally-related images, or a video.

Notes – other classification places

Constructional details of the image acquisition arrangements are covered by a hierarchy of subgroups branching from group G06V 10/12:

• Group G06V 10/14 covers the design of the optical path, including the light source (if any), the different optical elements such as lenses, prisms, mirrors, apertures/diaphragms, filters, the individual optical characteristics of these elements (e.g. refraction indices, focal lengths, chromatic aberrations, or distortions), and their optical arrangement;
• Group G06V 10/141 covers the control of the illumination, e.g. strategies for activating additional light sources if the ambient lighting is insufficient for a reliable pattern recognition or if individual facets of an object are obstructed by shadows;
• Group G06V 10/143 covers processes or devices which emit or sense radiation in different parts of the electromagnetic spectrum (e.g. infrared light, the visual spectrum, and ultraviolet light) so as to obtain a comprehensive set of sensor readings, which when combined facilitate an automated distinction of different kinds of objects. For example, an infrared image could be used for isolating living bodies from the background to analyse the presence of a living body in a second image modality, like an RGB image, the second image being aligned with the infrared image. The images captured in infrared could be used for night vision, e.g. detecting pedestrians or animals for collision avoidance. Sensors using multiple wavelengths are also typically used in remote sensing (e.g. when detecting different kinds of crops, forests, lakes, rivers, or urban areas in multispectral or hyperspectral satellite imagery; see also group G06V 20/13);
• Group G06V 10/145 covers illumination arrangements which are specially adapted to increase the reliability of the pattern recognition process. For example, mitigating shadow artefacts, which are likely to deteriorate the pattern recognition process, by providing specially designed arrangements of light sources (light domes, softboxes, ring flashes, etc). The pattern recognition process can also be supported by means of a structured light projector, which projects specific patterns (e.g. stripes or fringe patterns) on to the object so as to augment the two-dimensional image data with three-dimensional information and for this purpose, additional optical elements such as gratings or filter masks may be added to the illumination system. These various special illumination arrangements are also commonly used for recognising patterns in microscopic imagery (see also group G06V 20/69);
• Group G06V 10/147 covers technical details of the image sensor, such as the sensor technology (photodiodes, CCD, CMOS etc.), the size and the geometrical distribution of light receiving elements on the sensor surface, or the presence of additional optical elements on the sensor (e.g. micro-lenses, diaphragms, collimators or coded aperture masks).

Examples

Illumination by casting infra-red (IR) light onto a person to highlight regions of a hand, to assist in gesture recognition

Beziehungen zu anderen Klassifikationsstellen

CCTV and image transmission systems are classified in group H04N 7/00.

Querverweise

Einschränkende Querverweise

Nichteinschränkende Querverweise in anwendungsorientierte Klassifikationsstellen

Informative Querverweise

Glossar