Speckle pattern-based structured light camera row deviation automatic detection method and device

Abstract

The embodiment of the invention provides a speckle pattern-based structured light camera row deviation automatic detection method and device. The method comprises the following steps: extracting a speckle pattern of a test object as a test pattern; extracting a depth map and a saliency map corresponding to the test map; further determining a saliency mask corresponding to the saliency map; processing the saliency mask through flooding filling to obtain an extended saliency mask used for identifying an extended salient region in the saliency map; determining that the total number of the pixel points with the depth values in the corresponding region of the depth map in the extended salient region of the extended saliency mask identifier is the effective number of the depths; and finally, judging whether the structured light camera to be detected has row deviation or not based on the effective number of the depths and the total number of the pixel points in the extended salient region. According to the method and the device provided by the embodiment of the invention, whether a test speckle pattern shot by a to-be-tested structured light camera has the row deviation or not can be quickly and automatically detected, and time delay caused by re-calibration when the camera is used each time is avoided.

Description

technical field [0001] The present invention relates to the technical field of structured light cameras, in particular to an automatic detection method and device for line deviation of structured light cameras based on speckle patterns. Background technique [0002] Since the successful integration of depth cameras into mobile phones, depth cameras capable of recovering 3D information have gradually emerged in various consumer applications. According to the working principle of depth recovery, depth cameras can be divided into binocular depth cameras, TOF (time offly) depth cameras and structured light cameras. Among them, the structured light camera has been more applied because of its strong anti-interference and moderate cost. [0003] The depth recovery part of the structured light camera is usually composed of an infrared speckle projector and an infrared camera. Before recovering the depth, it is first necessary to solve the parameters of the camera, and then shoot a ...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a method and device for automatic detection of line deviation of a structured light camera based on a speckle pattern, to solve the problem of recalibrating the distance between the infrared speckle projector and the infrared camera before using the existing structured light camera. The cumbersome position and posture relationship brought by the camera, the time delay when the camera needs to be put into use

Images