Method, device and system for sensing depth of symbol array surface structured light

Abstract

The invention discloses a method, a device and a system for sensing depth of symbol array surface structured light. The method comprises the following steps: using a laser pattern projector for projecting a coding pattern composed of symbol arrays to a target object or a projection space; using an image sensor for acquiring and obtaining a continuous input symbol coding pattern sequence, firstly decoding an input symbol coding pattern and then performing symbol matching calculation on a symbol-identified input symbol decoding pattern and a distance-known reference symbol decoding pattern to obtain an optical parallax value, wherein a decoding process comprises pretreatment, symbol location, symbol identification and symbol correction; generating depth point cloud information of the target object or the projection space presented in grid forms in combination with a depth calculation formula. The method, the device and the system disclosed by the invention can be used for rapidly acquiring high-resolution and high-precision depth information of the target object or the projection space in a dynamic scene and providing convenience for implanting or embedding a module mode into intelligent equipment so as to realize three-dimensional modeling, three-dimensional map generation and the like.

Description

technical field [0001] The invention belongs to the technical fields of pattern recognition, human-computer interaction, three-dimensional reconstruction and machine vision, and in particular relates to a method, device and system for depth perception of symbol array surface structured light. Background technique [0002] In the field of consumer electronics, depth perception technology helps to improve the intelligence level and interaction capabilities of electronic products, helps smart terminals understand human actions, and becomes one of the means of interaction between the "real physical world" and the "virtual network world". , smart phones, home appliances, tablet PCs and other fields to achieve innovative applications, and can also be used in intelligent video surveillance, facial recognition systems, 3D animation production, dynamic scene detection, 3D map real-time generation and other 3D reconstruction occasions. In the industrial field, high-resolution, high-pr...

AI Technical Summary

Problems solved by technology

However, it is difficult to obtain high-resolution and high-precision depth information by generating laser speckle images through DoE diffraction to obtain depth information, and it is difficult to meet the application requirements of industrial modeling and other fields, and it does not have the ability of self-depth correction.

At the same time, the existing structured light coding depth perception and three-dimensional measurement technology is difficult to obtain high-resolution and high-precision depth information of target objects in dynamic scenes in real time.

Images