Object-centric monocular panoramic stereo vision sensor

A stereo vision and sensor technology, applied in the field of object-centered monocular panoramic stereo vision sensor, can solve the problems of poor practicability, high computational complexity, difficult maintenance and use, etc.

CN102980513BActive Publication Date: 2016-01-20ZHEJIANG UNIV OF TECH
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2016-01-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A monocular panoramic three-dimensional vision sensor focusing on objects comprises a visual detection box and a micro processor, wherein the visual detection box is used for shooting a to-be-reconstructed object, and the micro processor is used for carrying out image processing to the to-be-reconstructed object, reconstructing the object in a three-dimensional mode and outputting reconstruction results. The micro processor comprises an image reading module, a sensor calibration module, an image processing module, a three-dimensional reconstruction module and a result output module, and the image processing module is used for segmenting an image taken directly about the to-be-reconstructed object and a reflected image from an ellipsoidal mirror about the to-be-constructed object from a picture, carrying out perspective projection transformation processing to the reflected image from the ellipsoidal mirror about the to-be-reconstructed object, and obtaining a top view of a horizontal projection plane and four types of basic views, namely a main view, left side view, a right side view and a rear view. The three-dimensional reconstruction module is used for reconstructing a real shape of the to-be-reconstructed object based on corresponding relations, including 'the length in the main view needs to be aligned with the length in the top view, the height in the main view needs to be aligned with the height in the left side view and the height in the left side view, and the width in the top view needs to be the same as the width of the left side view and the width in the right side view', among the basis views. The monocular panoramic three-dimensional vision sensor focusing on the objects is high in practicability, low in calculation resource consumption, simple and reliable in hardware, great in real-time processing ability and convenient to maintain and use.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the application of optical technology and computer vision technology in stereo vision measurement. Background technique

[0002] Binocular stereo vision 3D measurement and stereo reconstruction technology based on computer vision is an emerging application technology with great development potential and practical value, which can be widely used in industrial inspection, geographical survey, medical cosmetic surgery, orthopedic orthopedics, Reproduction of cultural relics, criminal investigation and evidence collection, security identification, robot vision, rapid prototyping of molds, gifts, virtual reality, animated films, games and many other application fields.

[0003] The basic principle of stereo vision is to observe the same scene from two viewpoints to obtain perceptual images under different viewing angles, and calculate the position deviation between image pixels, that is, parallax, through the principle of triangulat...

Examples

Embodiment 1

[0057] refer to Figure 1 to Figure 6, an object-centric monocular panoramic stereo vision sensor, including a visual detection box for photographing the reconstructed object, microprocessing for image processing, three-dimensional reconstruction and reconstruction result output of the reconstructed object device;

[0058] The visual inspection box includes: an ellipsoidal mirror used to reflect the shape of the reconstructed object from different angles of view, an upper cover for fixing the camera and an LED light source and forming a closed detection space with the ellipsoidal mirror, for A support pole supporting the object to be reconstructed, a camera for photographing the shape of the object to be reconstructed, an LED light source for providing illumination for the visual inspection box; the camera is embedded in the upper center of the upper cover, and the The LED light source is embedded near the upper center of the upper cover, and the LED light source is inclined ...