A Flexible New Technique for Camera Calibration

By Zhengyou Zhang. 2000

15,685 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Detection and Continual Learning of Novel Face Presentation Attacks (2021, methodology): “To enable face detection in all captured frames, we use a standard calibration process using checkerboards [13].”
Simitate: A Hybrid Imitation Learning Benchmark (2019, neutral): “The transformation between the centroid of the RGB-D camera’s rigid body and optical center of the RGB-D camera are then estimated [46].”
Microsoft Kinect Sensor and Its Effect (2012, methodology): “The idea is an adaptation of my earlier camera calibration technique.(2) The depth value produced by the Kinect sensor is assumed to be an affine transformation [3B2-9] mmu2012020004.”
The Digital Emily project: photoreal facial modeling and animation (2009, neutral): “2007] involving image ratios, we can derive the reflection vector at each pixel, and from the camera orientations (calibrated with the technique of [Zhang 2000]) we also know the view vector.”
The Grid Method for In‐plane Displacement and Strain Measurement: A Review and Analysis (2016, background): “Several parametric models for geometric distortions are available in the literature, see, for instance, [183] or [184] where algorithms for parameter estimation are also proposed.”
Software techniques for two- and three-dimensional kinematic measurements of biological and biomimetic systems (2008, background): “Camera calibration is an active area of research within the computer vision community, with most efforts devoted towards rapid self-calibration of off-the-shelf cameras with little spatial separation between the cameras (e.g. Heikkila and Silven 1997, Zhang 2000).”
A cooperative perception system for multiple UAVs: Application to automatic detection of forest fires (2006, methodology): “This model is obtained through calibration for all the cameras, using the algorithm developed by Zhang (2000).”
Infrared Thermography for Temperature Measurement and Non-Destructive Testing (2014, background): “This issue has been widely dealt with in the image processing field applied to traditional cameras [82,83].”
The leaf angle distribution of natural plant populations: assessing the canopy with a novel software tool (2015, methodology): “The target calibration estimates camera geometries (intrinsics) and the geometry of the stereo rig (extrinsics) using a regular calibration pattern [31,38,39].”
ToxTrac: A fast and robust software for tracking organisms (2017, methodology): “ processed video frames (assumed to be equal for every sequence) Analysed Video Time 900 (Analysed Video Frames)/ (Video Framerate) Arena 1 Arena1 [0, 0] [990.332, 0], [0, 991.625] [990.332, 991.625] [0, 0, 1] [287.538, 0, 1] [0, 282.707, 1] [287.538, 282.707, 1] Arena number and arena name. Corners”
Using plane + parallax for calibrating dense camera arrays (2004, methodology): “We used a multi-camera version of Zhang’s algorithm [18].”
Learning to Recover 3D Scene Shape from a Single Image (2020, methodology): “Traditional methods utilize reference objects such as a planar calibration grids [51] or vanishing points [9], which can then be used to estimate a focal length.”
Kinect range sensing: Structured-light versus Time-of-Flight Kinect (2015, methodology): “In order to re-project the range values into 3D-space, we first estimated the camera intrinsics using the well known photometric calibration technique from [57].”
DPOD: 6D Pose Object Detector and Refiner (2019, methodology): “The 6D pose is then estimated using the Perspective-n-Point (PnP) [36] pose estimation method that estimates the camera pose given correspondences and intrinsic parameters of the camera.”
A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses (2006, methodology): “Thus, we use the singular value decomposition to compute the closest orthogonal matrices in the sense of Frobenius norm [19] and use them as initial guess for each Rj.”