• Corpus ID: 7263887

Surveillance Camera Autocalibration based on Pedestrian Height Distributions

  title={Surveillance Camera Autocalibration based on Pedestrian Height Distributions},
  author={Jingchen Liu and Robert T. Collins and Yanxi Liu},
We propose a new framework for automatic surveillance camera calibration by observing videos of pedestrians walking through the scene. Unlike existing methods that require accurate pedestrian detection and tracking, our method takes noisy foreground masks as input and automatically estimates the necessary intrinsic and extrinsic camera parameters using prior knowledge about the distribution of relative human heights. Our algorithm is computationally efficient enough for online parameter… 

Figures and Tables from this paper

Robust autocalibration for a surveillance camera network
This work proposes a novel approach for multi-camera autocalibration by observing multiview surveillance video of pedestrians walking through the scene and relies on a joint optimization framework with robust statistics to achieve accurate calibration under challenging scenarios.
Camera parameters estimation from pose detections
This work proposes a method for camera focal length, location and orientation estimation by observing human poses in the scene and shows that even being trained only on synthetic dataset, the proposed method outperforms known solution.
4-D Scene Alignment in Surveillance Video
This paper presents an automatic camera calibration process that provides a mechanism to reason about the spatial proximity between objects at different times and is robust to individual height variations and camera parameter estimation errors.
This paper proposes a novel method for camera pose estimation based on people observation in the input video captured by static camera that can deal with false positive detections and inaccurate localization results.
Fully Automatic Horizon Estimation for Surveillance Cameras
  • Vojtech Bartl, A. Herout
  • Computer Science
    2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
  • 2017
It turns out that the algorithm is on par with humans or it outperforms them in the difficult scenes.
Pedestrian-Based Variational Bayesian Self-Calibration of Surveillance Cameras
A probabilistic model is constructed that takes into account uncertainties in both the foot/head locations and the pedestrian heights, using foot-head homology and makes it possible to estimate the height of pedestrians and to obtain accurate camera parameters simultaneously.
Automatic Extrinsic Calibration of Camera Networks Based on Pedestrians
A novel accurate and fully automatic extrinsic calibration framework for camera networks with partially overlapping views based on the analysis of pedestrian tracks without other calibration objects is proposed, which can obtain the triangulation error of a few centimeters.
Automatic Multi-Camera Extrinsic Parameter Calibration Based on Pedestrian Torsors †
A novel, accurate and fully automatic extrinsic calibration framework for camera networks with partially overlapping views that detects human poses in the camera images and then models walking persons as vertical sticks and a novel method to calibrate the camera network by only using the top and centerline of a person when the bottom of the person is not available in heavily occluded scenes.
Automatic Calibration of Stationary Surveillance Cameras in the Wild
This paper presents the first combination of several existing components of calibration systems from literature, including a fully automatic camera calibration algorithm for monocular stationary surveillance cameras, and introduces novel pre- and post-processing stages that improve estimation of the horizon line and the vertical vanishing point.
Object Occlusion Detection Using Automatic Camera Calibration for a Wide-Area Video Surveillance System
An object occlusion detection algorithm using object depth information that is estimated by automatic camera calibration that can be applied to improve the performance of object tracking and object recognition algorithms for video surveillance systems.


Trajectory Rectification and Path Modeling for Video Surveillance
A novel linear solution to auto-calibrate any camera observing pedestrians and to use these calibrated cameras to detect unusual object behavior and test the proposed method on synthetic as well as on real-world pedestrian sequences.
Simultaneous surveillance camera calibration and foot-head homology estimation from human detections
  • B. Micusík, T. Pajdla
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
It is demonstrated that human body can be considered as a calibration target thus avoiding special calibration objects or manually established fiducial points, and a new constraint is derived which allows the calibration of internal and external camera parameters as a Quadratic Eigenvalue Problem.
Bayesian autocalibration for surveillance
A method for camera autocalibration based on information gathered by tracking people is developed and a Bayesian solution to the calibration problem is presented that can elegantly handle measurement uncertainties, outliers, as well as prior information.
Camera calibration from video of a walking human
A self-calibration method to estimate a camera's intrinsic and extrinsic parameters from vertical line segments of the same height is presented. An algorithm to obtain the needed line segments by
What Can Casual Walkers Tell Us About The 3 D Scene
An approach for incremental learning of the 3D scene from a single static video camera is presented, exploiting the presence of casual people walking in the scene to infer relative depth, learn shadows, and segment the critical ground structure.
Crowd Detection with a Multiview Sampler
A set of novel proposals that leverage multiview geometry to propose global moves that jump more efficiently between modes of the posterior distribution of a posterior distribution for detecting and counting people in crowds are developed.
Combining scene and auto-calibration constraints
A simple approach to combining scene and auto-calibration constraints for the calibration of cameras from single views and stereo pairs and examples of various cases of constraint combination and degeneracy as well as computational techniques are presented.
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Single View Metrology
An algebraic representation is developed which unifies the three types of measurement and permits a first order error propagation analysis to be performed, associating an uncertainty with each measurement.
Model acquisition using stochastic projective geometry
This thesis presents a methodology for scene reconstruction that is based on the principles of projective geometry, while dealing with uncertainty at a fundamental level. Uncertainty in geometric