Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dive Deeper into Rectifying Homography for Stereo Camera Online Self-Calibration

Hongbo Zhao, Yikang Zhang, Qijun Chen, Rui Fan

TL;DR

This paper first delve deeply into the concept of rectifying homography, which serves as the cornerstone for the development of the novel stereo camera online self-calibration algorithm, for cases where only a single pair of images is available.

Abstract

Accurate estimation of stereo camera extrinsic parameters is the key to guarantee the performance of stereo matching algorithms. In prior arts, the online self-calibration of stereo cameras has commonly been formulated as a specialized visual odometry problem, without taking into account the principles of stereo rectification. In this paper, we first delve deeply into the concept of rectifying homography, which serves as the cornerstone for the development of our novel stereo camera online self-calibration algorithm, for cases where only a single pair of images is available. Furthermore, we introduce a simple yet effective solution for global optimum extrinsic parameter estimation in the presence of stereo video sequences. Additionally, we emphasize the impracticality of using three Euler angles and three components in the translation vectors for performance quantification. Instead, we introduce four new evaluation metrics to quantify the robustness and accuracy of extrinsic parameter estimation, applicable to both single-pair and multi-pair cases. Extensive experiments conducted across indoor and outdoor environments using various experimental setups validate the effectiveness of our proposed algorithm. The comprehensive evaluation results demonstrate its superior performance in comparison to the baseline algorithm. Our source code, demo video, and supplement are publicly available at mias.group/StereoCalibrator.

Dive Deeper into Rectifying Homography for Stereo Camera Online Self-Calibration

TL;DR

This paper first delve deeply into the concept of rectifying homography, which serves as the cornerstone for the development of the novel stereo camera online self-calibration algorithm, for cases where only a single pair of images is available.

Abstract

Accurate estimation of stereo camera extrinsic parameters is the key to guarantee the performance of stereo matching algorithms. In prior arts, the online self-calibration of stereo cameras has commonly been formulated as a specialized visual odometry problem, without taking into account the principles of stereo rectification. In this paper, we first delve deeply into the concept of rectifying homography, which serves as the cornerstone for the development of our novel stereo camera online self-calibration algorithm, for cases where only a single pair of images is available. Furthermore, we introduce a simple yet effective solution for global optimum extrinsic parameter estimation in the presence of stereo video sequences. Additionally, we emphasize the impracticality of using three Euler angles and three components in the translation vectors for performance quantification. Instead, we introduce four new evaluation metrics to quantify the robustness and accuracy of extrinsic parameter estimation, applicable to both single-pair and multi-pair cases. Extensive experiments conducted across indoor and outdoor environments using various experimental setups validate the effectiveness of our proposed algorithm. The comprehensive evaluation results demonstrate its superior performance in comparison to the baseline algorithm. Our source code, demo video, and supplement are publicly available at mias.group/StereoCalibrator.
Paper Structure (11 sections, 22 equations, 4 figures, 2 tables)

This paper contains 11 sections, 22 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Methodology
  4. Dive deeper into rectifying homography
  5. Energy function and its solution for single-pair cases
  6. Global optimization for multi-pair cases
  7. Experimental Results
  8. Experiment setup and implementation details
  9. Evaluation metrics
  10. Comprehensive performance evaluation
  11. Conclusion

Figures (4)

  • Figure 1: The experimental setup with the left camera mounted at five different viewpoints.
  • Figure 2: Comparison between ling2016high and our proposed algorithm on our created large-scale datasets. presents the results achieved by Ling and Shen ling2016high, and presents the results achieved by our proposed method.
  • Figure 3: Comparison between ling2016high and our proposed algorithm on the KITTI 2015 menze2015joint and Middlebury 2021 scharstein2014high datasets. presents the results achieved by Ling and Shen ling2016high, and presents the results achieved by our proposed method.
  • Figure 4: Qualitative experimental results of disparity estimation: (a) left images; (b) disparity maps estimated using unrectified stereo images; (c) disparity maps estimated using stereo images rectified based on the extrinsic parameters estimated using Ling and Shen's algorithm ling2016high; (d) disparity maps estimated using stereo images rectified based on the extrinsic parameters estimated using our proposed algorithm.