Jaccard distance as similarity measure for disparity map estimation

Authors

  • Victor Alejandro Gonzalez-Huitron Instituto Politécnico Nacional, Santa Ana 1000, ESIME Culhuacan, Mexico-City 04440, Mexico https://orcid.org/0000-0003-0426-0515
  • Abraham Efraim Rodriguez-mata Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico. https://orcid.org/0000-0002-0262-420X
  • Leonel Ernesto Amabilis-Sosa CONACYT-TecNM campus Culiacan, Juan de Dios Bátiz No. 310 Pte. , Col. Guadalupe, C.P. 80220 Culiacán Rosales, Sin. https://orcid.org/0000-0002-9020-1951
  • Rogelio Baray-Arana Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico. https://orcid.org/0000-0003-1084-0807
  • Isidro Robledo-Vega Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico. https://orcid.org/0000-0002-5180-3124
  • Guillermo Valencia-Palomo IT de Hermosillo, Av. Tec. y Per. Poniente, S/N, 83170, Hermosillo, Mexico https://orcid.org/0000-0002-3382-8213

Keywords:

Stereoscopic vision, disparity mapping, Jaccard, image processing

Abstract

High confidence in disparity map estimation is critical in several application fields. A novel framework that employs customized local binary patterns and Jaccard distance for stereo matching along stereo consistency checks is presented. The proposal contributes with a method that allows greater confidence in its estimates, without dependence on supervised learning, and capable of generating a dense map with low-cost filtering. The proposed framework has been implemented in CPU and GPU for parallel processing capability. First, Local binary patterns are obtained during the initial stage; then, the Jaccard distance is employed as a similarity measure in the stereo matching stage; subsequently, a matching consistency check is performed, and singular disparities are removed. A comparison among novel and state-of-the-art algorithms for sparse disparity map estimation is performed employing Middlebury and KITTI stereo Datasets where the quality criteria used were percentage of bad pixels (B), quantity of invalid pixels, processing time and running environments to put each framework into context, obtaining down to 2.07% bad matching pixels and performing better than state-of-the-art cost functions

Downloads

Download data is not yet available.

Author Biographies

Victor Alejandro Gonzalez-Huitron, Instituto Politécnico Nacional, Santa Ana 1000, ESIME Culhuacan, Mexico-City 04440, Mexico

attained his Ph.D. in communications and electronics in 2017 and M.S. degree in engineering in microelectronics in 2013, from Instituto Politecnico Nacional. He is currently working as a professor and researcher at TecNM. His research interests include computer vision, image processing and digital signal processing

Abraham Efraim Rodriguez-mata, Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico.

He obtained a degree in Chemical Engineering in 2009, Master and PhD in Automatic Control at Cinvestav of IPN Mexico. He is currently a researcher is TecNM campus Chihuahua and a member of the National System of Researchers (SNI) of Mexico. He is interesting in robust control, active disturbance rejection and nonlinear observer design, artificial intelligence applications to various engineering problems.

Leonel Ernesto Amabilis-Sosa, CONACYT-TecNM campus Culiacan, Juan de Dios Bátiz No. 310 Pte. , Col. Guadalupe, C.P. 80220 Culiacán Rosales, Sin.

PhD in Environmental Engineering, graduated from Mexico's highest university with honors. He is also an expert in multiparametric statistics applied to various engineering problems. He is currently interested in applications of artificial intelligence and machine learning to various engineering phenomena related to environmental research

Rogelio Baray-Arana, Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico.

received the BSc(1987) and the MSc.(1990) degrees in electrical engineering from the Chihuahua Institute of Technology, Chihuahua, Chih., Mexico. His professional experience includes development of projects and consultancy for several companies. He currently works as a Research Professor at the Chihuahua Institute of Technology, in Chihuahua, Chih.

Isidro Robledo-Vega, Tecnológico Nacional de Mexico/IT Chihuahua, Av. Tec. 2909, 31200, Chihuahua, Mexico.

Isidro Robledo-Vega received the BSc degree in industrial engineering in electronics in 1989 and the MSc degree in electronics engineering with a computer science option in 1996 from the Technological Institute of Chihuahua, Mexico, and the PhD degree in computer science.

Guillermo Valencia-Palomo, IT de Hermosillo, Av. Tec. y Per. Poniente, S/N, 83170, Hermosillo, Mexico

received his PhD in Automatic Control and Systems Engineering from the University of Sheffield, U.K., in 2010. Since 2010, he has been with Tecnológico Nacional de México, IT Hermosillo. He is Associate Editor of IEEE Access, IEEE Latin America Transactions, Int. J. of Aerospace Engineering

References

D. Scharstein and R. Szeliski, “A taxonomy and evaluation of dense

two-frame stereo correspondence algorithms,” International Journal of

Computer Vision, vol. 47, no. 1, pp. 7–42, 2002.

S. Trejo, K. Martinez, and G. Flores, “Depth map estimation methodology

for detecting free-obstacle navigation areas,” in 2019 International

Conference on Unmanned Aircraft Systems (ICUAS), pp. 916–922, IEEE,

J.-N. Zhang, Q.-X. Su, P.-Y. Liu, H.-Y. Ge, and Z.-F. Zhang, “Mudeepnet:

Unsupervised learning of dense depth, optical flow and camera pose

using multi-view consistency loss,” International Journal of Control,

Automation and Systems, vol. 17, no. 10, pp. 2586–2596, 2019.

K. Zhou, X. Meng, and B. Cheng, “Review of stereo matching algorithms

based on deep learning,” Computational Intelligence and

Neuroscience, vol. 2020, 2020.

R. Fan, X. Ai, and N. Dahnoun, “Road surface 3d reconstruction based

on dense subpixel disparity map estimation,” IEEE Transactions on

Image Processing, vol. 27, no. 6, pp. 3025–3035, 2018.

R. A. Hamzah, A. F. Kadmin, M. S. Hamid, S. F. A. Ghani, and

H. Ibrahim, “Improvement of stereo matching algorithm for 3d surface

reconstruction,” Signal Processing: Image Communication, vol. 65,

pp. 165–172, 2018.

J. H. Jung, S. Heo, and C. G. Park, “Patch-based stereo direct visual

odometry robust to illumination changes,” International Journal of

Control, Automation and Systems, vol. 17, no. 3, pp. 743–751, 2019.

T. S. Sheikh and I. M. Afanasyev, “Stereo vision-based optimal path

planning with stochastic maps for mobile robot navigation,” in International

Conference on Intelligent Autonomous Systems, pp. 40–55,

Springer, 2018.

B.-S. Shin, X. Mou, W. Mou, and H. Wang, “Vision-based navigation of an unmanned surface vehicle with object detection and tracking

abilities,” Machine Vision and Applications, vol. 29, no. 1, pp. 95–112,

L. Ting and D. Yuelin, “A novel method of human tracking based on

stereo vision,” in 2018 5th IEEE International Conference on Cloud

Computing and Intelligence Systems (CCIS), pp. 883–889, IEEE, 2018.

K. Batsos and P. Mordohai, “Recresnet: A recurrent residual cnn

architecture for disparity map enhancement,” in 2018 International

Conference on 3D Vision (3DV), pp. 238–247, IEEE, 2018.

F. Cheng, X. He, and H. Zhang, “Learning to refine depth for robust

stereo estimation,” Pattern Recognition, vol. 74, pp. 122–133, 2018.

S. J. Lee, H. Choi, and S. S. Hwang, “Real-time depth estimation using

recurrent cnn with sparse depth cues for slam system,” International

Journal of Control, Automation and Systems, vol. 18, no. 1, pp. 206–

, 2020.

C. Lin, Y. Li, G. Xu, and Y. Cao, “Optimizing ZNCC calculation in

binocular stereo matching,” Signal Processing: Image Communication,

vol. 52, pp. 64–73, 2017.

J.-I. Kang and S.-W. Lee, “A light-weight stereo matching network

for an embedded vision system,” in 2020 International Conference

on Information and Communication Technology Convergence (ICTC),

pp. 1234–1237, IEEE, 2020.

S. Perri, F. Frustaci, F. Spagnolo, and P. Corsonello, “Design of realtime

fpga-based embedded system for stereo vision,” in 2018 IEEE

International Symposium on Circuits and Systems (ISCAS), pp. 1–5,

IEEE, 2018.

H. Hirschmuller, “Stereo processing by semiglobal matching and mutual

information,” IEEE Transactions on Pattern Analysis and Machine

Intelligence, vol. 30, no. 2, pp. 328–341, 2007.

J. Valentin, A. Kowdle, J. T. Barron, N. Wadhwa, M. Dzitsiuk,

M. Schoenberg, V. Verma, A. Csaszar, E. Turner, I. Dryanovski, et al.,

“Depth from motion for smartphone ar,” ACM Transactions on Graphics

(ToG), vol. 37, no. 6, pp. 1–19, 2018.

Y. Zhong, C. Loop, W. Byeon, S. Birchfield, Y. Dai, K. Zhang,

A. Kamenev, T. Breuel, H. Li, and J. Kautz, “Displacement-invariant

cost computation for efficient stereo matching,” arXiv preprint

arXiv:2012.00899, 2020.

W. Mao, M. Wang, J. Zhou, and M. Gong, “Semi-dense stereo matching

using dual cnns,” in 2019 IEEE Winter Conference on Applications of

Computer Vision (WACV), pp. 1588–1597, IEEE, 2019.

J. Zbontar, Y. LeCun, et al., “Stereo matching by training a convolutional

neural network to compare image patches.,” Journal of Machine

Learning Research, vol. 17, no. 1, pp. 2287–2318, 2016.

J. Navarro and A. Buades, “Semi-dense and robust image registration by

shift adapted weighted aggregation and variational completion,” Image

and Vision Computing, vol. 89, pp. 258–275, 2019.

L. Keselman, J. Iselin Woodfill, A. Grunnet-Jepsen, and A. Bhowmik,

“Intel realsense stereoscopic depth cameras,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops,

pp. 1–10, 2017.

R. Zabih and J. Woodfill, “Non-parametric local transforms for computing

visual correspondence,” in European conference on computer vision,

pp. 151–158, Springer, 1994.

F. Guney and A. Geiger, “Displets: Resolving stereo ambiguities using

object knowledge,” in Proceedings of the IEEE Conference on Computer

Vision and Pattern Recognition, pp. 4165–4175, 2015.

M. S. Hamid, N. Abd Manap, R. A. Hamzah, and A. F. Kadmin, “Stereo

matching algorithm based on deep learning: A survey,” Journal of King

Saud University-Computer and Information Sciences, 2020.

K. Yamaguchi, D. McAllester, and R. Urtasun, “Robust monocular

epipolar flow estimation,” in Proceedings of the IEEE Conference on

Computer Vision and Pattern Recognition, pp. 1862–1869, 2013.

A. Seki and M. Pollefeys, “SGM-nets: Semi-global matching with neural

networks,” in Proceedings of the IEEE Conference on Computer Vision

and Pattern Recognition, pp. 231–240, 2017.

X. Cheng, P. Wang, and R. Yang, “Learning depth with convolutional

spatial propagation network,” IEEE Transactions on Pattern Analysis

and Machine Intelligence, vol. 42, no. 10, pp. 2361–2379, 2019.

W. Ende, Z. Yalong, P. Liangyu, L. Yijun, and W. Tianyao, “Stereo

matching algorithm based on the combination of matching costs,” in

IEEE 7th Annual International Conference on CYBER Technology

in Automation, Control, and Intelligent Systems (CYBER), pp. 1001–

, IEEE, 2017.

V. Gonzalez-Huitron, V. Ponomaryov, E. Ramos-Diaz, and S. Sadovnychiy,

“Parallel framework for dense disparity map estimation using

hamming distance,” Signal, Image and Video Processing, vol. 12, no. 2,

pp. 231–238, 2018.

V. Kravchenko, V. Ponomaryov, V. Pustovoit, and D. Rosas-Miranda,

“Depth map reconstruction based on features formed by descriptor of

stereo color pairs,” in Doklady Mathematics, vol. 100, pp. 396–400,

Springer, 2019.

M. Rahman, S. Rahman, M. Shoyaib, et al., “MCCT: a multi-channel

complementary census transform for image classification,” Signal, Image

and Video Processing, vol. 12, no. 2, pp. 281–289, 2018.

C. Singh, E. Walia, and K. P. Kaur, “Color texture description with novel

local binary patterns for effective image retrieval,” Pattern recognition,

vol. 76, pp. 50–68, 2018.

C. Ahlberg, M. León, F. Ekstrand, and M. Ekström, “The genetic

algorithm census transform: evaluation of census windows of different

size and level of sparseness through hardware in-the-loop training,”

Journal of Real-Time Image Processing, vol. 18, no. 3, pp. 539–559,

S. Kosub, “A note on the triangle inequality for the jaccard distance,”

Pattern Recognition Letters, vol. 120, pp. 36–38, 2019.

V. Verma and R. K. Aggarwal, “A comparative analysis of similarity

measures akin to the Jaccard index in collaborative recommendations:

empirical and theoretical perspective,” Social Network Analysis and

Mining, vol. 10, no. 1, pp. 1–16, 2020.

D. Scharstein, H. Hirschmüller, Y. Kitajima, G. Krathwohl, N. Neši´c,

X. Wang, and P. Westling, “High-resolution stereo datasets with

subpixel-accurate ground truth,” in German Conference on Pattern

Recognition, pp. 31–42, Springer, 2014.

M. Menze, C. Heipke, and A. Geiger, “Joint 3D estimation of vehicles

and scene flow,” ISPRS Annals of the Photogrammetry, Remote Sensing

and Spatial Information Sciences, vol. 2, p. 427, 2015.

Published

2023-04-18

How to Cite

Gonzalez-Huitron, V. A., Rodriguez-mata, A. E., Amabilis-Sosa, L. E., Baray-Arana, R., Robledo-Vega, I., & Valencia-Palomo, G. (2023). Jaccard distance as similarity measure for disparity map estimation. IEEE Latin America Transactions, 21(5), 690–698. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/7560

Issue

Section

Electronics

Most read articles by the same author(s)