Oriental Journal of Computer Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Real Time Depth Hole Filling using Kinect Sensor and Depth Extract from Stereo Images


Affiliations
1 College of Agricultural Engineering and Technology, Electronics Communication Engineering, Junagadh Agricultural University, Gujarat, India
2 C. U. Shah University, Pro- Vice Chancellor, Wadhwan City, Gujarat, India
3 Electronics Communication Engineering, Atmiya Institute of technology & Science, Gujarat technological university, Gujarat, India
4 College of Agricultural Engineering and Technology, Junagadh Agricultural University, Gujarat, India
 

The researcher have suggested real time depth based on frequency domain hole filling. It get better quality of depth sequence generated by sensor. This method is capable to produce high feature depth video which can be quite useful in improving the performance of various applications of Microsoft Kinect such as obstacle detection and avoidance, facial tracking, gesture recognition, pose estimation and skeletal. For stereo matching approach images depth extraction is the hybrid (Combination of Morphological Operation) mathematical algorithm. There are few step like color conversion, block matching, guided filtering, minimum disparity assignment design, mathematical perimeter, zero depth assignment, combination of hole filling and permutation of morphological operator and last nonlinear spatial filtering. Our algorithm is produce smooth, reliable, noise less and efficient depth map. The evaluation parameter such as Structure Similarity Index Map (SSIM), Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) measure the results for proportional analysis.

Keywords

Depth, Disparity, Guided Filter, Kinect, Morphological Filter, Stereo Matching, Warp, Zero Depth, 3-Dimension.
User
Notifications
Font Size

  • Conference Papers

  • Jianbo Jiao, Ronggang Wang, “Local stereo matching with improved matching cost and disparity refinement,” IEEE Computer Society, 1070-986X/14/2014, pp.16-27.

  • S. Mukherjee, R. M. Guddeti, “A hybrid algorithm for disparity calculation from sparse disparity estimates based on stereo vision,” IEEE, 978-1-4799-4665-5/14/ 2014.

  • He, K., Sun, J. and Tang, X., 2010, September. Guided image filtering. In European conference on computer vision (pp. 1-14). Springer Berlin Heidelberg.

  • K. Rao, Joohee Kim, “Refinement of Depth Maps Generated By Low-Cost Depth Sensors,” 978-1-4673-2990-3, pp. 355-358, ISOCC, IEEE, 2012.

  • Books

  • Gonzalez, R.C. and Woods, R.E., 2008. Digital image processing. Nueva Jersey.

  • Jain, A.K., 1989. Fundamentals of digital image processing. Prentice-Hall, Inc..

  • Journal Papers

  • Xiaoyan Hu, Philippos Mordohai, “A quantitative evaluation of confidence measures for stereo vision”, IEEE transactions on pattern analysis and machine intelligence, 0162-8828/12, vol. 34, no. 11, November 2012, pp. 2121-2133.

  • Kaiming He, Jian Sun, “Guided image filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, 2013.

  • Ashish M. Kothari, Ved Vyas Dwivedi, “Performance Analysis of Digital Video Watermarking using Discrete Cosine Transform,” International Journal of Electrical and Computer Engineering Systems Issues Vol. 2, Number 1, pp. 11-16 2011

  • Ling Shao, “Computer Vision for RGB-D Sensors: Kinect and Its Applications”, IEEE Transactions On Cybernetics, Vol. 43, No. 5, October 2013.

  • T. Mallick, “Characterizations of Noise in Kinect Depth Images: A Review,” IEEE Sensors Journal, VOL. 14, NO. 6, pp. 1731-1740, 2014.

  • Yongjoo Cho, Kiyoung Seo, Kyoung Shin Park, “Enhancing Depth Accuracy on the Region of Interest in a Scene for Depth Image Based Rendering”, KSII Transactions On Internet And Information Systems Vol. 8, No. 7, July. 2014

  • Ke-Yu Lin and Hsueh-Ming Hang, “Depth Map Enhancement On Rgb-D Video Captured By Kinect V2” Proceedings, APSIPA Annual Summit and Conference 2018 ,12-15 November 2018, Hawaii, 978-988-14768-5-2.

  • Web Resources

  • Kinect sensor specifications, [Online], Available: http://www.microsoft.com.


Abstract Views: 332

PDF Views: 0




  • Real Time Depth Hole Filling using Kinect Sensor and Depth Extract from Stereo Images

Abstract Views: 332  |  PDF Views: 0

Authors

Kapil Raviya
College of Agricultural Engineering and Technology, Electronics Communication Engineering, Junagadh Agricultural University, Gujarat, India
Ved Vyas Dwivedi
C. U. Shah University, Pro- Vice Chancellor, Wadhwan City, Gujarat, India
Ashish Kothari
Electronics Communication Engineering, Atmiya Institute of technology & Science, Gujarat technological university, Gujarat, India
Gunvantsinh Gohil
College of Agricultural Engineering and Technology, Junagadh Agricultural University, Gujarat, India

Abstract


The researcher have suggested real time depth based on frequency domain hole filling. It get better quality of depth sequence generated by sensor. This method is capable to produce high feature depth video which can be quite useful in improving the performance of various applications of Microsoft Kinect such as obstacle detection and avoidance, facial tracking, gesture recognition, pose estimation and skeletal. For stereo matching approach images depth extraction is the hybrid (Combination of Morphological Operation) mathematical algorithm. There are few step like color conversion, block matching, guided filtering, minimum disparity assignment design, mathematical perimeter, zero depth assignment, combination of hole filling and permutation of morphological operator and last nonlinear spatial filtering. Our algorithm is produce smooth, reliable, noise less and efficient depth map. The evaluation parameter such as Structure Similarity Index Map (SSIM), Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) measure the results for proportional analysis.

Keywords


Depth, Disparity, Guided Filter, Kinect, Morphological Filter, Stereo Matching, Warp, Zero Depth, 3-Dimension.

References





DOI: https://doi.org/10.13005/ojcst12.03.06