Abstract
With the advent of RGB-D cameras, such as Kinect, it is now possible to benefit from both color and depth of the field of view in real time towards a better understanding of the scene. While such devices are providing appreciative depth information; captured depth map suffers from noticeable noise. Recent methods reach satisfactory results in depth recovery by focusing on color and depth images individually or cooperatively. In this paper, we propose a geometric approach to structurally model the scene by extracting a series of planes from the point cloud. The problem is formulated as an energy minimization function based on initial depth values calculated by modeling the scene using planes, and applying local filters on color image and depth map. The presented method is implemented and tested on simulation data and experimental results show its accurate and precise performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Camplani, M., Salgado, L.: Efficient spatio-temporal hole filling strategy for kinect depth maps. In: IST/SPIE Electronic Imaging, SPIE Proceedings, vol. 8290, pp. 82900E–82900E. International Society for Optics and Photonics (2012)
Chen, L., Lin, H., Li, S.: Depth image enhancement for Kinect using region growing and bilateral filter. In: 21st International Conference on Pattern Recognition (ICPR), pp. 3070–3073. IEEE (2012)
Chen, C., Cai, J., Zheng, J., Cham, T.J., Shi, G.: A color-guided, region-adaptive and depth-selective unified framework for Kinect depth recovery. In: IEEE 15th International Workshop on Multimedia Signal Processing (MMSP), pp. 007–012. IEEE (2013)
Chen, C., Cai, J., Zheng, J., Cham, T.J., Shi, G.: Kinect depth recovery using a color-guided, region-adaptive, and depth-selective framework. ACM Trans. Intell. Syst. Technol. (TIST) 6(2), 12 (2015)
Alehdaghi, M., Esfahani, M.A., Harati, A.: Parallel RANSAC: speeding up plane extraction in RGBD image sequences using GPU. In: 5th International Conference on Computer and Knowledge Engineering (ICCKE), pp. 295–300. IEEE (2015)
Chen, X., Kristian H., Yinhai, W.: Kinect–based pedestrian detection for crowded scenes. Comput. Aided Civ. Inf. Eng. 31(3), 229–240 (2016)
Dolson, J., Baek, J., Plagemann, C., Thrun, S.: Upsampling range data in dynamic environments. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1141–1148. IEEE (2010). ISO 690
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Freedman, B., Shpunt, A., Machline, M., Arieli, Y.: U.S. Patent No. 8,493,496. U.S. Patent and Trademark Office, Washington, DC (2013)
Kopf, J., Cohen, M.F., Lischinski, D., Uyttendaele, M.: Joint bilateral upsampling. ACM Trans. Graphics (TOG) 26(3), 96 (2007)
Liu, S., Lai, P., Tian, D., Gomila, C., Chen, C.W.: Joint trilateral filtering for depth map compression. In: Visual Communications and Image Processing, SPIE Proceedings, vol. 7744, pp. 77440F–77440F. International Society for Optics and Photonics (2010). ISO 690
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007). Minneapolis (2007)
Richardt, C., Stoll, C., Dodgson, N.A., Seidel, H.P., Theobalt, C.: Coherent spatiotemporal filtering, upsampling and rendering of RGBZ videos. Comput. Graph. Forum 31(2pt1), 247–256 (2012)
Schnabel, R., Wahl, R., Klein, R.: Efficient RANSAC for point cloud shape detection. Comput. Graphics Forum 26(2), 214–226 (2007)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: Sixth International Conference on Computer Vision, pp. 839–846. IEEE (1998)
Yang, Q., Yang, R., Davis, J., Nistér, D. Spatial-depth super resolution for range images. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)
Zhu, M., Canjun, Y., Wei, Y., Qian, B.: A Kinect-based motion capture method for assessment of lower extremity exoskeleton. In: Wearable Sensors and Robots, pp. 481–494. Springer, Singapore (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Esfahani, M.A., Pourreza, H. (2017). Kinect Depth Recovery Based on Local Filters and Plane Primitives. In: Constanda, C., Dalla Riva, M., Lamberti, P., Musolino, P. (eds) Integral Methods in Science and Engineering, Volume 2. Birkhäuser, Cham. https://doi.org/10.1007/978-3-319-59387-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-59387-6_6
Published:
Publisher Name: Birkhäuser, Cham
Print ISBN: 978-3-319-59386-9
Online ISBN: 978-3-319-59387-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)