ANALYSIS AND ENHANCEMENT OF THE DENOISING DEPTH DATA USING KINECT THROUGH ITERATIVE TECHNIQUE
DOI:
https://doi.org/10.11113/jt.v78.5348Keywords:
Types of noise, denoising, depth map, Kinect sensorAbstract
Since the release of Kinect by Microsoft, the, accuracy and stability of Kinect data-such as depth map, has been essential and important element of research and data analysis. In order to develop efficient means of analyzing and using the kinnect data, researchers require high quality of depth data during the preprocessing step, which is very crucial for accurate results. One of the most important concerns of researchers is to eliminate image noise and convert image and video to the best quality. In this paper, different types of the noise for Kinect are analyzed and a unique technique is used, to reduce the background noise based on distance between Kinect devise and the user. Whereas, for shadow removal, the iterative method is used to eliminate the shadow casted by the Kinect. A 3D depth image is obtained as a result with good quality and accuracy. Further, the results of this present study reveal that the image background is eliminated completely and the 3D image quality in depth map has been enhanced.
References
Andersen, M. R., et al. 2012. Kinect Depth Sensor Evaluation For Computer Vision Applications. Ã…rhus University.
Arbel, E. and H. Hel-Or 2011. Shadow removal using intensity surfaces and texture anchor points. Pattern Analysis and Machine Intelligence. IEEE Transactions on. 33(6): 1202-1216.
Arieli, Y., et al. 2012. Depth Mapping Using Projected Patterns, Google Patents.
Barnich, O. and M. Van Droogenbroeck 2009. ViBe: A Powerful Random Technique To Estimate The Background In Video Sequences. Acoustics, Speech and Signal Processing. International Conference on, IEEE. 2009. ICASSP 2009.
Barnich, O. and M. Van Droogenbroeck 2011. Vibe: A Universal Background Subtraction Algorithm For Video Sequences. Image Processing, IEEE Transactions on. 20(6): 1709-1724.
Dakkak, A. and A. Husain 2012. Recovering Missing Depth Information from Microsoft’s Kinect. Carnegie Mellon University's.
Danciu, G., et al. 2012. Shadow Removal In Depth Images Morphology-Based For Kinect Cameras. System Theory, 16th International Conference on, IEEE, Control and Computing (ICSTCC), 2012.
Essmaeel, K., et al. 2012. Temporal Denoising Of Kinect Depth Data. Signal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on, IEEE.
Faion, F., et al. 2012. Intelligent sensor-scheduling for multi-kinect-tracking. International Conference on, IEEE, Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ
Fu, J., et al. 2012. Kinect-like Depth Denoising. Circuits and Systems (ISCAS), 2012 IEEE International Symposium on, IEEE.
Hsieha, C.-F. et al. 2014. An Improved Depth Image In Painting.
Hu, W., et al. 2013. Depth Map Denoising Using Graph-Based Transform And Group Sparsity. IEEE 15th International Workshop on, IEEE., Multimedia Signal Processing (MMSP), 2013
Kean, S., et al. 2011. Meet the Kinect: An Introduction to Programming Natural User Interfaces, Apress.
Khoshelham, K. 2011. Accuracy Analysis Of Kinect Depth Data. ISPRS Workshop Laser Scanning.
Khoshelham, K. and S. O. Elberink 2012. Accuracy And Resolution Of Kinect Depth Data For Indoor Mapping Applications. Sensors. 12(2): 1437-1454.
Leens, J., et al. 2009. Combining Color, Depth, And Motion For Video Segmentation. Computer Vision Systems. Springer. 104-113.
Liu, J., et al. 2012. Guided In Painting And Filtering For Kinect Depth Maps. 21st International Conference on, IEEE, Pattern Recognition (ICPR), 2012.
Liu, S., et al. 2013. Kinect Depth In painting via Graph Laplacian with TV21 Regularization. 2nd IAPR Asian Conference on, IEEE., Pattern Recognition (ACPR), 2013.
Matyunin, S., et al. 2011. Temporal Filtering For Depth Maps Generated By Kinect Depth Camera. 3DTV Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON), 2011, IEEE.
Milani, S. and G. Calvagno 2012. Joint Denoising And Interpolation Of Depth Maps For MS Kinect Sensors. Acoustics, 2012 IEEE International Conference on, IEEE., Speech and Signal Processing (ICASSP).
Mueller, M., et al. 2010. Adaptive cross-trilateral depth map filtering. 3DTV-Conference: The True Vision-Capture. Transmission and Display of 3D Video (3DTV-CON), 2010, IEEE.
Nguyen, C. V., et al. 2012. Modeling Kinect Sensor Noise For Improved 3d Reconstruction And Tracking. Second International Conference on, IEEE., 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012.
Park, J.-H., et al. 2012. Spatial Uncertainty Model for Visual Features Using a Kinectâ„¢ Sensor. Sensors. 12(7): 8640-8662.
Qi, F., et al. 2013. Structure Guided Fusion For Depth Map In Painting. Pattern Recognition Letters. 34(1): 70-76.
Tallón, M., et al. 2012. Up Sampling And Denoising Of Depth Maps Via Joint-Segmentation. Proceedings of the 20th European, IEEE., Signal Processing Conference (EUSIPCO), 2012.
Xiao, Y., et al. Shadow Removal from Single RGB-D Images.
Xiong, H., et al. 2006. Enhancing data analysis with noise removal" Knowledge and Data Engineering. IEEE Transactions on.18(3): 304-319.
Xu, Y., et al. 2014. Spatial-Temporal Depth De-Noising For Kinect Based On Texture Edge-Assisted Depth Classification. 19th International Conference on, IEEE., Digital Signal Processing (DSP), 2014.
Yu, Y., et al. 2013. A Shadow Repair Approach For Kinect Depth Maps. Computer Vision–ACCV 2012. Springer. 615-626.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
