Abstract
For enhancing the low contrast and detecting the noise in depth image from Kinect sensor, the Non-Subsampled Contourlet Transform (NSCT) and non-linear fractional differential are studied in this paper. Firstly, on the basis of the NSCT’s advantages, the depth image is decomposed into low frequency and high frequency. The low frequency component is applied to enhance depth image using adaptive scale Retinex, and the scale parameter is adjusted by local mean and standard deviation. The high frequency component is calculated by Non-Local-Means operator to preserve the texture detail. The final enhanced image can be achieved by inverse NSCT. Secondly, the fractional differential theory is studied to accomplish noise detection. The experimental results show that the proposed method can enhance the depth image and detect noise effectively.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Cevikalp, H., & Triggs, B. (2010). Face recognition based on image sets. In IEEE conference on computer vision and pattern recognition (CVPR), San Francisco (pp. 2567–2573).
Boutellaa, E., Hadid, A., Bengherabi, M., et al.(2015). On the use of Kinect depth data for identity, gender and ethnicity classification from facial images. Pattern Recognition Letters, 68(P2), 270–277.
Fanelli, G., Gall, J., & VanGool, L. (2011). Realtime head pose estimation with random regression forests, In 2011 IEEE conference on computer vision and pattern recognition (CVPR), Colorado Springs (pp. 617–624).
As’ari, M. A., Sheikh, U. U., & Supriyanto, E. (2014). 3D shape descriptor for object recognition based on Kinect-like depth image. Image and Vision Computing, 32, 260–269.
Nissimov, S., Goldberger, J., & Alchanatis, V. (2015). Obstacle detection in a greenhouse environment using the Kinect sensor. Computers and Electronics in Agriculture, 113(C) 104–115.
Khan, A., Moideen, F., Lopez, J., Khoo, W. L., & Zhu, Z. (2012). Kindectect: Kinect detecting objects. In: International conference on computers helping people with special needs (pp. 588–595).
Liu, L., Jia, Z., Yang, J., & Kasabov, N. (2015). A medical image enhancement method using adaptive thresholding in nsct domain combined unsharp masking. International Journal of Imaging Systems & Technology, 25(3), 199–205.
Centeno, J., & Haertel, V. (2014). An adaptive image enhancement algorithm. Pattern Recognition, 30(7), 1183–1189.
Wu, Y. Q., & Shi, J. P. (2015). Image enhancement in non-subsampled contourlet transform domain based on multi-scale retinex. Acta Optica Sinica, 35(3), 1–10.
Li, B., & Xie, W. (2015). Adaptive fractional differential approach and its application to medical image enhancement. Computers & Electrical Engineering, 45, 324–335.
Li, B., et al. (2016). Image denoising and enhancement based on adaptive fractional calculus of small probability strategy. Neuro Computing, 175, 704–717.
Yang, J., Gan, Z., Li, K., & Hou, C. (2015). Graph-based segmentation for RGB-D data using 3-D geometry enhanced superpixels. IEEE Transactions on Cybernetics, 45(5), 927–940.
Zhang, L., Yang, F., Zhang, Y. D., et al. (2016). Road crack detection using deep convolutional neural network. In IEEE international conference on image processing. IEEE.
Acknowledgements
This research is financially supported by the central university fund in China (No. CHD2013G2241019), the major program of international cooperation in Shaanxi province of China (No. 2013KW03), and Excellent Doctoral Dissertation Foster Fund of Chang’an University in China (No. 310824150011).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cao, T., Wang, W. Depth Image Enhancement and Detection on NSCT and Fractional Differential. Wireless Pers Commun 103, 1025–1035 (2018). https://doi.org/10.1007/s11277-018-5494-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-018-5494-y