Vusi Skosana
ABSTRACT
Edge-preserving smoothing filters have had many applications in the image processing community, such as image compression, restoration, deblurring and abstraction. However, their potential application in computer vision and machine learning has never been fully studied. The most successful feature descriptors for image classification use gradient images for extracting the overall shapes of objects, thus edge preserving filters could improve their quality. The effects of various edge-preserving filters were evaluated as a pre-processing step inhuman detection. In this work, three smoothing filters were tested, namely the total variation (TV), relative total variation (RTV) and L0 smoothing. Significant performance gains were realised with TV and RTV for both colour and thermal images while the L0 smoothing filter only realised a slight improvement on thermal images and poorer performance on colour images. These results show that smoothing filters have a potential to improve the robustness of common statistical learning classifiers.
- R. Arnheim. 2004. Art and Visual Perception: A Psychology of the Creative Eye. University of California Press.Google Scholar
- Jonathan T Barron and Jitendra Malik. 2011. High-frequency shape and albedo from shading using natural image statistics. In CVPR 2011. IEEE, 2521--2528. Google ScholarDigital Library
- Jonathan T Barron and Jitendra Malik. 2012. Color constancy, intrinsic images, and shape estimation. In European Conference on Computer Vision. Springer, 57--70. Google ScholarDigital Library
- Rodrigo Benenson, Mohamed Omran, Jan Hosang, and Bernt Schiele. 2014. Ten years of pedestrian detection, what have we learned?. In European Conference on Computer Vision. Springer, 613--627.Google Scholar
- Sai Bi, Xiaoguang Han, and Yizhou Yu. 2015. An L 1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition. ACM Transactions on Graphics (TOG) 34, 4 (2015), 78. Google ScholarDigital Library
- Andrew Blake, Andrew Zisserman, and Greg Knowles. 1985. Surface descriptions from stereo and shading. Image and Vision Computing 3, 4 (1985), 183--191. Google ScholarDigital Library
- Navneet Dalal and Bill Triggs. 2005. Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, Vol. 1. IEEE, 886--893. Google ScholarDigital Library
- Piotr Dollár, Zhuowen Tu, Pietro Perona, and Serge J. Belongie. 2009. Integral Channel Features. In British Machine Vision Conference, BMVC 2009, London, UK, September 7-10, 2009. Proceedings. 1--11.Google Scholar
- Piotr Dollar, Christian Wojek, Bernt Schiele, and Pietro Perona. 2012. Pedestrian detection: An evaluation of the state of the art. IEEE transactions on pattern analysis and machine intelligence 34, 4 (2012), 743--761. Google ScholarDigital Library
- Michael Elad, Mario AT Figueiredo, and Yi Ma. 2010. On the role of sparse and redundant representations in image processing. Proc. IEEE 98, 6 (2010), 972--982.Google Scholar
- Zeev Farbman, Raanan Fattal, Dani Lischinski, and Richard Szeliski. 2008. Edge-preserving decompositions for multi-scale tone and detail manipulation. In ACM Transactions on Graphics (TOG), Vol. 27. ACM, 67. Google ScholarDigital Library
- Pedro Felzenszwalb, David McAllester, and Deva Ramanan. 2008. A discriminatively trained, multiscale, deformable part model. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 1--8.Google ScholarCross Ref
- Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. 2010. Object detection with discriminatively trained part-based models. Pattern Analysis and Machine Intelligence, IEEE Transactions on 32, 9 (2010), 1627--1645. Google ScholarDigital Library
- Hiroshi Fukui, Takayoshi Yamashita, Yuji Yamauchi, Hironobu Fujiyoshi, and Hiroshi Murase. 2015. Pedestrian detection based on deep convolutional neural network with ensemble inference network. In 2015 IEEE Intelligent Vehicles Symposium (IV). IEEE, 223--228.Google ScholarCross Ref
- Wei Gao, Haizhou Ai, and Shihong Lao. 2009. Adaptive contour features in oriented granular space for human detection and segmentation. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 1786--1793.Google Scholar
- K. He, J. Sun, and X. Tang. 2013. Guided Image Filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 6 (June 2013), 1397--1409. Google ScholarDigital Library
- Jan Hosang, Mohamed Omran, Rodrigo Benenson, and Bernt Schiele. 2015. Taking a deeper look at pedestrians. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4073--4082.Google ScholarCross Ref
- Henry Kang, Seungyong Lee, and Charles K Chui. 2009. Flow-based image abstraction. IEEE transactions on visualization and computer graphics 15, 1 (2009), 62--76. Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105. Google ScholarDigital Library
- Dumisani Kunene. 2017. SIGNI infrared pedestrian dataset, electronic dataset. Google Drive Storage. https://goo.gl/ugbevV.Google Scholar
- Dumisani Kunene and Vusi Skosana. 2019. Enhancing edge-based image descriptor models through colour unification. In 2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA). IEEE, 147--152.Google ScholarCross Ref
- Dumisani Kunene and Hima Vadapalli. 2017. Better feature acquisition through the use of infrared imaging for human detection systems. In Proceedings of the South African Institute of Computer Scientists and Information Technologists. ACM, 21. Google ScholarDigital Library
- Jan Eric Kyprianidis, Henry Kang, and Jürgen Döllner. 2009. Image and video abstraction by anisotropic Kuwahara filtering. In Computer Graphics Forum, Vol. 28. Wiley Online Library, 1955--1963.Google Scholar
- Ting-Hao Lin, Der-Lor Way, Zen-Chung Shih, Wen-Kai Tai, and Chin-Chen Chang. 2016. An Efficient Structure-Aware Bilateral Texture Filtering for Image Smoothing. In Computer Graphics Forum, Vol. 35. Wiley Online Library, 57--66. Google ScholarDigital Library
- Qiegen Liu, Biao Xiong, Dingcheng Yang, and Minghui Zhang. 2016. A generalized relative total variation method for image smoothing. Multimedia tools and applications 75, 13 (2016), 7909--7930. Google ScholarDigital Library
- Kaiyue Lu, Shaodi You, and Nick Barnes. 2018. Deep Texture and Structure Aware Filtering Network for Image Smoothing. In Proceedings of the European Conference on Computer Vision (ECCV). 217--233.Google ScholarDigital Library
- Ping Luo, Yonglong Tian, Xiaogang Wang, and Xiaoou Tang. 2014. Switchable deep network for pedestrian detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 899--906. Google ScholarDigital Library
- Dongbo Min, Sunghwan Choi, Jiangbo Lu, Bumsub Ham, Kwanghoon Sohn, and Minh N Do. 2014. Fast global image smoothing based on weighted least squares. IEEE Transactions on Image Processing 23, 12 (2014), 5638--5653.Google Scholar
- Wanli Ouyang and Xiaogang Wang. 2012. A discriminative deep model for pedestrian detection with occlusion handling. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3258--3265. Google ScholarDigital Library
- Wanli Ouyang and Xiaogang Wang. 2013. Joint deep learning for pedestrian detection. In Proceedings of the IEEE International Conference on Computer Vision. 2056--2063. Google ScholarDigital Library
- Yanwei Pang, Yuan Yuan, Xuelong Li, and Jing Pan. 2011. Efficient HOG human detection. Signal Processing 91, 4 (2011), 773--781. Google ScholarDigital Library
- Sylvain Paris, Pierre Kornprobst, Jack Tumblin, and Frédo Durand. 2007. A gentle introduction to bilateral filtering and its applications. In ACM SIGGRAPH 2007 courses. ACM, 1. Google ScholarDigital Library
- Federico Perazzi, Philipp Krähenbühl, Yael Pritch, and Alexander Hornung. 2012. Saliency filters: Contrast based filtering for salient region detection. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 733--740. Google ScholarDigital Library
- Pietro Perona and Jitendra Malik. 1990. Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on pattern analysis and machine intelligence 12, 7 (1990), 629--639. Google ScholarDigital Library
- Payam Sabzmeydani and Greg Mori. 2007. Detecting pedestrians by learning shapelet features. In 2007 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.Google ScholarCross Ref
- Pierre Sermanet, Koray Kavukcuoglu, Soumith Chintala, and Yann LeCun. 2013. Pedestrian detection with unsupervised multi-stage feature learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3626--3633. Google ScholarDigital Library
- Evgeny Strekalovskiy and Daniel Cremers. 2014. Real-time minimization of the piecewise smooth Mumford-Shah functional. In European conference on computer vision. Springer, 127--141.Google ScholarCross Ref
- Chang Tang, Chunping Hou, Yonghong Hou, Pichao Wang, and Wanqing Li. 2017. An effective edge-preserving smoothing method for image manipulation. Digital Signal Processing 63 (2017), 10--24. Google ScholarDigital Library
- Marshall F Tappen, Edward H Adelson, and William T Freeman. 2006. Estimating intrinsic component images using non-linear regression. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), Vol. 2. IEEE, 1992--1999. Google ScholarDigital Library
- Stefan Walk, Nikodem Majer, Konrad Schindler, and Bernt Schiele. 2010. New features and insights for pedestrian detection. In 2010 IEEE Computer society conference on computer vision and pattern recognition. IEEE, 1030--1037.Google Scholar
- Xiaoyu Wang, Tony X Han, and Shuicheng Yan. 2009. An HOG-LBP human detector with partial occlusion handling. In Computer Vision, 2009 IEEE 12th International Conference on. IEEE, 32--39.Google ScholarCross Ref
- Holger Winnemöller, Sven C Olsen, and Bruce Gooch. 2006. Real-time video abstraction. In ACM Transactions On Graphics (TOG), Vol. 25. ACM, 1221--1226. Google ScholarDigital Library
- Jianxin Wu, Christopher Geyer, and James M Rehg. 2011. Real-time human detection using contour cues. In Robotics and Automation (ICRA), 2011 IEEE International Conference on. IEEE, 860--867.Google ScholarCross Ref
- Tong Xiao, Shuang Li, Bochao Wang, Liang Lin, and Xiaogang Wang. 2016. End-to-end deep learning for person search. arXiv preprint arXiv:1604.01850 2 (2016).Google Scholar
- Li Xu, Cewu Lu, Yi Xu, and Jiaya Jia. 2011. Image Smoothing via L0 Gradient Minimization. ACM Trans. Graph. 30, 6, Article 174 (Dec. 2011), 12 pages. Google ScholarDigital Library
- Li Xu, Qiong Yan, Yang Xia, and Jiaya Jia. 2012. Structure extraction from texture via relative total variation. ACM Transactions on Graphics (TOG) 31, 6 (2012), 139. Google ScholarDigital Library
- Yu Zang, Hua Huang, and Lei Zhang. 2015. Guided adaptive image smoothing via directional anisotropic structure measurement. IEEE transactions on visualization and computer graphics 21, 9 (2015), 1015--1027.Google Scholar
- Xingyu Zeng, Wanli Ouyang, and Xiaogang Wang. 2013. Multi-stage contextual deep learning for pedestrian detection. In Proceedings of the IEEE International Conference on Computer Vision. 121--128. Google ScholarDigital Library
- Liliang Zhang, Liang Lin, Xiaodan Liang, and Kaiming He. 2016. Is faster R-CNN doing well for pedestrian detection?. In European Conference on Computer Vision. Springer, 443--457.Google ScholarCross Ref
- Li Zhang, Bo Wu, and Ram Nevatia. 2007. Pedestrian detection in infrared images based on local shape features. In 2007 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.Google ScholarCross Ref
- Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng, and Shai Avidan. 2006. Fast human detection using a cascade of histograms of oriented gradients. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), Vol. 2. IEEE, 1491--1498. Google ScholarDigital Library
- Robert Zimmer. 2003. Abstraction in art with implications for perception. Philosophical Transactions of the Royal Society of London B: Biological Sciences 358, 1435 (2003), 1285--1291.Google ScholarCross Ref
Index Terms
- Edge-preserving smoothing filters for improving object classification
Recommendations
An improved anisotropic diffusion model for detail- and edge-preserving smoothing
It is important in image restoration to remove noise while preserving meaningful details such as blurred thin edges and low-contrast fine features. The existing edge-preserving smoothing methods may inevitably take fine details as noise or vice versa. ...
Edge-Preserving Decomposition-Based Single Image Haze Removal
Single image haze removal is under-constrained, because the number of freedoms is larger than the number of observations. In this paper, a novel edge-preserving decomposition-based method is introduced to estimate transmission map for a haze image so as ...
Edge Guided High Order Image Smoothing
ACPR '13: Proceedings of the 2013 2nd IAPR Asian Conference on Pattern RecognitionEdge-preserving smoothing has recently emerged as a valuable tool for a variety of applications in computer graphics and image processing. Edge-preserving smoothing using first order smoothness prior in the regularization term under optimization ...
Comments