Cited By
View all- Wang ZYang LSheng YShen M(2021)Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road ScenesRemote Sensing10.3390/rs1321438213:21(4382)Online publication date: 30-Oct-2021
Enhancing scene parsing by transferring structures via efficient low-rank graph matching
Authors: 
Tianshu Yu, Ruisheng WangAuthors Info & Claims
Tianshu Yu, Ruisheng WangAuthors Info & ClaimsArticle No.: 22, Pages 1 - 9
Abstract
Scene parsing has attracted significant attention for its practical and theoretical value in computer vision. A typical scene parsing algorithm seeks to densely label pixels or 3-dimensional points from a scene. Traditionally, this procedure relies on a pre-trained classifier to identify the label information, and a smoothing step via Markov Random Field to enhance the consistency. LabelTranfer is a category of scene parsing algorithms to enhance traditional scene parsing framework, by finding dense correspondence and transferring labels across scenes. In this paper, we present a novel scene parsing algorithm which matches maximal similar structures between scenes via efficient low-rank graph matching. The inputs of the algorithm are images, and well- aligned point clouds if available. The images and the point clouds are processed in separate pipelines. The pipeline of images is to learn a reliable classifier and to match local structures via graph matching. The pipeline of point clouds is to conduct preliminary segmentation and to generate feasible label sets. The two pipelines are merged at inference step, in which we elaborate effective and efficient potential functions. We propose a new graph matching model incorporating low-rank and Frobenius regularization, which not only guarantees an accurate solution, but also provides high optimization efficiency via an eigen-decomposition strategy. Several challenging experiments are conducted, showing competitive performance of the proposed method compared to state-of-the-art LabelTransfer algorithm. Further, with point clouds, the performance can be significantly enhanced.
References
[1]
A. Arnab, S. Jayasumana, S. Zheng, and P. Torr. Higher order potentials in end-to-end trainable conditional random fields. arXiv preprint arXiv:1511.08119, 2015.
[2]
P. Babahajiani, L. Fan, and M. Gabbouj. Semantic parsing of street scene images using 3d lidar point cloud. In ICCVW, pages 714--721, 2013.
[3]
S. T. Birchfield and S. Rangarajan. Spatiograms versus histograms for region-based tracking. In CVPR, volume 2, pages 1158--1163, 2005.
[4]
M. Cho, J. Lee, and K. M. Lee. Reweighted random walks for graph matching. In ECCV, pages 492--505, 2010.
[5]
T. Cour, P. Srinivasan, and J. Shi. Balanced graph matching. In NIPS, pages 313--320, 2007.
[6]
C. Farabet, C. Couprie, L. Najman, and Y. Lecun. Scene parsing with multiscale feature learning, purity trees, and optimal covers. In ICML, pages 575--582, 2012.
[7]
C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. PAMI, 35(8):1915--1929, 2013.
[8]
P. F. Felzenszwalb and D. P. Huttenlocher. Efficient belief propagation for early vision. IJCV, 70(1):41--54, 2006.
[9]
M. A. Fischler and O. Firschein. Readings in Computer Vision: Issues, Problem, Principles, and Paradigms. Morgan Kaufmann, 2014.
[10]
A. Jain, A. Gupta, and L. S. Davis. Learning what and how of contextual models for scene labeling. In ECCV, pages 199--212. 2010.
[11]
P. Krähenbühl and V. Koltun. Efficient inference in fully connected crfs with gaussian edge potentials. In NIPS, pages 109--117, 2011.
[12]
B. Kulis, A. C. Surendran, and J. C. Platt. Fast low-rank semidefinite programming for embedding and clustering. In International Conference on Artificial Intelligence and Statistics, pages 235--242, 2007.
[13]
M. Leordeanu and M. Hebert. A spectral technique for correspondence problems using pairwise constraints. In ICCV, pages 1482--1489, 2005.
[14]
C. Liu, J. Yuen, and A. Torralba. Nonparametric scene parsing via label transfer. PAMI, 33(12):2368--2382, 2011.
[15]
C. Liu, J. Yuen, and A. Torralba. Sift flow: Dense correspondence across scenes and its applications. PAMI, 33(5):978--994, 2011.
[16]
H. Myeong, J. Y. Chang, and K. M. Lee. Learning object relationships via graph-based context model. In CVPR, pages 2727--2734, 2012.
[17]
H. Myeong and K. M. Lee. Tensor-based high-order semantic relation transfer for semantic scene segmentation. In CVPR, pages 3073--3080, 2013.
[18]
A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV, 42(3):145--175, 2001.
[19]
P. Pinheiro and R. Collobert. Recurrent convolutional neural networks for scene labeling. In ICML, pages 82--90, 2014.
[20]
X. Ren and J. Malik. Learning a classification model for segmentation. In ICCV, pages 10--17, 2003.
[21]
B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman. Labelme: a database and web-based tool for image annotation. IJCV, 77(1-3):157--173, 2008.
[22]
R. B. Rusu, N. Blodow, Z. C. Marton, and M. Beetz. Close-range scene segmentation and reconstruction of 3d point cloud maps for mobile manipulation in domestic environments. In IROS, pages 1--6, 2009.
[23]
C. Schellewald and C. Schnaörr. Probabilistic subgraph matching based on convex relaxation. In EMMCVPR, pages 171--186, 2005.
[24]
C. J. Taylor and A. Cowley. Fast scene analysis using image and range data. In ICRA, pages 3562--3567, 2011.
[25]
J. Tighe and S. Lazebnik. Superparsing: scalable nonparametric image parsing with superpixels. In ECCV, pages 352--365. 2010.
[26]
F. Tung and J. J. Little. Scene parsing by nonparametric label transfer of content-adaptive windows. CVIU, 143:191--200, 2016.
[27]
P. Wang, C. Shen, and A. van den Hengel. A fast semidefinite approach to solving binary quadratic problems. In CVPR, pages 1312--1319, 2013.
[28]
R. Wang, F. P. Ferrie, and J. Macfarlane. Automatic registration of mobile lidar and spherical panoramas. In CVPRW, pages 33--40, 2012.
[29]
T. Yu and R. Wang. Graph matching with low-rank regularization. In WACV, 2016.
[30]
T. Yu and R. Wang. Scene parsing using graph matching on street-level data. doi: 10.1016/j.cviu.2016.01.004, 2016.
[31]
C. Zhang, L. Wang, and R. Yang. Semantic segmentation of urban scenes using dense depth maps. In ECCV, pages 708--721, 2010.
[32]
H. Zhang, T. Fang, X. Che, Q. Zhao, and L. Quan. Partial similarity based nonparametric scene parsing in certain environment. In CVPR, pages 2241--2248, 2011.
[33]
S. Zheng, S. Jayasumana, B. Romera-Paredes, V. Vineet, Z. Su, D. Du, C. Huang, and P. Torr. Conditional random fields as recurrent neural networks. In ICCV, 2015.
[34]
H. Zou and T. Hastie. Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301--320, 2005.
Index Terms
- Enhancing scene parsing by transferring structures via efficient low-rank graph matching
Recommendations
Scene parsing using graph matching on street-view data
An effective scene parsing framework via graph matching guidance on street-level data is proposed.Graph matching is introduced to partially match image components taking into account the regional similarity of scenes.The proposed algorithm can be ...
Cluttered indoor scene modeling via functional part-guided graph matching
We propose an automatic method for fast reconstruction of indoor scenes from raw point scans, which is a fairly challenging problem due to the restricted accessibility and the cluttered space for indoor environment. We first detect and remove points ...
Single/cross-camera multiple-person tracking by graph matching
Single and cross-camera multiple person tracking in unconstrained condition is an extremely challenging task in computer vision. Facing the main difficulties caused by the existence of occlusion in single-camera scenario and the occurrence of transition ...
Comments
Information & Contributors
Information
Published In
October 2016
649 pages
ISBN:9781450345897
DOI:10.1145/2996913
- General Chairs:
- Mohamed Ali,
- Shawn Newsam,
- Program Chairs:
- Matthias Renz,
- Goce Trajcevski,
- Siva Ravada
Copyright © 2016 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 31 October 2016
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Google Research Award
Conference
SIGSPATIAL'16
SIGSPATIAL'16: 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
October 31 - November 3, 2016
California, Burlingame
Acceptance Rates
SIGSPACIAL '16 Paper Acceptance Rate 40 of 216 submissions, 19%;
Overall Acceptance Rate 257 of 1,238 submissions, 21%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 96Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Feb 2025
Other Metrics
Citations
Cited By
View all- Wang ZYang LSheng YShen M(2021)Pole-Like Objects Segmentation and Multiscale Classification-Based Fusion from Mobile Point Clouds in Road ScenesRemote Sensing10.3390/rs1321438213:21(4382)Online publication date: 30-Oct-2021
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in