Abstract
Label imbalance and the insufficiency of labeled training samples are major obstacles in most methods for counting people in images or videos. In this work, a sparse representation-based semi-supervised regression method is proposed to count people in images with limited data. The basic idea is to predict the unlabeled training data, select reliable samples to expand the labeled training set, and retrain the regression model. In the algorithm, the initial regression model, which is learned from the labeled training data, is used to predict the number of people in the unlabeled training dataset. Then, the unlabeled training samples are regarded as an over-complete dictionary. Each feature of the labeled training data can be expressed as a sparse linear approximation of the unlabeled data. In turn, the labels of the labeled training data can be estimated based on a sparse reconstruction in feature space. The label confidence in labeling an unlabeled sample is estimated by calculating the reconstruction error. The training set is updated by selecting unlabeled samples with minimal reconstruction errors, and the regression model is retrained on the new training set. A co-training style method is applied during the training process. The experimental results demonstrate that the proposed method has a low mean square error and mean absolute error compared with those of state-of-the-art people-counting benchmarks.
- S. Bai and X. Bai. 2016. Sparse contextual activation for efficient visual re-ranking. IEEE Transactions on Image Processing 25, 3, 1056--1069. Google Scholar
Digital Library
- A. B. Chan and N. Vasconcelos. 2012. Counting people with low-level features and Bayesian regression. IEEE Transactions on Image Processing 21, 4, 2160--2177. Google Scholar
Digital Library
- C. L. Chen et al. 2013. From semi-supervised to transfer counting of crowds. In Proceedings of the IEEE International Conference on Computer Vision. 2256--2263.Google Scholar
- K. Chen et al. 2012. Feature mining for localised crowd counting. In Proceedings of the British Machine Vision Conference. 1--11. Google Scholar
Cross Ref
- W. J. Chen et al. 2014. Laplacian smooth twin support vector machine for semi-supervised classification. International Journal of Machine Learning and Cybernetics 5, 3, 459--468. Google Scholar
Cross Ref
- Y. Cong et al. 2009. Flow mosaicking: Real-time pedestrian counting without scene-specific learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1093--1100. Google Scholar
Cross Ref
- H. Foroughi et al. 2015. Robust people counting using sparse representation and random projection. Pattern Recognition 48, 10, 3038--3052. Google Scholar
Digital Library
- C. Gao et al. 2016. People-flow counting in complex environments by combining depth and color information. Multimedia Tools and Applications 75, 15, 1--17. Google Scholar
Digital Library
- X. Guo and K. Uehara. 2015. Graph-based semi-supervised regression and its extensions. International Journal of Advanced Computer Science 8 Applications 6, 6.Google Scholar
- Y. L. Hou and G. K. H. Pang. 2011. People counting and human detection in a challenging situation. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans 41, 1, 24--33. Google Scholar
Digital Library
- C. L. Huang et al. 2011. People counting using ellipse detection and forward/backward tracing. In Proceedings of the 2011 1st Asian Conference on Pattern Recognition (ACPR). 505--509.Google Scholar
- S. Karaman et al. 2014. Leveraging local neighborhood topology for large scale person re-identification. Pattern Recognition 47, 12, 3767--3778. Google Scholar
Cross Ref
- L. Maddalena et al. 2014. People counting by learning their appearance in a multi-view camera environment. Pattern Recognition Letters 36, 125--134. Google Scholar
Digital Library
- D. Merad et al. 2010. Fast people counting using head detection from skeleton graph. In Proceedings of the 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). 233--240. Google Scholar
Digital Library
- S. Mukherjee et al. 2015. Unique people count from monocular videos. The Visual Computer 31, 10, 1405--1417. Google Scholar
Digital Library
- A. Oliva and A. Torralba. 2001. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision 42, 3, 145--175. Google Scholar
Digital Library
- C. Raghavachari et al. 2015. A comparative study of vision based human detection techniques in people counting applications. Procedia Computer Science 58, 461--469. Google Scholar
Cross Ref
- R. Raina et al. 2007. Self-taught learning: Transfer learning from unlabeled data. In Proceedings of the International Conference on Machine Learning. 759--766. Google Scholar
Digital Library
- D. Ryan et al. 2015. An evaluation of crowd counting methods, features and regression models. Computer Vision 8 Image Understanding 130, C, 1--17.Google Scholar
- B. Tan et al. 2011. Semi-supervised elastic net for pedestrian counting. Pattern Recognition 44, 10-11, 2297--2304. Google Scholar
Digital Library
- J. Tang et al. 2011. Image annotation by kNN-sparse graph-based label propagation over noisily tagged web images. ACM Transactions on Intelligent Systems 8 Technology 2, 2, 14.Google Scholar
- J. Wang et al. 2014. Semi-supervised learning via geodesic weighted sparse representation. IEICE Transactions on Information 8 Systems E97.D, 6, 1673--1676.Google Scholar
- W. Xia et al. 2015. Semisupervised pedestrian counting with temporal and spatial consistencies. IEEE Transactions on Intelligent Transportation Systems 16, 4, 1--11. Google Scholar
Digital Library
- A. Y. Yang et al. 2010. Fast ℓ1-minimization algorithms and an application in robust face recognition: A review. Technical Report, EECS Department, University of California, Berkeley: 1849--1852. Google Scholar
Cross Ref
- G. Yu et al. 2015. Semi-supervised classification based on subspace sparse representation. Knowledge and Information Systems 43, 1, 81--101. Google Scholar
Digital Library
- C. Zeng and H. Ma. 2010. Robust head-shoulder detection by PCA-based multilevel HOG-LBP detector for people counting. In Proceedings of the International Conference on Pattern Recognition. 2069--2072. Google Scholar
Digital Library
- Z. H. Zhou and M. Li. 2007. Semi-supervised regression with co-training style algorithms. IEEE Transactions on Knowledge 8 Data Engineering 19, 11, 1479--1493.Google Scholar
Digital Library
Index Terms
Sparse Representation-Based Semi-Supervised Regression for People Counting
Recommendations
On semi-supervised linear regression in covariate shift problems
Semi-supervised learning approaches are trained using the full training (labeled) data and available testing (unlabeled) data. Demonstrations of the value of training with unlabeled data typically depend on a smoothness assumption relating the ...
Semi-supervised regression: A recent review
Special Section: Ambient advancements in intelligent computational sciencesNowadays, Semi-Supervised Learning lies at the core of the Machine Learning field trying to effectively exploit unlabeled data as much as possible, together with a small amount of labeled data aiming to improve the predictive performance. Depending on the ...
Semi-supervised learning with local and global consistency by geodesic distance and sparse representation
IScIDE'12: Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data EngineeringIn many practical data mining applications, such as web categorization, key gene selection, etc., generally, unlabeled training examples are readily available, but labeled ones are fairly expensive to obtain. Therefore, in recent years, semi-supervised ...






Comments