-
IEICE Transactions. 01/2012; 95-D:699-702.
-
[show abstract]
[hide abstract]
ABSTRACT: In online tracking, the tracker evolves to reflect variations in object appearance and surroundings. This updating process is formulated as a supervised learning problem, thus a slight inaccuracy of the tracker will degrade the updating. Multiple Instance Learning (MIL) is used to alleviate such a problem by representing training samples in bags of image patches (or called instances). Difficulties are then passed on to the learning method to train a classifier that discovers the most accurate instance. This paper proposes a Maximizing Bag's Margin (MBM) criteria for MIL. Combined with MBM, a hierarchical boosting is proposed for updating, in which bag and instance weights are introduced to guide classifier retrain ing. Our approach effectively improves the updating's efficiency with less computation cost. Experiments demonstrate the benefits of our method.
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on; 06/2011 · 4.63 Impact Factor
-
IEICE Transactions. 01/2011; 94-D:1721-1724.
-
IEICE Transactions. 01/2011; 94-D:1700-1707.
-
IEICE Transactions. 01/2011; 94-D:930-933.
-
IEICE Transactions. 01/2011; 94-A:979-989.
-
Pattern Recognition Letters. 01/2011; 32:1564-1571.
-
IEICE Transactions. 01/2011; 94-D:2549-2552.
-
IEICE Transactions. 01/2011; 94-D:2541-2544.
-
[show abstract]
[hide abstract]
ABSTRACT: A novel approach for detecting anomaly in visual surveillance system is proposed in this paper. It is composed of three parts:(a) a dense motion field and motion statistics method, (b) one-class SVM for one-class classification, (c) motion directional PCA for feature dimensionality reduction. Experiments demonstrate the effectiveness of proposed algorithm in detecting abnormal events in surveillance video, while keeping a low false alarm rate. Moreover, it works well in complicated situation where the common tracking or detection module won't work.
Image Processing (ICIP), 2010 17th IEEE International Conference on; 10/2010
-
[show abstract]
[hide abstract]
ABSTRACT: This paper introduces a topology based affine invariant descriptor for maximally stable extremal regions (MSERs). The popular SIFT descriptor computes the texture information on a grey-scale patch. Instead our descriptor use only the topology and geometric information among MSERs so that features can be rapidly matched regardless of the texture in the image patch. Based on the ellipses fitting for the detected MSERs, geometric affine invariants between ellipses pair are extracted as the descriptors. Finally topology based voting selector is designed to achieve the best correspondences. Experiment shows that our descriptor is not only computational faster than SIFT descriptor, but also has better performance on wide angle of view and nonlinear illumination change. In addition, our descriptor shows a good result on multi sensor images registration.
Image Processing (ICIP), 2010 17th IEEE International Conference on; 10/2010
-
IEICE Transactions. 01/2010; 93-D:658-661.
-
IEICE Transactions. 01/2010; 93-D:1317-1320.
-
IEICE Transactions. 01/2010; 93-D:662-665.
-
IEICE Transactions. 01/2010; 93-B:3161-3164.
-
Proceedings of the International Conference on Image Processing, ICIP 2010, September 26-29, Hong Kong, China; 01/2010
-
IEICE Transactions. 01/2010; 93-D:1321-1324.
-
IEICE Transactions. 01/2009; 92-A:1737-1742.
-
Proceedings of the 2009 IEEE International Conference on Multimedia and Expo, ICME 2009, June 28 - July 2, 2009, New York City, NY, USA; 01/2009
-
[show abstract]
[hide abstract]
ABSTRACT: Kernel based object tracking (KBOT) is one of the most popular and effective techniques for tracking task. However the constancy of the target model and unsound scale adaptation method are two main limitations. In this paper, we present a kernel based approach incorporated with scale estimation and target model update for articulated object tracking task. After predicating the object center with scale fixed KBOT, we extend scale selection theory to estimate the local optimal object scale. Once the object scale has been estimated, a kernel density estimation based strategy is developed to update the target model. Experimental results show that our approach is superior to traditional KBOT in the following two aspects: 1) it is less affected by the object scale change; 2) it is less prone to appearance variation.
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on; 05/2008 · 4.63 Impact Factor