Browsing by Author "Liu, Tyng-Luh"

Now showing 1 - 5 of 5

Improving local learning for object categorization by exploring the effects of ranking
(2008)
Chang, Tien-Lung
;
Liu, Tyng-Luh
;
Chuang, Jen-Hui
;
資訊工程學系
;
Department of Computer Science
Local learning for classification is useful in dealing with various vision problems. One key factor for such approaches to be effective is to find good neighbors for the learning procedure. In this work we describe a novel method to rank neighbors by learning a local distance function, and meanwhile to derive the local distance function by focusing on the high-ranked neighbors. The two aspects of considerations can be elegantly coupled through a well-defined objective function, motivated by a supervised ranking method called P-Norm Push. While the local distance functions are learned independently, they can be reshaped altogether so that their values can be directly compared. We apply the proposed method to the Caltech-101 dataset, and demonstrate the use of proper neighbors can improve the performance of classification techniques based on nearest-neighbor selection.
Learning a Scene Background Model via Classification
(2009-05-01)
Lin, Horng-Horng
;
Liu, Tyng-Luh
;
Chuang, Jen-Hui
;
資訊工程學系
;
Department of Computer Science
Learning to efficiently construct a scene background model is crucial for tracking techniques relying on background subtraction. Our proposed method is motivated by criteria leading to what a general and reasonable background model should be, and realized by a practical classification technique. Specifically, we consider a two-level approximation scheme that elegantly combines the bottom-up and top-down information for deriving a background model in real time. The key idea of our approach is simple but effective: If a classifier can be used to determine which image blocks are part of the background, its outcomes can help to carry out appropriate blockwise updates in learning such a model. The quality of the solution is further improved by global validations of the local updates to maintain the interblock consistency. And a complete background model can then be obtained based on a measurement of model completion. To demonstrate the effectiveness of our method, various experimental results and comparisons are included.
Object-detection method multi-class Bhattacharyya Boost algorithm used therein
(2006-11-02)
Liu, Tyng-Luh
;
Lin, Yen-Yu
The present invention discloses an object-detection method and a multi-class Bhattacharyya Boost algorithm used therein, wherein firstly, integral images are calculated from an image data in order to speed up the extraction of the characteristics of the objects; then, multiple rectangles of different sizes are scanned at different locations of the image data, and the multi-class Bhattacharyya Boost algorithm is used to detect multi-class objects. In the present invention, the detection framework can use only one single boosted cascade to determine the status and position of the object inside the image data. The simultaneous multi-class detection of the present invention can effectively overcome the detection difficulties resulting from the diversification of object appearances under different conditions. Therefore, the present invention can detect multiple objects simultaneously and can also detect one object having multiple classes of appearances, and further, the detection speed and the system robustness of the present invention are superior to those of the conventional technologies.
Regularized Background Adaptation: A Novel Learning Rate Control Scheme for Gaussian Mixture Modeling
(2011-03-01)
Lin, Horng-Horng
;
Chuang, Jen-Hui
;
Liu, Tyng-Luh
;
資訊工程學系
;
Department of Computer Science
To model a scene for background subtraction, Gaussian mixture modeling (GMM) is a popular choice for its capability of adaptation to background variations. However, GMM often suffers from a tradeoff between robustness to background changes and sensitivity to foreground abnormalities and is inefficient in managing the tradeoff for various surveillance scenarios. By reviewing the formulations of GMM, we identify that such a tradeoff can be easily controlled by adaptive adjustments of the GMM's learning rates for image pixels at different locations and of distinct properties. A new rate control scheme based on high-level feedback is then developed to provide better regularization of background adaptation for GMM and to help resolving the tradeoff. Additionally, to handle lighting variations that change too fast to be caught by GMM, a heuristic rooting in frame difference is proposed to assist the proposed rate control scheme for reducing false foreground alarms. Experiments show the proposed learning rate control scheme, together with the heuristic for adaptation of over-quick lighting change, gives better performance than conventional GMM approaches.
Spatio-Temporal Learning of Basketball Offensive Strategies
(2015)
Chen, Ching-Hang
;
Liu, Tyng-Luh
;
Wang, Yu-Shuen
;
Chu, Hung-Kuo
;
Tang, Nick C.
Video-based group behavior analysis is drawing attention to its rich applications in sports, military, surveillance and biological observations. The recent advances in tracking techniques, based on either computer vision methodology or hardware sensors, further provide the opportunity of better solving this challenging task. Focusing speci fi cally on the analysis of basketball o ff ensive strategies, we introduce a systematic approach to establishing unsupervised modeling of group behaviors. In view that a possible group behavior (offensive strategy) could be of di ff erent duration and represented by dynamic player trajectories, the crux of our method is to automatically divide training data into meaningful clusters and learn their respective spatio-temporal model, which is established upon Gaussian mixture regression to account for intra-class spatio-temporal variations. The resulting strategy representation turns out to be flexible that can be used to not only establish the discriminant functions but also improve learning the models. We demonstrate the usefulness of our approach by exploring its e ff ectiveness in analyzing a set of given basketball video clips.