Browsing by Author "Lee, Suh-Yin"

Now showing 1 - 20 of 68

2D Histogram-based player localization in broadcast volleyball videos
(2016-06)
Hsu, Chun-Chieh
;
Chen, Hua-Tsung
;
Chou, Chien-Li
;
Lee, Suh-Yin
;
資訊工程學系
Player location is one of the most informative cues for obtaining tactics arrangement and collecting descriptive game statistics. However, state-of-the-art supervised learning-based methods for player localization require a large amount of labeled training data. Hence, the development of automatic systems for player localization becomes indispensable. Volleyball games reach a huge audience base and contain a variety of tactical strategies, necessitating the implementation of systems for inferring tactics and analyzing formations automatically. Therefore, a novel 2D histogram-based player localization method capable of locating players with occlusions is developed and presented in this paper. The proposed system is able to automatically detect the court lines for camera calibration, extract players by calculating both x and y histograms of extracted player masks, and visualize the team formations on real-world court model. The experiments on broadcast volleyball videos demonstrate efficient and effective results against a traditional object segmentation method (connected component analysis) and a supervised learning approach utilizing histogram of oriented gradient features.
A baseball exploration system using spatial pattern recognition
(2008)
Chen, Hua-Tsung
;
Hsiao, Ming-Ho
;
Chen, Hsuan-Shen
;
Tsai, Wen-Jiin
;
Lee, Suh-Yin
Despite a lot of research efforts in baseball video processing, little work has been done in analyzing the detailed process and ball movement of the batting content. This paper proposes a novel system to automatically summarize the progress of each batting in baseball videos. Utilizing the strictly-defined specifications of the baseball field, the system recognizes the spatial patterns in each frame and identifies what region of the baseball field is currently focused. Finally, an annotation string which abstracts the batting content is generated. With the annotation strings, the system is able to make descriptions and provide exploration for baseball videos, so that users can be given a further insight into the game quickly. The experiments on broadcast baseball videos of MLB and JPB show promising results.
A new algorithm for maintaining closed frequent itemsets in data streams by incremental updates
(2006)
Li, Hua-Fu
;
Ho, Chin-Chuan
;
Kuo, Fang-Fei
;
Lee, Suh-Yin
;
資訊工程學系
Online mining of closed frequent itemsets over streaming data is one of the most important issues in mining data streams. In this paper, we propose an efficient one-pass algorithm, NewMoment to maintain the set of closed frequent itemsets in data streams with a transaction-sensitive sliding window. An effective bit-sequence representation of items is used in the proposed algorithm to reduce the time and memory needed to slide the windows. Experiments show that the proposed algorithm not only attain highly accurate mining results, but also run significant faster and consume less memory than existing algorithm Moment for mining closed frequent itemsets over recent data streams.
A NOVEL VIDEO ANNOTATION FRAMEWORK USING NEAR-DUPLICATE SEGMENT DETECTION
(2015)
Chou, Chien-Li
;
Chen, Hua-Tsung
;
Hsu, Chun-Chieh
;
Lee, Suh-Yin
;
資訊工程學系
The traditional video annotation approaches focus on annotating keyframes, shots, or the whole video with semantic keywords. However, the extractions of keyframes and shots lack of semantic meanings, and it is hard to use a few keywords to describe a video by using multiple topics. Therefore, we propose a novel video annotation framework using near-duplicate segment detection not only to preserve but also to purify the semantic meanings of target annotation units. A hierarchical near-duplicate segment detection method is proposed to efficiently localize near-duplicate segments in frame-level. Videos containing near-duplicate segments are clustered and keyword distributions of clusters are analyzed. Finally, the keywords ranked according to keyword distribution scores are annotated onto the obtained annotation units. Comprehensive experiments demonstrate the effectiveness of the proposed video annotation framework and near-duplicate segment detection method.
A Parametric Window Design for OBMC with Variable Block Size Motion Estimates
(2009)
Chen, Yi-Wen
;
Wang, Tse-Wei
;
Tseng, Yu-Cheng
;
Peng, Wen-Hsiao
;
Lee, Suh-Yin
This paper addresses the problem of adapting overlapped block motion compensation (OBMC) windows for use with variable blocksize motion estimates. We tackle the problem by using a parametric window design, which expresses, based on a statistical motion model, the optimal weights as a function of the distances between the predicted pixel and its nearby block centers. The formula enables both prediction weights and prediction order to be adapted on a pixel-by-pixel basis. Extensive experiments have been conducted using JM 12.4. Compared with conventional block motion compensation, our scheme shows a bitrate saving of 18%, (5% on average) while maintaining the same or even higher PSNR (0.1 dB). It also provides a competitive advantage to variable block size motion compensation. Additionally, a hybrid of the two techniques achieves a further bitrate reduction of 13%. The result, nevertheless, provides only a lower bound on what is achievable since both motion estimation and mode decision were accomplished without considering OBMC. Further improvement is expected by incorporating iterative methods.
A Robust Vision-Based Heart Rate Evaluation
(2015-01-01)
Lin, Kuan-Yi
;
Chen, Duan-Yu
;
Lee, Suh-Yin
;
資訊工程學系
;
Department of Computer Science
Monitoring heart rates using conventional electrocardiogram (ECG) equipment requires patients to wear adhesive gel patches or chest straps that can cause skin irritation and discomfort. Commercially-available pulse oximetry sensors that attach to the fingertips or earlobes also cause inconvenience for patients and the spring-loaded clips can be painful to use. Therefore, a novel robust face-based heart rate monitoring technique is proposed to allow for the evaluation of heart rate variation without physical contact with the patient. Face reflectance is first decomposed from a single image and then heart rate evaluation is conducted from consecutive frames according to the periodic variation of reflectance strength resulting from changes to hemoglobin absorptivity across the visible light spectrum as heartbeats cause changes to blood volume in the blood vessels in the face. To achieve a robust evaluation, ensemble empirical mode decomposition (EEMD) of the Hilbert-Huang Transform (HHT) is used to acquire the primary heart rate signal while reducing the effect of ambient light changes. Our proposed approach is found to outperform the current stateo-f-the-art, providing greater measurement accuracy with smaller variance and is shown to be feasible in real-world environments.
A SINGLE-SCAN ALGORITHM FOR MINING SEQUENTIAL PATTERNS FROM DATA STREAMS
(2012-03-01)
Li, Hua-Fu
;
Ho, Chin-Chuan
;
Chen, Hsuan-Sheng
;
Lee, Suh-Yin
;
資訊工程學系
Sequential pattern mining (SPAM) is one of the most interesting research issues of data mining. In this paper, a new research problem of mining data streams for sequential patterns is defined. A data stream is an unbound sequence of data elements arriving at a rapid rate. Based on the characteristics of data streams, the problem complexity of mining data streams for sequential patterns is more difficult than that of mining sequential patterns from large static databases. Therefore, mining sequential patterns from data streams is a challenging research issue of data mining and knowledge discovery. Hence, an efficient single-pass algorithm, called IncSparn (Incremental Sequential pattern mining of streaming itemset-sequences), is proposed for discovering sequential patterns from streaming itemset-sequences over extended sliding window models. In the framework of IncSpam algorithm, a new sliding window model, called CSW-BV (Customer Sliding Window with Bit-Vectors), and an extended lexicographic tree-based data structure, called LesSeq-Tree (Lexicographic Sequence Tree), are developed to reduce the time and memory needed to slide the windows over streaming data and maintain all sequential patterns of current sliding windows. Experimental results show that the proposed method is an efficient single-pass algorithm for mining sequential patterns from streaming data.
A System for Front Vehicle Detection and Fast Indexing Using a Single Car-Mounted Camera
(2015-01-01)
Hsu, Chun-Chieh
;
Wu, Yi-Chien
;
Chen, Hua-Tsung
;
Lee, Suh-Yin
;
交大名義發表
Video safety becomes a recently arising issue in the automobile industry due to the rapid expansion of car ownership worldwide. Increasing driver assistance systems have been developed for security and accident prevention by continuously monitoring the vehicle surroundings and the driving behaviors to detect potential problems in advance. Since most traffic/criminal accidents are caused by vehicles, recognizing and tracking the fleeing vehicles on the roads are of vital importance. In this paper, we propose a vision-based front vehicle detection and fast indexing system using a single car-mounted camera, which tends to be widespread deployed. First, front vehicle candidates are detected by a cascade of Gentle Adaboost classifiers utilizing Histogram of Oriented Gradients features. To improve the detection accuracy, symmetry of taillights are further employed to filter out the false detected candidates. Once a vehicle is detected, the GPS locations are reported to a central server, so that a database of detections can be maintained and can be provided to the related departments for timely retrieving and quickly indexing the searched vehicles on the maps. Experiments conducted on real videos demonstrate that satisfactory results can be obtained by the proposed detection scheme.
A tempo analysis system for automatic musk accompaniment
(2007)
Chen, Hua-Tsung
;
Hsiao, Ming-Ho
;
Tsai, Wen-Jiin
;
Lee, Suh-Yin
;
Yu, Jen-Yu
This paper proposes a music accompaniment system capable of catching the tempo of music. The original signal is first reduced to a detection function revealing the pulses of music. To induce the tempo and locate beats, a Fourier analysis-based algorithm with high practicality and generality is designed that it is robust to beat strength and not restricted to specific music genres. The regularity and periodicity of music beats are extracted and even the missing beats are recovered. The performance is validated using a comprehensive testing data set, and results in both formal objective experiments and subjective listening evaluations show convincible performance. Moreover, an interactive interface is designed that users are allowed to select an instrument to accompany the music based on the obtained tempo.
A trajectory-based ball tracking framework with visual enrichment for broadcast baseball videos
(2008-01-01)
Chen, Hua-Tsung
;
Chen, Hsuan-Sheng
;
Hsiao, Ming-Ho
;
Tsai, Wen-Jiin
;
Lee, Suh-Yin
Pitching contents play the key role in the resultant victory or defeat in a baseball game. Utilizing the physical characteristic of ball motion, this paper presents a trajectory-based framework for automatic ball tracking and pitching evaluation in broadcast baseball videos. The task of ball detection and tracking in broadcast baseball videos is very challenging because in video frames, the noises may cause many ball-like objects, the ball size is small, and the ball may deform due to its high speed movement. To overcome these challenges, we first define a set of filters to prune most non-ball objects but retain the ball, even if it is deformed. In ball position prediction and trajectory extraction, we analyze the 2D distribution of ball candidates and exploit the characteristic that the ball trajectory presents in a near parabolic curve in video frames. Most of the non-qualified trajectories are pruned, which greatly improves the computational efficiency. The missed balls can also be recovered in the trajectory by applying the position prediction. The experiments of ball tracking on the testing sequences of JPB, MLB and CPBL captured from different TV channels show promising results. The ball tracking framework is able to extract the ball trajectory, superimposed on the video, and in near real-time provide visual enrichment before the next pitch coming up without specific cameras or equipments set up in the stadiums. It can also be utilized in strategy analysis and intelligence statistics for player training.
A view-invariant and anti-reflection algorithm for car body extraction and color classification
(2013-08-01)
Gu, Hui-Zhen
;
Lee, Suh-Yin
;
資訊工程學系
;
Department of Computer Science
This study proposes an intelligent algorithm with tri-state architecture for real-time car body extraction and color classification. The algorithm is capable of managing both the difficulties of viewpoint and light reflection. Because the influence of light reflection is significantly different on bright, dark, and colored cars, three different strategies are designed for various color categories to acquire a more intact car body. A SARM (Separating and Re-Merging) algorithm is proposed to separate the car body and the background, and recover the entire car body more completely. A robust selection algorithm is also performed to determine the correct color category and car body. Then, the color type of the vehicle is decided only by the pixels in the extracted car body. The experimental results show that the tri-state method can extract almost 90% of car body pixels from a car image. Over 98% of car images are distinguished correctly in their categories, and the average accuracy of the 10-color-type classification is higher than 93%. Furthermore, the computation load of the proposed method is light; therefore it is applicable for real-time systems.
Automatic closed caption detection and filtering in MPEG videos for video structuring
(2006-09-01)
Chen, Duan-Yu
;
Hsiao, Ming-Ho
;
Lee, Suh-Yin
;
資訊工程學系
;
Department of Computer Science
Video structuring is the process of extracting temporal structural information of video sequences and is a crucial step in video content analysis especially for sports videos. It involves detecting temporal boundaries, identifying meaningful segments of a video and then building a compact representation of video content. Therefore, in this paper, we propose a novel mechanism to automatically parse sports videos in compressed domain and then to construct a concise table of video content employing the superimposed closed captions and the semantic classes of video shots. First of all, shot boundaries are efficiently examined using the approach of GOP-based video segmentation. Color-based shot identification is then exploited to automatically identify meaningful shots. The efficient approach of closed caption localization is proposed to first detect caption frames in meaningful shots. Then caption frames instead of every frame are selected as targets for detecting closed captions based on long-term consistency without size constraint. Besides, in order to support discriminate captions of interest automatically, a novel tool - font size detector is proposed to recognize the font size of closed captions using compressed data in MPEG videos. Experimental results show the effectiveness and the feasibility of the proposed mechanism.
Automatic Restaurant Information and Keyword Extraction by Mining Blog Data for Chinese Restaurant Search
(2014-01-01)
Chou, Chien-Li
;
Tsai, Min-Ho
;
Chao, Chien-Ho
;
Lin, Hsiao-Jung
;
Chen, Hua-Tsung
Restaurant search and recommendation system is a very popular service in many countries. In those systems, most of the restaurant information such as restaurant name, address, phone number, and introduction are collected manually. In this paper, we propose a restaurant information extraction method which can automatically extract restaurant information from online reviews of restaurants in blogs. In addition, by calculating TFIDFs of words in blog posts, the hot keywords can be discovered and ranked. For restaurant search, users are allowed to search by keywords, areas, and/or extracted hot keywords. The experimental results show that the proposed method can achieve over 90 % average accuracy of hot keyword extraction and about 95 % mean average precision for restaurant search. In user study, the fact that the proposed system is more useful than Google search in restaurant search is presented.
Ball tracking and 3D trajectory approximation with applications to tactics analysis from single-camera volleyball sequences
(2012-10-01)
Chen, Hua-Tsung
;
Tsai, Wen-Jiin
;
Lee, Suh-Yin
;
Yu, Jen-Yu
;
資訊工程學系
Providing computer-assisted tactics analysis in sports is a growing trend. This paper presents an automatic system for ball tracking and 3D trajectory approximation from single-camera volleyball sequences as well as demonstrates several applications to tactics analysis. Ball tracking in volleyball video has great complexity due to the high density of players on the court and the complicated overlapping of ball-player. The 2D-to-3D inference is intrinsically challenging due to the loss of 3D information in projection to 2D frames. To overcome these challenges, we propose a two-phase ball tracking algorithm in which we first detect ball candidates for each frame, and then use them to compute the ball trajectories. With the aid of camera calibration, we involve physical characteristics of ball motion to approximate the 3D ball trajectory from the 2D trajectory. The visualization of 3D trajectory and the applications to trajectory-based tactics analysis not only assist the coaches and players in game study but also make game watching a whole new experience. The experiments on international volleyball games show encouraging results. We believe that the proposed framework can be extended and applied to various kinds of sports games.
Baseball Event Semantic Exploring System Using HMM
(2011)
Tsai, Wei-Chin
;
Chen, Hua-Tsung
;
Gu, Hui-Zhen
;
Lee, Suh-Yin
;
Yu, Jen-Yu
Despite a lot of research efforts in baseball video processing in recent years, little work has been done in analyzing the detailed semantic baseball event detection. This paper presents an effective and efficient baseball event classification system for broadcast baseball videos. Utilizing the specifications of the baseball field and the regularity of shot transition, the system recognizes highlight in video clips and identifies what semantic baseball event of the baseball clips is currently proceeding. First, a video is segmented into several highlights starting with a PC (Pitcher and Catcher) shot and ending up with some specific shots. Before every baseball event classifier is designed, several novel schemes including some specific features such as soil percentage and objects extraction such as first base are applied. The extracted mid-level cues are used to develop baseball event classifiers based on an HMM (Hidden Markov model). Due to specific features detection, more hitting baseball events are detected and the simulation results show that the classification of twelve significant baseball events is very promising.
Car model recognition by utilizing symmetric property to overcome severe pose variation
(2013-02-01)
Gu, Hui-Zhen
;
Lee, Suh-Yin
;
資訊工程學系
;
Department of Computer Science
This paper presents a mirror morphing scheme to deal with the challenging pose variation problem in car model recognition. Conventionally, researchers adopt pose estimation techniques to overcome the pose problem, whereas it is difficult to obtain very accurate pose estimation. Moreover, slight deviation in pose estimation degrades the recognition performance dramatically. The mirror morphing technique utilizes the symmetric property of cars to normalize car images of any orientation into a typical view. Therefore, the pose error and center bias can be eliminated and satisfactory recognition performance can be obtained. To support mirror morphing, active shape model (ASM) is used to acquire car shape information. An effective pose and center estimation approach is also proposed to provide a good initialization for ASM. In experiments, our proposed car model recognition system can achieve very high recognition rate (> 95%) with very low probability of false alarm even when it is dealing with the severe pose problem in the cases of cars with similar shape and color.
CIM: Community-Based Influence Maximization in Social Networks
(2014-04-01)
Chen, Yi-Cheng
;
Zhu, Wen-Yuan
;
Peng, Wen-Chih
;
Lee, Wang-Chien
;
Lee, Suh-Yin
Given a social graph, the problem of influence maximization is to determine a set of nodes that maximizes the spread of influences. While some recent research has studied the problem of influence maximization, these works are generally too time consuming for practical use in a large-scale social network. In this article, we develop a new framework, community-based influence maximization (CIM), to tackle the influence maximization problem with an emphasis on the time efficiency issue. Our proposed framework, CIM, comprises three phases: (i) community detection, (ii) candidate generation, and (iii) seed selection. Specifically, phase (i) discovers the community structure of the network; phase (ii) uses the information of communities to narrow down the possible seed candidates; and phase (iii) finalizes the seed nodes from the candidate set. By exploiting the properties of the community structures, we are able to avoid overlapped information and thus efficiently select the number of seeds to maximize information spreads. The experimental results on both synthetic and real datasets show that the proposed CIM algorithm significantly outperforms the state-of-the-art algorithms in terms of efficiency and scalability, with almost no compromise of effectiveness.
COHERENT EVENT-BASED SURVEILLANCE VIDEO SYNOPSIS USING TRAJECTORY CLUSTERING
(2015)
Chou, Chien-Li
;
Lin, Chin-Hsien
;
Chiang, Tzu-Hsuan
;
Chen, Hua-Tsung
;
Lee, Suh-Yin
With the rapid development of the camera industry, surveillance systems become more and more popular in our daily life. However, it is very time-consuming to find out specific persons or objects from a mass of surveillance videos with long duration. For efficient browsing surveillance videos, numerous researchers are devoted to eliminating the inherent spatiotemporal redundancy for video synopsis. Nevertheless, too much information in a synopsis frame may distract viewers\' attention. Therefore, we propose a novel surveillance video synopsis system using coherent event classification to alleviate the above issues. Object trajectories are extracted by background subtraction, and then clustered. Coherent events containing similar actions of objects with different moving speeds are obtained by applying the longest common subsequence algorithm to measure the similarity among trajectories. The trajectories in each cluster are rescheduled and stitched onto the background to generate synopsis videos with coherent events. Comprehensive experiments conducted on various surveillance videos demonstrate the convincing performance of our proposed system.
Computer-assisted Billiard Self-Training Using Intelligent Glasses
(2017-01-01)
Hsu, Chun-Chieh
;
Tsai, Hou-Chun
;
Chen, Hua-Tsung
;
Tsai, Wen-Jiin
;
Lee, Suh-Yin
Self-training plays an important role in sports exercise. However, if not under the instruction of a coach, it would be ineffective for most amateurs or inexperienced players to exercise on their own. Therefore, establishing computer-assisted training systems for sports exercise is a recently emerging topic. In this paper, we propose a billiard self-training system, which aims at improving billiard players' performance by utilizing intelligent glasses as a wearable camera and displayer. The proposed system is able to automatically analyze user-captured images of the billiard table from multiple views and display the ball configurations on a virtual top-view table. Enriched visual presentation can be provided to give the practitioner a further sight into the game. The experiments conducted on sixteen sets of different ball configurations show promising results.
COMPUTER-ASSISTED SELF-TRAINING SYSTEM FOR SPORTS EXERCISE USING KINECTS
(2013)
Chen, Hua-Tsung
;
He, Yu-Zhen
;
Chou, Chien-Li
;
Lee, Suh-Yin
;
Lin, Bao-Shuh P.
Self-training plays an important role in sports exercise. However, if not under the instruction of a coach, improper training postures can cause serious harm to muscles and ligaments of the body. Hence, the development of computer-assisted self-training systems for sports exercise is a recently emerging research topic. In this paper, we propose a Yoga self-training system, entitled YogaST, which aims at instructing the user/practitioner to perform the asana (Yoga posture) correctly and preventing injury caused by improper postures. Involving professional Yoga training knowledge, YogaST analyzes the practitioner's posture from both front and side views using two Kinects with perpendicular viewing directions and assists him/her in rectifying bad postures. The contour, skeleton, and feature axes of the human body are extracted as posture representation. Then, YogaST analyzes the practitioner's posture and presents visualized instruction for posture rectification so that the practitioner can easily understand how to adjust his/her posture.