Browsing by Author "Chen, Yen-Lin"

Now showing 1 - 20 of 29

A CUSTOMIZED AND PORTABLE COMPONENT-BASED FRAMEWORK FOR INTELLIGENT HOMECARE SYSTEM DESIGN WITH VIDEO AND PHYSIOLOGICAL MONITORING MACHINERIES
(2011-10-01)
Chen, Yen-Lin
;
Chiang, Chuan-Yen
;
Yu, Chao-Wei
;
Yuan, Shyan-Ming
;
Hong, Zeng-Wei
This study proposes a customized and reusable component-based design framework based on the UML modeling process for intelligent home healthcare systems. All the proposed functional components are reusable, replaceable, and extensible for the system developers to implement customized home healthcare systems addressing different demands of patients and caregivers from healthcare monitoring aspects. The prototype design of the intelligent healthcare system based on these proposed components can provide the following features: (1) monitoring and recording videos of rehabilitation situations and patient behavior using multiple CCD cameras, which can be stored accordingly in an archive; (2) recording the patient's physiological data and corresponding treatment plan, which can be stored in an XML archiving database for caregivers' review; (3) automatically alerting patients to remind them of medication schedules or treatment plans, while recording the patient's treatment situations; (4) caregivers monitoring videos and physiological records of the patient's rehabilitation using handheld mobile devices via the Internet or wireless communication networks; and (5) caregivers and patients establishing alert mechanisms for the patients' physiological warning states. If the patient's physiological state suddenly deteriorates, the module would immediately alert caregivers by sending notification messages to their remote mobile devices or web browsers.
A multi-plane approach for text segmentation of complex document images
(2009-07-01)
Chen, Yen-Lin
;
Wu, Bing-Fei
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This study presents a new method, namely the multiplane segmentation approach, for segmenting and extracting textual objects from various real-life complex document images. The proposed multi-plane segmentation approach first decomposes the document image into distinct object planes to extract and separate homogeneous objects including textual regions of interest, non-text objects such as graphics and pictures, and background textures. This process consists of two stages-localized histogram multilevel thresholding and multi-plane region matching and assembling. Then a text extraction procedure is applied Oil the resultant planes to detect and extract textual objects with different characteristics in the respective planes. The proposed approach processes document images regionally and adaptively according to their respective local features. Hence detailed characteristics of the extracted textual objects, Particularly small characters with thin strokes, as well as gradational illuminations of characters, can be well-preserved. Moreover, this way also allows background objects with uneven, gradational, and sharp variations in contrast, illumination, and texture to be handled easily and well. Experimental results on real-life complex document images demonstrate that the proposed approach is effective in extracting textual objects with Various illuminations, sizes, and font styles from various types of complex document images. (C) 2008 Elsevier Ltd. All rights reserved.
A Project-based Curriculum for Teaching C plus plus Object-Oriented Programming
(2012)
Chen, Yen-Lin
;
Chiang, Chuan-Yen
;
Huang, Yo-Ping
;
Yuan, Shyan-Ming
;
資訊工程學系
This paper presented a project-based remedial curriculum for teaching the C++ programming language and object-oriented programming (OOP) skills and concepts. The pedagogical approach of the proposed curriculum comprises of a set of homemade projects for facilitating the students to quickly learn the essential C++ and OOP skills by accordingly implementing a large-scale communication software system. Based on the constructivist learning technology, the proposed project-based curriculum can effectively improve and enhance the learning effectiveness and interests of the students via the hands-on, minds-on, and learning by doing practices related to their lives. From the students\' survey and grade assessment results, the proposed project-based curriculum and practical homemade projects demonstrates its effectiveness and feasibility for motivating the students\' interests on C++ and OOP skills and incorporating these skills for developing practical and large-scale software.
A Real-Time Vision System for Nighttime Vehicle Detection and Traffic Surveillance
(2011-05-01)
Chen, Yen-Lin
;
Wu, Bing-Fei
;
Huang, Hao-Yu
;
Fan, Chung-Jui
;
電控工程研究所
This paper presents an effective traffic surveillance system for detecting and tracking moving vehicles in nighttime traffic scenes. The proposed method identifies vehicles by detecting and locating vehicle headlights and taillights using image segmentation and pattern analysis techniques. First, a fast bright-object segmentation process based on automatic multilevel histogram thresholding is applied to effectively extract bright objects of interest. This automatic multilevel thresholding approach provides a robust and adaptable detection system that operates well under various nighttime illumination conditions. The extracted bright objects are then processed by a spatial clustering and tracking procedure that locates and analyzes the spatial and temporal features of vehicle light patterns, and identifies and classifies moving cars and motorbikes in traffic scenes. The proposed real-time vision system has also been implemented and evaluated on a TI DM642 DSP-based embedded platform. The system is set up on elevated platforms to perform traffic surveillance on real highways and urban roads. Experimental results demonstrate that the proposed traffic surveillance approach is feasible and effective for vehicle detection and identification in various nighttime environments.
A Traffic Video Searching and Sharing Platform based on Smart Wearable Devices
(2014-01-01)
Yuan, Shyan-Ming
;
Chiang, Chuan-Yen
;
Yang, Shian-Bo
;
Chen, Yen-Lin
;
資訊工程學系
Traffic accidents have become a major cause of death. Most traffic accidents are caused by driver carelessness on traffic conditions. The driving dispute is a critical problem for drivers when the car accident is happened. The drivers usually install the car video recorder in their car to recode their driving images in recent years. If a traffic accident being happened, the driver can provide a driving video file as an evidence to claim that they did not conduct any dangerous driving behaviors for protecting themselves from suspicions. However, under some such situations, drivers may not stay in their car accident when driving the car, but they have similar requirements for a video record, because they need to use those video files to find out the crime in some hit-and-run accidents. The goal of this paper is to develop a platform which can allow user to share their driving videos by using smart wearable devices and allow other users to search traffic video by some given specific time, date and location from the platforms\' database.
A vision-based blind spot warning system for daytime and nighttime driver assistance
(2013-04-01)
Wu, Bing-Fei
;
Huang, Hao-Yu
;
Chen, Chao-Jung
;
Chen, Ying-Han
;
Chang, Chia-Wei
This paper proposes an effective blind spot warning system (BSWS) for daytime and nighttime conditions. The proposed BSWS includes camera models of a dynamic calibration and blind spot detection (BSD) algorithms for the daytime and nighttime. Under daytime conditions, the proposed system presents the Horizontal Edge and Shadow Composite Region (HESCR) method to extract the searching region and to acquire the shadow location of the targeted vehicles. Additionally, to detect vehicles at nighttime road scenes, the proposed system extracts bright objects and recognizes the paired headlights of the targeted vehicles for the BSD. The BSWS is implemented on a DSP-based embedded platform. The results of the BSWS are obtained by conducting practical experiments on our camera-assisted car on a highway in Taiwan under both nighttime and daytime conditions. Experimental results show that the proposed BSWS is feasible for vehicle detection and collision warning in various daytime and nighttime road environments. (C) 2013 Elsevier Ltd. All rights reserved.
A Vision-Based Driver Nighttime Assistance and Surveillance System Based on Intelligent Image Sensing Techniques and a Heterogamous Dual-Core Embedded System Architecture
(2012-03-01)
Chen, Yen-Lin
;
Chiang, Hsin-Han
;
Chiang, Chuan-Yen
;
Liu, Chuan-Ming
;
Yuan, Shyan-Ming
This study proposes a vision-based intelligent nighttime driver assistance and surveillance system (VIDASS system) implemented by a set of embedded software components and modules, and integrates these modules to accomplish a component-based system framework on an embedded heterogamous dual-core platform. Therefore, this study develops and implements computer vision and sensing techniques of nighttime vehicle detection, collision warning determination, and traffic event recording. The proposed system processes the road-scene frames in front of the host car captured from CCD sensors mounted on the host vehicle. These vision-based sensing and processing technologies are integrated and implemented on an ARM-DSP heterogamous dual-core embedded platform. Peripheral devices, including image grabbing devices, communication modules, and other in-vehicle control devices, are also integrated to form an in-vehicle-embedded vision-based nighttime driver assistance and surveillance system.
An Intelligent Knowledge-Based and Customizable Home Care System Framework with Ubiquitous Patient Monitoring and Alerting Techniques
(2012-08-01)
Chen, Yen-Lin
;
Chiang, Hsin-Han
;
Yu, Chao-Wei
;
Chiang, Chuan-Yen
;
Liu, Chuan-Ming
This study develops and integrates an efficient knowledge-based system and a component-based framework to design an intelligent and flexible home health care system. The proposed knowledge-based system integrates an efficient rule-based reasoning model and flexible knowledge rules for determining efficiently and rapidly the necessary physiological and medication treatment procedures based on software modules, video camera sensors, communication devices, and physiological sensor information. This knowledge-based system offers high flexibility for improving and extending the system further to meet the monitoring demands of new patient and caregiver health care by updating the knowledge rules in the inference mechanism. All of the proposed functional components in this study are reusable, configurable, and extensible for system developers. Based on the experimental results, the proposed intelligent homecare system demonstrates that it can accomplish the extensible, customizable, and configurable demands of the ubiquitous healthcare systems to meet the different demands of patients and caregivers under various rehabilitation and nursing conditions.
ATP: A Browser-based Distributed Testing Service Platform
(2016-01-01)
Chiang, Chuan-Yen
;
Chang, Che-Pin
;
Chen, Hung-Yu
;
Chen, Yen-Lin
;
Yuan, Shyan-Ming
In recent years, web services have become an indispensable part of our life. By use of personal computers, smart phones and wearable smart devices, people can enjoy the convenience brought by these web services and use them to not only enrich our daily life but also solve life issues. Thus, to more appropriately realize the performance of a web service, it is necessary to perform an overall and credible web service testing. Among the areas of current research and applications of web service testing issues, a tester can use a single-node testing tool to rapidly build a simple test environment on a single test node or LAN environment; the tester can also take advantage of the cloud testing method to create large-scale test environment. However, these existing tools and methods suffer some problems so that the test environment is neither close enough to the real context of the use cases nor able to meet tester's requirement (test node dispersion, resource management and ease of deploying a test, etc.). In this paper, we identify three essential requirements for web service testing applications (elastic test environment provisioning, large scale simulation capability, and geographical test support) and propose an efficient design of browser-based distributed testing service platform. As a result, the tester can significantly save their time and reduce the cost via the proposed of browser-based distributed testing service platform.
Automatic Rack Cabinet Management System for Data Center
(2013)
Yuan, Shyan-Ming
;
Chiang, Chuan-Yen
;
Chen, Meng-Jie
;
Chen, Yen-Lin
;
資訊工程學系
With the evolution of computer science technology the concept of clouds are kept booming. The management of a large number of computer and peripheral equipment becomes an important issue. For centrally managing such a large number of computers and peripheral equipment scattered in many long-distance locations, the IP-based peripheral equipment is presented in the market today. The smart automatic management which includes automatically handling the common equipment status and controlling the number of running computer is neglected. In addition, managers will usually want a semantic way to think about how to control these devices. This paper presents a user-configurable semantic control system which allows users define their own automation control processes. The prediction of computer status is used for energy control, and the intelligent home language SHPL is also adopted to describe the semantics of the process. The system achieves the cross-device automatic management using device status and the power-saving functionality is also provided.
Degraded License Plate Recognition System for Town Buses on Highway
(2013)
Wu, Bing-Fei
;
Huang, Hao-Yu
;
Chen, Yen-Lin
;
Lin, Hsin-Yu
;
Lee, Tsu-Tian
This study presented a Degraded License Plate Recognition (DLPR) to identify town buses on highway. Since the License Plates (LPs) of town buses are influenced by the external conditions and become hardly distinguished by the Optical Character Recognition (OCR) method. The proposed DLPR system adopts Histogram of Oriented Gradient (HOG) and Support Vector Machine (SVM)-for classification-based solution. The proposed system implements a two-level LPR, including LP localization and character recognition. For the recognition efficiency of the proposed system, two trained databases for LP localization and character recognition are reduced by the mathematical and feature-based approaches, respectively, and thus the searching time can be saved significantly. To certify the performance of recognizing the degraded LPs, the proposed system is demonstrated by physical degraded LP images, and thus the results reveal that the proposed system overcomes several degraded LP images with reasonable recognition accuracy.
Development of Smart Shopping Carts with Customer-Oriented Service
(2016)
Chiang, Hsin-Han
;
You, Wan-Ting
;
Lin, Shu-Hsuan
;
Shih, Wei-Chih
;
Liao, Yu-Te
This paper presents a preliminary development of the smart shopping cart (SSC) that can be integrated into the smart mall system. The SSC can provide customers with the efficient user interface so that the shopping service can be effectively promoted. In the current design, with the function of face recognition on the user interface, the SSC can recognize the customer and further provide the associated assistive shopping information based on the purchase history. With the use of radio-frequency identification (RFID) tags, the SSC can automatically detect the various products which are being added in the cart and show the related information on the user interface. Through the searching function of SSC, the purchasing efficiency and navigation aid in the mall can be effectively supplied. Finally, the automatic billing service can be done by the SSC and the stored shopping data will be transmitted to the cloud server of shopping mall. The experimental demonstration shows the effectiveness of the proposed SSC which interacts with the customer and provides efficient shopping service.
Dynamic Calibration and Occlusion Handling Algorithms for Lane Tracking
(2009-05-01)
Wu, Bing-Fei
;
Lin, Chuan-Tsai
;
Chen, Yen-Lin
;
電控工程研究所
;
Institute of Electrical and Control Engineering
An approach of rapidly computing the projective width of lanes is presented to predict the projective positions and widths of lanes. The Lane Marking Extraction Finite State Machine is designed to extract points with features of lane markings in the image, and a cubic B-spline is adopted to conduct curve fitting to reconstruct road geometry. A statistical search algorithm is also proposed to correctly and adaptively determine thresholds under various kinds of illumination conditions. Furthermore, the parameters of the camera in a moving car may change with (be vibration, so a dynamic calibration algorithm is applied to calibrate camera parameters and lane widths with the information of lane projection. Moreover, a fuzzy logic is applied to determine the situation of occlusion. Finally, a region-of-interest determination strategy is developed to reduce the search region and to make the detection more robust with respect to the occlusion on the lane markings or complicated changes of curves and road boundaries.
Embedded Driver-Assistance System Using Multiple Sensors for Safe Overtaking Maneuver
(2014-09-01)
Chiang, Hsin-Han
;
Chen, Yen-Lin
;
Wu, Bing-Fei
;
Lee, Tsu-Tian
;
交大名義發表
Advanced driver-assistance systems have recently become one of the most active topics related to intelligent vehicles. Such assistance facilitates vehicular operation by allowing drivers increased control and an enhanced driving experience, and it even comes in the form of automated assistance for autonomous vehicle operation. This paper presents a driver-assistance system that uses a low-cost embedded digital signal processor, with the overall system installed in a commercial vehicle. Based on driving information supplied by multiple sensors, such as a real-time vision system, a vehicle-to-vehicle communication system, and in-vehicle sensors, the proposed system can facilitate decision making and the performing of driving tasks while executing overtaking maneuvers. This paper developed a data fusion stage based on a collision warning algorithm in which the overtaken vehicle and other vehicles in the neighboring lane are accounted for to avoid collisions. The system employs fuzzy control in the steering and speed automation to emulate the driving tasks performed by humans. The applicability of the proposed system was examined in a real-road environment, and a set of experimental results demonstrate the feasibility of using the involved coordination strategies while conducting various driving maneuvers.
Embedded On-road Nighttime Vehicle Detection and Tracking System for Driver Assistance
(2010)
Chen, Yen-Lin
;
Chiang, Chuan-Yen
;
資訊工程學系
;
Department of Computer Science
This study presents an effective method for detecting vehicles in front of the camera-assisted car during nighttime driving and implements it on an embedded system. The proposed method detects vehicles based on detecting and locating vehicle headlights and taillights using techniques of image segmentation and pattern analysis. Firstly, to effectively extract bright objects of interest, a segmentation process based on automatic multilevel thresholding applied on the grabbed road-scene images. Then the extracted bright objects are processed by to identify and tracking the vehicles by locating and analyzing the spatial and temporal features of vehicle light patterns and to estimate their distances to the camera-assisted car. Finally, we also implement the above vision-based techniques on a real-time system mounted in the host car. The proposed vision-based techniques are integrated and implemented on an ARM-Linux embedded platform, as well as the peripheral devices, including image grabbing devices, voice reporting module, and other in-vehicle control devices, will be also integrated to accomplish an in-vehicle embedded vision-based nighttime driver assistance system
Magnetic and Metal Binding Structural Analysis of Mn,Zn-Metallothionein-Green Fluorescence Fusion Protein
(2012-01-31)
Chen, Ting-Kai
;
Lin, Yin-Chih
;
Chen, Yu-Chen
;
Chen, Yen-Lin
;
Tseng, Wei-Lun
Magnetic Mesocrystal-Assisted Magnetoresistance in Manganite
(2014-11-01)
Yang, Jan-Chi
;
He, Qing
;
Zhu, Yuan-Min
;
Lin, Jheng-Cyuan
;
Liu, Heng-Jui
Mesocrystal, a new class of crystals as compared to conventional and well-known single crystals and polycrystalline systems, has captured significant attention in the past decade. Recent studies have been focused on the advance of synthesis mechanisms as well as the potential on device applications. In order to create further opportunities upon functional mesocrystals, we fabricated a self-assembled nanocomposite composed of magnetic CoFe2O4 mesocrystal in Sr-doped manganites. This combination exhibits intriguing structural and magnetic tunabilities. Furthermore, the antiferromagnetic coupling of the mesocrystal and matrix has induced an additional magnetic perturbation to spin-polarized electrons, resulting in a significantly enhanced magnetoresistance in the nanocomposite. Our work demonstrates a new thought toward the enhancement of intrinsic functionalities assisted by mesocrystals and advanced design of novel mesocrystal-embedded nanocomposites.
MPEG-2/4 Low-Complexity Advanced Audio Coding Optimization and Implementation on DSP
(2010-05-01)
Wu, Bing-Fei
;
Huang, Hao-Yu
;
Chen, Yen-Lin
;
Peng, Hsin-Yuan
;
Huang, Jia-Hsiung
This study presents several optimization approaches for the MPEG-2/4 Audio Advanced Coding (AAC) Low Complexity (LC) encoding and decoding processes. Considering the power consumption and the peripherals required for consumer electronics, this study adopts the TI OMAP5912 platform for portable devices. An important optimization issue for implementing AAC codec on embedded and mobile devices is to reduce computational complexity and memory consumption. Due to power saving issues, most embedded and mobile systems can only provide very limited computational power and memory resources for the coding process. As a result, modifying and simplifying only one or two blocks is insufficient for optimizing the AAC encoder and enabling it to work well on embedded systems. It is therefore necessary to enhance the computational efficiency of other important modules in the encoding algorithm. This study focuses on optimizing the Temporal Noise Shaping (TNS), Mid/Side (M/S) Stereo, Modified Discrete Cosine Transform (MDCT) and Inverse Quantization (IQ) modules in the encoder and decoder. Furthermore, we also propose an efficient memory reduction approach that provides a satisfactory balance between the reduction of memory usage and the expansion of the encoded files. In the proposed design, both the AAC encoder and decoder are built with fixed-point arithmetic operations and implemented on a DSP processor combined with an ARM-core for peripheral controlling. Experimental results demonstrate that the proposed AAC codec is computationally effective, has low memory consumption, and is suitable for low-cost embedded and mobile applications.
Nighttime vehicle detection for driver assistance and autonomous vehicles
(2006)
Chen, Yen-Lin
;
Chen, Yuan-Hsin
;
Chen, Chao-Jung
;
Wu, Bing-Fei
;
電控工程研究所
This study presents an effective method for detecting vehicles in front of the camera-assisted car during nighttime driving. The proposed method detects vehicles based on detecting and locating vehicle headlights and taillights using techniques of image segmentation and pattern analysis. First, to effectively extract bright objects of interest, a segmentation process based on automatic multilevel thresholding is applied on the grabbed road-scene images. Then the extracted bright objects are processed by a rule-based procedure, to identify the vehicles by locating and analyzing their vehicle light patterns, and estimate their distances to the camera-assisted car. Experimental results demonstrate the effectiveness of the proposed method on detecting vehicles at night.
Range and Size Estimation Based on a Coordinate Transformation Model for Driving Assistance Systems
(2009-09-01)
Wu, Bing-Fei
;
Lin, Chuan-Tsai
;
Chen, Yen-Lin
;
交大名義發表
;
National Chiao Tung University
This paper presents new approaches for the estimation of range between the preceding vehicle and the experimental vehicle, estimation of vehicle size and its projective size, and dynamic camera calibration. First, our proposed approaches adopt a camera model to transform coordinates from the ground plane onto the image plane to estimate the relative position between the detected vehicle and the camera. Then, to estimate the actual and projective size of the preceding vehicle, we propose a new estimation method. This method can estimate the range from a preceding vehicle to the camera based on contact points between its tires and the ground and then estimate the actual size of the vehicle according to the positions of its vertexes in the image. Because the projective size of a vehicle varies with respect to its distance to the camera, we also present a simple and rapid method of estimating a vehicle's projective height, which allows a reduction in computational time for size estimation in real-time systems. Errors caused by the application of different camera parameters are also estimated and analyzed in this study. The estimation results are used to determine suitable parameters during camera installation to suppress estimation errors. Finally, to guarantee robustness of the detection system, a new efficient approach to dynamic calibration is presented to obtain accurate camera parameters, even when they are changed by camera vibration owing to on-road driving. Experimental results demonstrate that our approaches can provide accurate and robust estimation results of range and size of target vehicles.