{"title":"Falling down detection on zebra crossing at night by thermal imager","authors":"Ying-Nong Chen, Wen-Yao Tsai, Kuo-Chin Fan, Chi-Hung Chuang","doi":"10.1109/ISPACS.2012.6473473","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473473","url":null,"abstract":"Falling down detection is an important application for surveillance system. In this study, a two-stage falling down detection at night based on optical flow and motion histogram image (MHI) is proposed. Based on the thermal imager, the foreground pedestrian could be perfectly extracted. In the first stage, vertical optical flow feature is used to roughly detect the falling down event, then, in the second stage, vertical optical flow hybrid MHI feature is fed into the Naive Bayes classifier to verify the falling down event. The experimental results show that the detection rate is 98.6%, which demonstrates the effectiveness of the proposed method.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115385572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Chiu, Chi-Hsien Sun, L. Tuen, Ching-Lieh Li, Szu-Chi Shen, Shang-Yi Yang
{"title":"Electromagnetic imaging of buried perfectly conducting cylinders targets using APSO","authors":"C. Chiu, Chi-Hsien Sun, L. Tuen, Ching-Lieh Li, Szu-Chi Shen, Shang-Yi Yang","doi":"10.1109/ISPACS.2012.6473586","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473586","url":null,"abstract":"We present a computational approach to the imaging of a two-dimensional (2-D) embedded perfectly conducting cylinder by the asynchronous particle swarm optimization (APSO). An embedded conducting cylinder of unknown shape scatters the incident transverse magnetic (TM) wave in a half space while the scattered field is recorded outside. Based on the boundary condition and the measured scattered field, a set of nonlinear integral equations is derived and the imaging problem is reformulated into an optimization problem. The inverse problem is solved by an optimization approach and the global searching scheme the asynchronous particle swarm optimization is then employed to search the parameter space. Numerical simulations show that even when the measured scattered fields are contaminated with Gussian noise, the quality of the reconstructed results obtained by the APSO algorithm is very good.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124870945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Hsieh, Hui-Chun Wang, Yeh-Kuang Wu, Liung-Chun Chang, Tai-Ku Kuo
{"title":"A Kinect-based people-flow counting system","authors":"C. Hsieh, Hui-Chun Wang, Yeh-Kuang Wu, Liung-Chun Chang, Tai-Ku Kuo","doi":"10.1109/ISPACS.2012.6473470","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473470","url":null,"abstract":"This paper proposed a bi-directional people-flow counting system with Kinect. It can also be applied to multi-flow to correspond with the demand for the practical application. Firstly, we set the Kinect above the doorway to capture the situation of pedestrian flow. Then this system detects people in the covering area using the depth image information from Kinect system. And we do the morphological processing like erosion to the object and find the region of interest (ROI) often performed on using a mapping-based detection approach. After these previous steps, this system set a detected line and let people go through it. Therefore, we can get people number of the experimental result. For the multi-flow case, it will cause the occlusion problem, so we could apply the depth information to distinguish the target on occlusion problem. Final, we compare the experimental results with the manual count results and other research. Under normal circumstances, our system provides not only almost 100% for bi-directional counting but also correspond with the demand for real-time.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123409341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Design and implementation of a gardening mobile robot with embedded face-tracking system","authors":"Chung-Liang Chang, Jian-Fong Chen, Jia-Heng Jhu","doi":"10.1109/ISPACS.2012.6473487","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473487","url":null,"abstract":"This paper proposes a gardening robot capable of visual tracking and obstacle avoidance. Firstly, YCbCr color space transformation is utilized for skin detection. Then, dilation/erosion/closing and 8-neighbors methods are adopted to search the maximum area of desired object and eliminate noise. Finally, center coordinate of object is acquired. The tracking object can be set beforehand or immediate identification. The micro-controller is employed to receive coordinate information and conduct steering control. The infrared sensors module is used to avoid obstacle. The proposed system designs one human-machine interface at remote end for easy surveillance and emergent control of robot location. This system is implemented in one prototype of gardening robot, which can share farmers' task and provide carriage of goods.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121383120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive fuzzy beamformer to steering vector mismatch","authors":"J. Hung","doi":"10.1109/ISPACS.2012.6473608","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473608","url":null,"abstract":"This paper proposed an efficient beamformer to deal with the signal steering vector mismatches. The empirical results show that the significant performance degradation occurs when the signal steering vector for the desired signal is not known exactly. Thus, we design adaptive fuzzy beamformer, which adopt the method of fuzzy systems to modify the value of signal steering vector by first-order Taylor expansion. In this situation, the beamformer design problem becomes a complicated nonlinear estimation problem. In this study, a design method based on differential evolution (DE) algorithm is proposed to treat the adaptive fuzzy beamformer design problem. Finally, the simulation confirm that the proposed scheme performance is significantly improved and preferable robustness if the effect of point error of desired signal is considered along with the use of expert knowledge enabled by the beamformer.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116489197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Power line communication chip design with data error detecting/correcting and data encrypting/decrypting ability","authors":"Ko-Chi Kuo, H. Hsu","doi":"10.1109/ISPACS.2012.6473575","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473575","url":null,"abstract":"This paper presents a low cost chip design of Power Line Communication for the applications in the home networks. The data transmission occur burst errors easily by the noise interference from the environment. In order to reduce the error rate, an all-digital modulation/demodulation chip with error correctable and high error detected ability for power line communication is designed. The proposed design consists of Cyclic Redundancy Check, Digital Pulse Width Modulation, Digital Frequency Shift Keying, Forward Error Correction, interleaving techniques, and Tiny Encryption Algorithm. The fabricated chip area is 1.352 mm2 with 3.3/1.8 supply voltages. The measured data shows that the proposed design is fully functional and consumes 70 μW.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126458888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CRT-based fragile self-recovery watermarking scheme for image authentication and recovery","authors":"B. Patra, J. Patra","doi":"10.1109/ISPACS.2012.6473528","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473528","url":null,"abstract":"Fragile watermarking is one of the effective techniques for authentication of digital documents and images. However, recovering the content of the tampered region in a watermarked image is a challenging task while considering conflicting criteria of imperceptibility and watermark embedding capacity. In this paper we propose a Chinese remainder theorem (CRT)-based watermarking scheme which can recover the original contents in the tampered region of the digital content while maintaining imperceptibility criterion. High peak signal to noise ratio (PSNR) and large watermark capacity can be achieved by using the CRT-based embedding scheme. Since only modular operations are involved in computation of the CRT-based technique, it provides computational advantage as it involves only modular arithmetic. Besides, CRT-based technique introduces additional security to the watermarking scheme. By taking several digital images, we have shown that the proposed technique can recover the tampered contents effectively. We have also considered forgery detection on a digital cheque, eCheque, and shown that the proposed technique can detect and recover the original content from the forged cheque.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125202434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An image-based Entamoeba automatic detecting system","authors":"Der-Chen Huang, Y. Chan, Tsung-Ho Wu","doi":"10.1109/ISPACS.2012.6473556","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473556","url":null,"abstract":"The amoeba is a parasite which can compromise the human's health. Many people died of amoeba every year. Traditionally, pathologists use microscopy to execute the diagnosis in experiment. The pathologists adopt the number of amoebas in the amoebas to diagnose the severity of infection by the amoeba for a patient. However, the diagnosing quality and performance are heavily impacted by human's behaviors such as eyesight, strength and professional knowledge etc. Thus, in this paper, an image-based amoeba automatic detecting system is proposed to segment the amoebas cell from an amoeba image. The experimental results tell that the proposed method can precisely count the number of cells and detects their locations for most amoeba sample images.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"133 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125464080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Human action classification using histogram-based discriminative embedding","authors":"Cheng-Hsien Lin, Wei-Yang Lin","doi":"10.1109/ISPACS.2012.6473443","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473443","url":null,"abstract":"In order to have a rich representation for human action, we propose to combine two complementary features so that a human posture can be characterized in more details. In particular, the distance signal feature and the width feature are combined in an effective way to enhance each other's discriminating capability. The resulting feature vector is quantized into mid-level features using k-means clustering. In the mid-level feature space, we apply the nonparametric embedding method to construct a compact yet discriminative subspace model. We have conducted a series of experiments on the Weizmann dataset to validate the proposed scheme. Compared with the existing approaches, our method can achieve high recognition accuracy while having a reduced computational complexity in classification stage.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122354455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DC power supply system for intelligent server","authors":"Ching-Chang Wong, Chih-Cheng Liu, K. Hou","doi":"10.1109/ISPACS.2012.6473488","DOIUrl":"https://doi.org/10.1109/ISPACS.2012.6473488","url":null,"abstract":"An automatic self-adjustable of parallel DC supply system is proposed. In this thesis, the modular DC power supply unit (PSU) integrated six PSU with power distribution board to become integrated DC power supply system. For efficiency improvement of the DC supply system, the graphical programming language LabVIEW and the interface I2C device NI-USB 8451 are used to control the automatic self-adjustable of six-parallel DC PSU system. The time of the development, data collection from each power supply, and verification will be reduced by the proposed method. Moreover, the visual programming language can be easily used to debug. Some experimental results are presented to illustrate that the proposed fuzzy control method can adjust the quantity of PSU based on the tactual power requirement of the server system. The power saving of each PSU even though not much, but the proposed method can save a lot of unnecessary waste of electricity in the case of long-term use of a large number of PSU. Moreover, the proposed power supply configuration and control method can also provide the data center and the cloud server as a reference for the design and planning of power supply products.","PeriodicalId":158744,"journal":{"name":"2012 International Symposium on Intelligent Signal Processing and Communications Systems","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127170738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}