Abstract An algorithm that enables efficient maze exploration is presented in the paper. The algorithm involves two phases: first the whole maze is explored in an ordered way and then, the shortest possible way out is determined. The algorithm has been derived in a way that combines main advantages of the two known labirynth-exploration algorithms: “Wall follower” and “Trémaux’s algorithm”. The algorithm has been tested using an autonomous vehicle, controlled by Arduino UNO, with two DC engines, ultrasonic sensors and gyroscope. It has been shown that the proposed approach provides a few crucial advantages with respect to already known solutions.
{"title":"Maze Exploration Algorithm for Small Mobile Platforms","authors":"Łukasz Bienias, Krzysztof Szczepański, P. Duch","doi":"10.1515/ipc-2016-0013","DOIUrl":"https://doi.org/10.1515/ipc-2016-0013","url":null,"abstract":"Abstract An algorithm that enables efficient maze exploration is presented in the paper. The algorithm involves two phases: first the whole maze is explored in an ordered way and then, the shortest possible way out is determined. The algorithm has been derived in a way that combines main advantages of the two known labirynth-exploration algorithms: “Wall follower” and “Trémaux’s algorithm”. The algorithm has been tested using an autonomous vehicle, controlled by Arduino UNO, with two DC engines, ultrasonic sensors and gyroscope. It has been shown that the proposed approach provides a few crucial advantages with respect to already known solutions.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131837118","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}
Abstract The paper explores possibility of improving Support Vector Machine-based classification performance by introducing an input data dimensionality reduction step. Feature extraction by means of two different kernel methods are considered: kernel Principal Component Analysis (kPCA) and Supervised kernel Principal Component Analysis. It is hypothesized that input domain transformation, aimed at emphasizing between-class differences, would facilitate classification problem. Experiments, performed on three different datasets show that one can benefit from the proposed approach, as it provides lower variability in classification performance at similar, high recognition rates.
{"title":"Object Classification Using Support Vector Machines with Kernel-based Data Preprocessing","authors":"Krzysztof Adamiak, P. Duch, K. Slot","doi":"10.1515/ipc-2016-0015","DOIUrl":"https://doi.org/10.1515/ipc-2016-0015","url":null,"abstract":"Abstract The paper explores possibility of improving Support Vector Machine-based classification performance by introducing an input data dimensionality reduction step. Feature extraction by means of two different kernel methods are considered: kernel Principal Component Analysis (kPCA) and Supervised kernel Principal Component Analysis. It is hypothesized that input domain transformation, aimed at emphasizing between-class differences, would facilitate classification problem. Experiments, performed on three different datasets show that one can benefit from the proposed approach, as it provides lower variability in classification performance at similar, high recognition rates.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116694965","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}
Abstract In this paper an embedded vision system for human silhouette detection in thermal images is presented. As the computing platform a reprogrammable device (FPGA – Field Programmable Gate Array) is used. The detection algorithm is based on a sliding window approach, which content is compared with a probabilistic template. Moreover, detection is four scales in supported. On the used test database, the proposed method obtained 97% accuracy, with average one false detection per frame. Due to the used parallelization and pipelining real-time processing for 720 × 480 @ 50 fps and 1280 × 720 @ 50 fps video streams was achieved. The system has been practically verified in a test setup with a thermal camera.
{"title":"FPGA Implementation of Multi-scale Pedestrian Detection in Thermal Images","authors":"Tomasz Kańka, T. Kryjak, M. Gorgon","doi":"10.1515/ipc-2016-0016","DOIUrl":"https://doi.org/10.1515/ipc-2016-0016","url":null,"abstract":"Abstract In this paper an embedded vision system for human silhouette detection in thermal images is presented. As the computing platform a reprogrammable device (FPGA – Field Programmable Gate Array) is used. The detection algorithm is based on a sliding window approach, which content is compared with a probabilistic template. Moreover, detection is four scales in supported. On the used test database, the proposed method obtained 97% accuracy, with average one false detection per frame. Due to the used parallelization and pipelining real-time processing for 720 × 480 @ 50 fps and 1280 × 720 @ 50 fps video streams was achieved. The system has been practically verified in a test setup with a thermal camera.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117145969","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}
Abstract The paper presents an idea of a new measuring method based on image tomography. This method focuses on registration of images of bubbles moving in two perpendicular directions. Two images are used for determination of the center of mass, movement trajectory and local velocities. Volume and area of bubbles are defined by using approximation of the bubble shape with the known geometric figures. The paper also presents the algorithm of reconstruction of the bubble shapes and movement trajectories, as well as exemplary test results. The obtained results were compared with empirical correlations in the published literature.
{"title":"Parameter Measurements of Moving Gas Bubbles Using Image Tomography Title","authors":"M. Rząsa","doi":"10.1515/ipc-2016-0012","DOIUrl":"https://doi.org/10.1515/ipc-2016-0012","url":null,"abstract":"Abstract The paper presents an idea of a new measuring method based on image tomography. This method focuses on registration of images of bubbles moving in two perpendicular directions. Two images are used for determination of the center of mass, movement trajectory and local velocities. Volume and area of bubbles are defined by using approximation of the bubble shape with the known geometric figures. The paper also presents the algorithm of reconstruction of the bubble shapes and movement trajectories, as well as exemplary test results. The obtained results were compared with empirical correlations in the published literature.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131514753","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}
Abstract In this paper, the problem of segmentation of 3D Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) brain images is considered. A supervoxel-based segmentation is regarded. In particular, a new approach called Relative Linear Interactive Clustering (RLIC) is introduced. The method, dedicated to image division into super-voxels, is an extension of the Simple Linear Interactive Clustering (SLIC) super-pixels algorithm. During RLIC execution firstly, the cluster centres and the regular grid size are initialized. These are next clustered by Fuzzy C-Means algorithm. Then, the extraction of the super-voxels statistical features is performed. The method contributes with 3D images and serves fully volumetric image segmentation. Five cases are tested demonstrating that our Relative Linear Interactive Clustering (RLIC) is apt to handle huge size of images with a significant accuracy and a low computational cost. The results of applying the suggested method to segmentation of the brain tumour are exposed and discussed.
摘要本文研究了三维磁共振成像(MRI)和计算机断层扫描(CT)脑图像的分割问题。考虑了基于超体素的分割。特别介绍了一种新的聚类方法——相对线性交互聚类(RLIC)。该方法是对简单线性交互聚类(Simple Linear Interactive Clustering, SLIC)超像素算法的扩展，致力于将图像划分为超体素。在RLIC执行过程中，首先初始化集群中心和规则网格大小。然后用模糊c均值算法聚类。然后，进行超体素统计特征的提取。该方法有利于三维图像的分割，完全满足体积图像分割的要求。五个案例的测试表明，我们的相对线性交互聚类(RLIC)能够以较低的计算成本和较高的精度处理大尺寸的图像。并对该方法在脑肿瘤分割中的应用结果进行了讨论。
{"title":"Features Determination from Super-Voxels Obtained with Relative Linear Interactive Clustering","authors":"Abdelkhalek Bakkari, A. Fabijańska","doi":"10.1515/ipc-2016-0017","DOIUrl":"https://doi.org/10.1515/ipc-2016-0017","url":null,"abstract":"Abstract In this paper, the problem of segmentation of 3D Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) brain images is considered. A supervoxel-based segmentation is regarded. In particular, a new approach called Relative Linear Interactive Clustering (RLIC) is introduced. The method, dedicated to image division into super-voxels, is an extension of the Simple Linear Interactive Clustering (SLIC) super-pixels algorithm. During RLIC execution firstly, the cluster centres and the regular grid size are initialized. These are next clustered by Fuzzy C-Means algorithm. Then, the extraction of the super-voxels statistical features is performed. The method contributes with 3D images and serves fully volumetric image segmentation. Five cases are tested demonstrating that our Relative Linear Interactive Clustering (RLIC) is apt to handle huge size of images with a significant accuracy and a low computational cost. The results of applying the suggested method to segmentation of the brain tumour are exposed and discussed.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129575734","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}
M. Majchrowicz, Paweł Kapusta, L. Jackowska-Strumillo, D. Sankowski
Abstract Electrical Capacitance Tomography is a non-invasive imaging technique, which allows visualization of the industrial processes interior and can be applied to many branches of the industry. Image reconstruction process, especially in case of 3D images, is a very time consuming task (when using classic processors and algorithms), which in turn leads to an unacceptable waiting time and currently limits the use of 3D Electrical Capacitance Tomography. Reconstruction using deterministic methods requires execution of many basic operations of linear algebra, such as matrix transposition, multiplication, addition and subtraction. In order to reach real-time reconstruction a 3D ECT computational subsystem must be able to transform capacitance data into images in a fraction of a second. By assuming, that many of the computations can be performed in parallel using modern, fast graphics processor and by altering the algorithms, time to achieve high quality image reconstruction will be shortened significantly. The research conducted while analysing ECT algorithms has also shown that, although dynamic development of GPU computational capabilities and its recent application for image reconstruction in ECT has significantly improved calculations time, in modern systems a single GPU is not enough to perform many tasks. Distributed Multi-GPU solutions can reduce reconstruction time to only a fraction of what was possible on pure CPU systems. Nevertheless performed tests clearly illustrate the need for further optimizations of previously developed algorithms.
{"title":"Optimization of Distributed Multi-Node, Multi-GPU, Heterogeneous System for 3D Image Reconstruction in Electrical Capacitance Tomography","authors":"M. Majchrowicz, Paweł Kapusta, L. Jackowska-Strumillo, D. Sankowski","doi":"10.1515/ipc-2016-0018","DOIUrl":"https://doi.org/10.1515/ipc-2016-0018","url":null,"abstract":"Abstract Electrical Capacitance Tomography is a non-invasive imaging technique, which allows visualization of the industrial processes interior and can be applied to many branches of the industry. Image reconstruction process, especially in case of 3D images, is a very time consuming task (when using classic processors and algorithms), which in turn leads to an unacceptable waiting time and currently limits the use of 3D Electrical Capacitance Tomography. Reconstruction using deterministic methods requires execution of many basic operations of linear algebra, such as matrix transposition, multiplication, addition and subtraction. In order to reach real-time reconstruction a 3D ECT computational subsystem must be able to transform capacitance data into images in a fraction of a second. By assuming, that many of the computations can be performed in parallel using modern, fast graphics processor and by altering the algorithms, time to achieve high quality image reconstruction will be shortened significantly. The research conducted while analysing ECT algorithms has also shown that, although dynamic development of GPU computational capabilities and its recent application for image reconstruction in ECT has significantly improved calculations time, in modern systems a single GPU is not enough to perform many tasks. Distributed Multi-GPU solutions can reduce reconstruction time to only a fraction of what was possible on pure CPU systems. Nevertheless performed tests clearly illustrate the need for further optimizations of previously developed algorithms.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121439768","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}
Abstract In this paper an FPGA based embedded vision system for face detection is presented. The sliding detection window, HOG+SVM algorithm and multi-scale image processing were used and extensively described. The applied computation parallelizations allowed to obtain real-time processing of a 1280 × 720 @ 50Hz video stream. The presented module has been verified on the Zybo development board with Zynq SoC device from Xilinx. It can be used in a vast number of vision systems, including diver fatigue monitoring.
{"title":"FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier","authors":"M. Drożdż, T. Kryjak","doi":"10.1515/ipc-2016-0014","DOIUrl":"https://doi.org/10.1515/ipc-2016-0014","url":null,"abstract":"Abstract In this paper an FPGA based embedded vision system for face detection is presented. The sliding detection window, HOG+SVM algorithm and multi-scale image processing were used and extensively described. The applied computation parallelizations allowed to obtain real-time processing of a 1280 × 720 @ 50Hz video stream. The presented module has been verified on the Zybo development board with Zynq SoC device from Xilinx. It can be used in a vast number of vision systems, including diver fatigue monitoring.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114611246","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}
Abstract Wearable motion capture systems using Micro-Electro-Mechanical-Systems (MEMS) based Inertial Measurement Units (IMUs) are considered a promising low-cost technology that evolves rapidly over the last few years. A wearable pointing system that consists of a pair of IMUs with acceleration and angular velocity sensors is presented in this work. Each IMU is equipped with Bluetooth connectivity and both are mounted on the user’s arm. The system provides automatic pointing on the presentation screen by capturing the arm’s rotational movement and by exploiting the speaker’s relative to the screen position. In this paper, we present the system’s design and its evaluation along with a training method for estimating the user-screen distance and relative position. Experimental results show promising pointing accuracy and precision in a variety of different display sizes and distances making the system an effective solution for automatic on-screen pointing.
{"title":"An IMU-Based Wearable System for Automatic Pointing During Presentations","authors":"Dimitrios Sikeridis, T. Antonakopoulos","doi":"10.1515/ipc-2016-0007","DOIUrl":"https://doi.org/10.1515/ipc-2016-0007","url":null,"abstract":"Abstract Wearable motion capture systems using Micro-Electro-Mechanical-Systems (MEMS) based Inertial Measurement Units (IMUs) are considered a promising low-cost technology that evolves rapidly over the last few years. A wearable pointing system that consists of a pair of IMUs with acceleration and angular velocity sensors is presented in this work. Each IMU is equipped with Bluetooth connectivity and both are mounted on the user’s arm. The system provides automatic pointing on the presentation screen by capturing the arm’s rotational movement and by exploiting the speaker’s relative to the screen position. In this paper, we present the system’s design and its evaluation along with a training method for estimating the user-screen distance and relative position. Experimental results show promising pointing accuracy and precision in a variety of different display sizes and distances making the system an effective solution for automatic on-screen pointing.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128670740","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}
Abstract The sub-sampling method for Orthogonal Frequency Division Multiplexing proposed recently, has been extended in this paper allowing the Analog-to-Digital Converter on the receiver side to operate in low power mode, up to 3/4 of the time. The predictability of the parity patterns generated by the Forward Error Correction encoder of the transmitter, when sparse data are exchanged, is exploited in order to define appropriate Inverse Fast Fourier Transform input symbol arrangements. These symbol arrangements allow the substitution of a number of samples by others that have already been received. Moreover, several operations of the Fast Fourier Transform can be omitted because their result is zero when identical values appear at its input. The advantages of the proposed method are: low power, higher speed and fewer memory resources. Despite other iterative sub-sampling approaches like Compressive Sampling, the proposed method is not iterative and thus it can be implemented with very low complexity hardware. The simulation results show that full input signal recovery or at least a very low Bit Error Rate is achieved in most of the cases that have been tested.
{"title":"Sub-Sampling in OFDM with Constant Time Signal Recovery","authors":"N. Petrellis","doi":"10.1515/ipc-2016-0008","DOIUrl":"https://doi.org/10.1515/ipc-2016-0008","url":null,"abstract":"Abstract The sub-sampling method for Orthogonal Frequency Division Multiplexing proposed recently, has been extended in this paper allowing the Analog-to-Digital Converter on the receiver side to operate in low power mode, up to 3/4 of the time. The predictability of the parity patterns generated by the Forward Error Correction encoder of the transmitter, when sparse data are exchanged, is exploited in order to define appropriate Inverse Fast Fourier Transform input symbol arrangements. These symbol arrangements allow the substitution of a number of samples by others that have already been received. Moreover, several operations of the Fast Fourier Transform can be omitted because their result is zero when identical values appear at its input. The advantages of the proposed method are: low power, higher speed and fewer memory resources. Despite other iterative sub-sampling approaches like Compressive Sampling, the proposed method is not iterative and thus it can be implemented with very low complexity hardware. The simulation results show that full input signal recovery or at least a very low Bit Error Rate is achieved in most of the cases that have been tested.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"34 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120873979","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}
Alisa Arno, Kentaroh Toyoda, Yuji Watanabe, I. Sasase, P. Mathiopoulos
Abstract Eavesdropping is an important and real concern in mobile NFC (Near Filed Communication) payment and data sharing applications. Although the DH (Diffie-Hellman) scheme has been widely used in key exchange for secure communications, it may fail in indoor environments due to its vulnerability against man-in-the-middle attack. In this paper, we propose a new vibration-based key exchange among multiple smart devices which are placed on a desk. In this scheme, devices are assumed to be located next to each other with each of them vibrating with patterns converted from a key to be exchanged. The vibration patterns are measured by an accelerometer and each key is recovered from the measured acceleration. The proposed scheme has been implemented using Android smartphones and various experimental performance evaluation results have validated its effectiveness.
{"title":"Vibration-based Key Exchange among Multiple Smart Devices on the Desk","authors":"Alisa Arno, Kentaroh Toyoda, Yuji Watanabe, I. Sasase, P. Mathiopoulos","doi":"10.1515/ipc-2016-0009","DOIUrl":"https://doi.org/10.1515/ipc-2016-0009","url":null,"abstract":"Abstract Eavesdropping is an important and real concern in mobile NFC (Near Filed Communication) payment and data sharing applications. Although the DH (Diffie-Hellman) scheme has been widely used in key exchange for secure communications, it may fail in indoor environments due to its vulnerability against man-in-the-middle attack. In this paper, we propose a new vibration-based key exchange among multiple smart devices which are placed on a desk. In this scheme, devices are assumed to be located next to each other with each of them vibrating with patterns converted from a key to be exchanged. The vibration patterns are measured by an accelerometer and each key is recovered from the measured acceleration. The proposed scheme has been implemented using Android smartphones and various experimental performance evaluation results have validated its effectiveness.","PeriodicalId":271906,"journal":{"name":"Image Processing & Communications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129540115","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：