Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030993
W. G. Ali Abdelaal, Gihan Nagib
In this paper, the dynamic model of a Shape Memory Alloy (SMA) Flexinol™ actuator wire is developed and simulated. The model is nonlinear with hysteresis behavior and its parameters are obtained easily using the manufacturer data sheet. The developed model can be served to investigate the SMA behavior and to design control applications. The simulation results using MATLAB/SIMULINK verified the dynamic model behavior and affirmed the potential of the modeling procedure. The results showed that the Flexinol™ wire is a powerful actuator with large strain up to 5% and high power to weight ratio.
{"title":"Modeling and simulation of SMA actuator wire","authors":"W. G. Ali Abdelaal, Gihan Nagib","doi":"10.1109/ICCES.2014.7030993","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030993","url":null,"abstract":"In this paper, the dynamic model of a Shape Memory Alloy (SMA) Flexinol™ actuator wire is developed and simulated. The model is nonlinear with hysteresis behavior and its parameters are obtained easily using the manufacturer data sheet. The developed model can be served to investigate the SMA behavior and to design control applications. The simulation results using MATLAB/SIMULINK verified the dynamic model behavior and affirmed the potential of the modeling procedure. The results showed that the Flexinol™ wire is a powerful actuator with large strain up to 5% and high power to weight ratio.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"662 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133334499","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030967
K. Hamouda, Mohammed M Elmogy, B. El-Desouky
In contemporary years, different watermarking schemes are proposed for image authentication and copyright protection. In this paper, a novel watermarking authentication technique based on Chaos and Fuzzy C-Means clustering is proposed for images of different sizes. Tamper localization and detection accuracy are two important aspects of the authentication watermarking schemes. The proposed hybrid technique is used to improve the tamper localization, detection accuracy, and security of the watermarking system. Fuzzy C-Means clustering technique creates the relationship between image blocks to improve the tamper localization and detection accuracy. It also makes the watermark dependent on the plain image to improve the security of the watermarking system. Chaotic maps are sensitive to initial values, so watermark cannot be established without the same initial values. Then, it gives high security to the proposed watermarking scheme. The proposed scheme not deals with square or even sized images, but it can deals with any images with different sizes. Experimental results show that the proposed scheme is checked through a series of attacks and achieve superior tamper detection and localization accuracy under different attacks.
{"title":"A fragile watermarking authentication schema based on Chaotic maps and fuzzy cmeans clustering technique","authors":"K. Hamouda, Mohammed M Elmogy, B. El-Desouky","doi":"10.1109/ICCES.2014.7030967","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030967","url":null,"abstract":"In contemporary years, different watermarking schemes are proposed for image authentication and copyright protection. In this paper, a novel watermarking authentication technique based on Chaos and Fuzzy C-Means clustering is proposed for images of different sizes. Tamper localization and detection accuracy are two important aspects of the authentication watermarking schemes. The proposed hybrid technique is used to improve the tamper localization, detection accuracy, and security of the watermarking system. Fuzzy C-Means clustering technique creates the relationship between image blocks to improve the tamper localization and detection accuracy. It also makes the watermark dependent on the plain image to improve the security of the watermarking system. Chaotic maps are sensitive to initial values, so watermark cannot be established without the same initial values. Then, it gives high security to the proposed watermarking scheme. The proposed scheme not deals with square or even sized images, but it can deals with any images with different sizes. Experimental results show that the proposed scheme is checked through a series of attacks and achieve superior tamper detection and localization accuracy under different attacks.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134594595","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030959
M. Soliman, E. Elsayed
This paper proposes a simultaneous multithreaded matrix processor called SMMP to improve the performance of data-parallel applications by exploiting ILP, DLP, and TLP. In SMMP, the well-known 5-stage pipeline (baseline scalar processor) is extended to execute multi-scalar/vector/matrix instructions on unified parallel execution datapaths. SMMP can issue four scalar instructions from two threads each cycle or four vector/matrix operations from one thread, where the execution of vector/matrix instructions in threads is done in round-robin fashion. Moreover, this paper presents the implementation of our proposed SMMP using VHDL targeting FPGA Virtex-6. In addition, the performance of SMMP is evaluated on some kernels from the basic linear algebra subprograms (BLAS). Our results show that, the hardware complexity of SMMP is 5.68 times higher than the baseline scalar processor. However, speedups of 4.9, 6.09, 6.98, 8.2, 8.25, 8.72, 9.36, 11.84, and 21.57 are achieved on BLAS kernels of applying Givens rotation, scalar times vector plus another, vector addition, vector scaling, setting up Givens rotation, dot-product, matrix-vector multiplication, Euclidean length, and matrix-matrix multiplications, respectively. In conclusion, the average speedup over the baseline is 9.55 and the average speedup over complexity is 1.68.
{"title":"FPGA implementation and performance evaluation of a simultaneous multithreaded matrix processor","authors":"M. Soliman, E. Elsayed","doi":"10.1109/ICCES.2014.7030959","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030959","url":null,"abstract":"This paper proposes a simultaneous multithreaded matrix processor called SMMP to improve the performance of data-parallel applications by exploiting ILP, DLP, and TLP. In SMMP, the well-known 5-stage pipeline (baseline scalar processor) is extended to execute multi-scalar/vector/matrix instructions on unified parallel execution datapaths. SMMP can issue four scalar instructions from two threads each cycle or four vector/matrix operations from one thread, where the execution of vector/matrix instructions in threads is done in round-robin fashion. Moreover, this paper presents the implementation of our proposed SMMP using VHDL targeting FPGA Virtex-6. In addition, the performance of SMMP is evaluated on some kernels from the basic linear algebra subprograms (BLAS). Our results show that, the hardware complexity of SMMP is 5.68 times higher than the baseline scalar processor. However, speedups of 4.9, 6.09, 6.98, 8.2, 8.25, 8.72, 9.36, 11.84, and 21.57 are achieved on BLAS kernels of applying Givens rotation, scalar times vector plus another, vector addition, vector scaling, setting up Givens rotation, dot-product, matrix-vector multiplication, Euclidean length, and matrix-matrix multiplications, respectively. In conclusion, the average speedup over the baseline is 9.55 and the average speedup over complexity is 1.68.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132339064","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030927
Shymaa EL-Leithy
The recent widespread of processing and transmitting 3D model in various fields such as computer graphics, animations and visualization calls an essential need for efficient geometry mesh compression technique that became more crucial. This paper explores a progressive compression technique for 3D normal meshes geometry by utilizing one of competitive learning methods. The introduced technique is based on multi-resolution decomposition which was obtained by wavelet transformation. Then the coefficients are quantized by neural gas algorithm as a vector quantizer which improves the visual quality of the reconstructed geometry mesh. Our experiments show that the explored technique out performs the state-of-art techniques in Terms of visual quality of compressed meshes.
{"title":"Neural gas based 3D normal mesh compression","authors":"Shymaa EL-Leithy","doi":"10.1109/ICCES.2014.7030927","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030927","url":null,"abstract":"The recent widespread of processing and transmitting 3D model in various fields such as computer graphics, animations and visualization calls an essential need for efficient geometry mesh compression technique that became more crucial. This paper explores a progressive compression technique for 3D normal meshes geometry by utilizing one of competitive learning methods. The introduced technique is based on multi-resolution decomposition which was obtained by wavelet transformation. Then the coefficients are quantized by neural gas algorithm as a vector quantizer which improves the visual quality of the reconstructed geometry mesh. Our experiments show that the explored technique out performs the state-of-art techniques in Terms of visual quality of compressed meshes.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132351208","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030941
M. K. Bek, E. Shaheen, S. Elgamel
Interference is one of the major concerns when using global positioning system (GPS) receivers. The interference signals may cause severe performance degradation to the GPS receiver performance. It can decrease the post-correlation carrier to noise ratio (C/No), causes the position error or even completely prohibit the acquisition or tracking of satellites. This paper analyzes the matched spectrum interference (MSI) effect on the GPS receiver correlator output. Novel analytical expressions for the MSI power at the correlator output are derived. The post-correlation carrier to noise ratio (C/No) is analytically derived in the presence of MSI and additive white Gaussian noise (AWGN). The time-frequency cross correlation function is defined and analyzed. The effects of the correlator coherent integration time and cross correlation sequence (CCS) spectral line in the MSI effect are also investigated. The derived analytical expressions are verified with the aid of computer based simulations.
{"title":"Mathematical analyses of matched spectrum interference signal on post-correlation C/N0 for the GPS receivers","authors":"M. K. Bek, E. Shaheen, S. Elgamel","doi":"10.1109/ICCES.2014.7030941","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030941","url":null,"abstract":"Interference is one of the major concerns when using global positioning system (GPS) receivers. The interference signals may cause severe performance degradation to the GPS receiver performance. It can decrease the post-correlation carrier to noise ratio (C/No), causes the position error or even completely prohibit the acquisition or tracking of satellites. This paper analyzes the matched spectrum interference (MSI) effect on the GPS receiver correlator output. Novel analytical expressions for the MSI power at the correlator output are derived. The post-correlation carrier to noise ratio (C/No) is analytically derived in the presence of MSI and additive white Gaussian noise (AWGN). The time-frequency cross correlation function is defined and analyzed. The effects of the correlator coherent integration time and cross correlation sequence (CCS) spectral line in the MSI effect are also investigated. The derived analytical expressions are verified with the aid of computer based simulations.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133951829","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030932
Tamer F. Ghanem, W. Elkilani, Hatem S. Ahmed, M. Hadhoud
Clustering multi-dense large scale high dimensional datasets is a challenging task duo to high time complexity of most clustering algorithms. Nowadays, data collection tools produce a large amount of data. So, fast algorithms are vital requirement for clustering such data. In this paper, a fast clustering algorithm, called Dimension-based Partitioning and Merging (DPM), is proposed. In DPM, First, data is partitioned into small dense volumes during the successive processing of dataset dimensions. Then, noise is filtered out using dimensional densities of the generated partitions. Finally, merging process is invoked to construct clusters based on partition boundary data samples. DPM algorithm automatically detects the number of data clusters based on three insensitive tuning parameters which decrease the burden of its usage. Performance evaluation of the proposed algorithm using different datasets shows its fastness and accuracy compared to other clustering competitors.
{"title":"DPM: Fast and scalable clustering algorithm for large scale high dimensional datasets","authors":"Tamer F. Ghanem, W. Elkilani, Hatem S. Ahmed, M. Hadhoud","doi":"10.1109/ICCES.2014.7030932","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030932","url":null,"abstract":"Clustering multi-dense large scale high dimensional datasets is a challenging task duo to high time complexity of most clustering algorithms. Nowadays, data collection tools produce a large amount of data. So, fast algorithms are vital requirement for clustering such data. In this paper, a fast clustering algorithm, called Dimension-based Partitioning and Merging (DPM), is proposed. In DPM, First, data is partitioned into small dense volumes during the successive processing of dataset dimensions. Then, noise is filtered out using dimensional densities of the generated partitions. Finally, merging process is invoked to construct clusters based on partition boundary data samples. DPM algorithm automatically detects the number of data clusters based on three insensitive tuning parameters which decrease the burden of its usage. Performance evaluation of the proposed algorithm using different datasets shows its fastness and accuracy compared to other clustering competitors.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132713422","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030945
Shereen M. Mosharafa, G. A. Ebrahim, A. Zekry
Audio-video synchronization is a very common quality issue that has a direct effect on the end-user's experience. Audio and video streams are supposed to be synchronized at the transmitter. However, they might be received out of synchronization. In general, loss of synchronization between audio and video streams may be attributed to several factors such as incorrect time-stamping at the transmitter, frame loss, and the different delays introduced by the signal processing and post-processing functions on each stream. Unfortunately, the video pipeline is much complicated as compared with the audio pipeline. Hence, during the journey of the streams from the transmitter to the presentation unit at the receiver, they may be susceptible to different processing delays. These different delays can make the two streams finally presented out of phase. Different algorithms were developed for preserving synchronization at the receiver side in order to provide the best possible perceptual quality. However, most of these algorithms rely on the encoded data of the bit streams. Hence, this paper introduces a new audio-video synchronization algorithm that exploits some features in MPEG-2 system layer. It addresses the misalignment of audio and video streams occurred due to the different processing and post-processing delays. The proposed algorithm relies on both the system clock reference and the relative alignment between the audio and video streams.
{"title":"A novel algorithm for synchronizing audio and video streams in MPEG-2 system layer","authors":"Shereen M. Mosharafa, G. A. Ebrahim, A. Zekry","doi":"10.1109/ICCES.2014.7030945","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030945","url":null,"abstract":"Audio-video synchronization is a very common quality issue that has a direct effect on the end-user's experience. Audio and video streams are supposed to be synchronized at the transmitter. However, they might be received out of synchronization. In general, loss of synchronization between audio and video streams may be attributed to several factors such as incorrect time-stamping at the transmitter, frame loss, and the different delays introduced by the signal processing and post-processing functions on each stream. Unfortunately, the video pipeline is much complicated as compared with the audio pipeline. Hence, during the journey of the streams from the transmitter to the presentation unit at the receiver, they may be susceptible to different processing delays. These different delays can make the two streams finally presented out of phase. Different algorithms were developed for preserving synchronization at the receiver side in order to provide the best possible perceptual quality. However, most of these algorithms rely on the encoded data of the bit streams. Hence, this paper introduces a new audio-video synchronization algorithm that exploits some features in MPEG-2 system layer. It addresses the misalignment of audio and video streams occurred due to the different processing and post-processing delays. The proposed algorithm relies on both the system clock reference and the relative alignment between the audio and video streams.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121216413","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030988
Shereen M. Mosharafa, G. A. Ebrahim, A. Zekry
This paper introduces an approach that adopts a two-stage multiplexing strategy for MPEG-2 transport stream encoder. The first stage in the proposed approach is responsible for multiplexing the elementary streams while the second stage is responsible for multiplexing the program streams. The function of the first stage is to form a single program transport stream from the elementary streams. It is designed to facilitate synchronization between elementary streams at the receiver. In other words, the transmission of elementary streams is time-interleaved according to the relative presentation time represented by each packet from each stream. On the other hand, the second stage is utilized to multiplex program streams to form a transport stream that conforms to MPEG-2 T-STD buffer requirements. The proposed approach reduces the real-time overhead compared with the other related approaches. Mainly, because other approaches make the multiplexing decision at the transmission time while the proposed approach takes this decision in advance. Hence, it reduces the associated overhead at the transmission time. A prototype of the proposed approach has been implemented in VHDL to evaluate its performance. Additionally, it has proven its effectiveness while testing it with H.264 and AAC codecs that are supported by digital video broadcasting systems.
{"title":"An efficient multiplexing approach for MPEG-2 transport stream encoder","authors":"Shereen M. Mosharafa, G. A. Ebrahim, A. Zekry","doi":"10.1109/ICCES.2014.7030988","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030988","url":null,"abstract":"This paper introduces an approach that adopts a two-stage multiplexing strategy for MPEG-2 transport stream encoder. The first stage in the proposed approach is responsible for multiplexing the elementary streams while the second stage is responsible for multiplexing the program streams. The function of the first stage is to form a single program transport stream from the elementary streams. It is designed to facilitate synchronization between elementary streams at the receiver. In other words, the transmission of elementary streams is time-interleaved according to the relative presentation time represented by each packet from each stream. On the other hand, the second stage is utilized to multiplex program streams to form a transport stream that conforms to MPEG-2 T-STD buffer requirements. The proposed approach reduces the real-time overhead compared with the other related approaches. Mainly, because other approaches make the multiplexing decision at the transmission time while the proposed approach takes this decision in advance. Hence, it reduces the associated overhead at the transmission time. A prototype of the proposed approach has been implemented in VHDL to evaluate its performance. Additionally, it has proven its effectiveness while testing it with H.264 and AAC codecs that are supported by digital video broadcasting systems.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121279549","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030951
Nesma M. Rezk, Y. Alkabani, H.S. Bedor, S. Hammad
Obstacle avoidance is an extremely important task in swarm robotics as it saves robots from hitting objects and being damaged. A Genetic algorithm can be used to teach robots how to avoid obstacles in different environments. However the evaluation module of this genetic algorithm can be very time consuming module as each candidate solution should be evaluated N times. This paper explains the methodology used to distribute the evaluation module of genetic Algorithm over a cluster of computers to speed up the algorithm. The proposed methodology can be used for any application which suffers from time consuming evaluation module. Experimental results showed that the speedup can reach 70x.
{"title":"A distributed genetic algorithm for swarm robots obstacle avoidance","authors":"Nesma M. Rezk, Y. Alkabani, H.S. Bedor, S. Hammad","doi":"10.1109/ICCES.2014.7030951","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030951","url":null,"abstract":"Obstacle avoidance is an extremely important task in swarm robotics as it saves robots from hitting objects and being damaged. A Genetic algorithm can be used to teach robots how to avoid obstacles in different environments. However the evaluation module of this genetic algorithm can be very time consuming module as each candidate solution should be evaluated N times. This paper explains the methodology used to distribute the evaluation module of genetic Algorithm over a cluster of computers to speed up the algorithm. The proposed methodology can be used for any application which suffers from time consuming evaluation module. Experimental results showed that the speedup can reach 70x.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132572418","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}
Pub Date : 2014-12-01DOI: 10.1109/ICCES.2014.7030972
Shymaa Saad, M. S. Yasein, M. Mousa, H. Nassar
This paper describes a new method for pedestrian detection. The focus of the proposed method is to enhance the number of detected pedestrian and to achieve high accuracy with low rates of false negative detection. The method has two stages: the first stage detects pedestrians using part based detector (poselet) while the second stage further detects people by combine top-down recognition with bottom-up image segmentation. For feature extraction, Pyramid Histogram of Orientation Gradient (PHOG) and Shape Context (SC) are used. The proposed method was tested on a popular pedestrian detection benchmark dataset “INRIA person data set” and experimental results show that the detection method achieves high accuracy with low rates of false negative detection.
{"title":"Pedestrian detection using shape context and PHOG","authors":"Shymaa Saad, M. S. Yasein, M. Mousa, H. Nassar","doi":"10.1109/ICCES.2014.7030972","DOIUrl":"https://doi.org/10.1109/ICCES.2014.7030972","url":null,"abstract":"This paper describes a new method for pedestrian detection. The focus of the proposed method is to enhance the number of detected pedestrian and to achieve high accuracy with low rates of false negative detection. The method has two stages: the first stage detects pedestrians using part based detector (poselet) while the second stage further detects people by combine top-down recognition with bottom-up image segmentation. For feature extraction, Pyramid Histogram of Orientation Gradient (PHOG) and Shape Context (SC) are used. The proposed method was tested on a popular pedestrian detection benchmark dataset “INRIA person data set” and experimental results show that the detection method achieves high accuracy with low rates of false negative detection.","PeriodicalId":339697,"journal":{"name":"2014 9th International Conference on Computer Engineering & Systems (ICCES)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129767779","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：