Pub Date : 2018-04-01DOI: 10.1109/ISACV.2018.8354032
S. Farrah, Hanane El Manssouri, E. Ziyati, M. Ouzzif
Platforms interacting with data in text format, such as social networks or search engines, face major challenges regarding this flow of texts such as storage, search and information processing. New disciplines have emerged as natural language processing that involve identifying all aspects of language (spoken or written). In this perspective, we focus on the aspect of part-of speech (POS) tagging applied to the Arabic language which consists in marking each word in the text with its good tag. One of the most difficult problems affecting POS tagging is the ambiguity of the text. Ambiguity is the most important problem in the natural language processing. We propose a rule-based hybrid approach with an artificial neural network classifier to determine the appropriate tags of an Arabic text. The first phase consists of extracting all the affixes to identify the nature of the word and its tags according to grammatical rules, the second phase begins by transliterating the Arabic text into text with Roman letters. The transliterated text is then transformed into digital vectors to form the input of the classifier based on the neural networks. The two phases are combined to identify the tag of each word.
{"title":"An hybrid approach to improve part of speech tagging system","authors":"S. Farrah, Hanane El Manssouri, E. Ziyati, M. Ouzzif","doi":"10.1109/ISACV.2018.8354032","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354032","url":null,"abstract":"Platforms interacting with data in text format, such as social networks or search engines, face major challenges regarding this flow of texts such as storage, search and information processing. New disciplines have emerged as natural language processing that involve identifying all aspects of language (spoken or written). In this perspective, we focus on the aspect of part-of speech (POS) tagging applied to the Arabic language which consists in marking each word in the text with its good tag. One of the most difficult problems affecting POS tagging is the ambiguity of the text. Ambiguity is the most important problem in the natural language processing. We propose a rule-based hybrid approach with an artificial neural network classifier to determine the appropriate tags of an Arabic text. The first phase consists of extracting all the affixes to identify the nature of the word and its tags according to grammatical rules, the second phase begins by transliterating the Arabic text into text with Roman letters. The transliterated text is then transformed into digital vectors to form the input of the classifier based on the neural networks. The two phases are combined to identify the tag of each word.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129382185","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354042
Elhoussaine Baba, A. Jilbab, A. Hammouch
Among the important research projects much deployed in healthcare field there is the wireless body Area networks (WBANs) applications, which can widely help to remote monitor the human health. This research aims to develop a wearable WBAN application for health remote monitoring, that monitor patient's health trough the continuous detection, process and communicate of human physiological parameters. This application use four biomedical sensor nodes that are able to measure physiological signal (ECG, SPO2, heart rate and breathing) and convert it to useful data. Then, the data are processed by a processor and transmitted to a central node using a transceiver. The central node collect the data and send it in real-time to the monitoring PC, which displays and records the physiological parameters on a graphical interface.
{"title":"A health remote monitoring application based on wireless body area networks","authors":"Elhoussaine Baba, A. Jilbab, A. Hammouch","doi":"10.1109/ISACV.2018.8354042","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354042","url":null,"abstract":"Among the important research projects much deployed in healthcare field there is the wireless body Area networks (WBANs) applications, which can widely help to remote monitor the human health. This research aims to develop a wearable WBAN application for health remote monitoring, that monitor patient's health trough the continuous detection, process and communicate of human physiological parameters. This application use four biomedical sensor nodes that are able to measure physiological signal (ECG, SPO2, heart rate and breathing) and convert it to useful data. Then, the data are processed by a processor and transmitted to a central node using a transceiver. The central node collect the data and send it in real-time to the monitoring PC, which displays and records the physiological parameters on a graphical interface.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115287099","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354066
Mouna Jiber, Imad Lamouik, Yahyaouy Ali, M. A. Sabri
Traffic flow management and analysis have become essential for both individuals to better manage and route their daily commutes, and for transportation planners to optimally schedule road infrastructure maintenance tasks. Therefore the ability to predict the nature of the traffic stream accurately is one of the most important requirements of traffic management systems. In this research, we will propose an intelligent method to predict traffic flow based on real data for the years 2016 and 2017 provided by the Moroccan center for road studies and research. The proposed solution focuses on training a neural network model to estimate future traffic flow on an hourly basis. Results determined by the simulation gave a good prediction to the traffic data.
{"title":"Traffic flow prediction using neural network","authors":"Mouna Jiber, Imad Lamouik, Yahyaouy Ali, M. A. Sabri","doi":"10.1109/ISACV.2018.8354066","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354066","url":null,"abstract":"Traffic flow management and analysis have become essential for both individuals to better manage and route their daily commutes, and for transportation planners to optimally schedule road infrastructure maintenance tasks. Therefore the ability to predict the nature of the traffic stream accurately is one of the most important requirements of traffic management systems. In this research, we will propose an intelligent method to predict traffic flow based on real data for the years 2016 and 2017 provided by the Moroccan center for road studies and research. The proposed solution focuses on training a neural network model to estimate future traffic flow on an hourly basis. Results determined by the simulation gave a good prediction to the traffic data.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126220327","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354074
Soukaina Chraa Mesbahi, Mohamed Adnane Mahraz, J. Riffi, H. Tairi
This paper presents a method for hand gesture recognition using convexity defect and background subtraction. First, the background subtraction is used to eliminate the useless information. To find contour of segmented hand images we used images processing techniques. After that we calculate the convex hull and convexity defects for this contour. The feature extraction purposes to detect and extract features that can be used to determine the significance of a given hand gesture. The features must be able to characterize gesture only, and invariant under translation and rotation of hand gesture to ensure reliable recognition. We propose a method to extract a series of features based on convex defect detection, catching advantage of the close relationship of convex defect and fingertips. This method is mere, efficient and free from gesture direction and position. We have tested five hand gestures classes to show using one, two, three, four, and five fingers one by one.
{"title":"Hand gesture recognition based on convexity approach and background subtraction","authors":"Soukaina Chraa Mesbahi, Mohamed Adnane Mahraz, J. Riffi, H. Tairi","doi":"10.1109/ISACV.2018.8354074","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354074","url":null,"abstract":"This paper presents a method for hand gesture recognition using convexity defect and background subtraction. First, the background subtraction is used to eliminate the useless information. To find contour of segmented hand images we used images processing techniques. After that we calculate the convex hull and convexity defects for this contour. The feature extraction purposes to detect and extract features that can be used to determine the significance of a given hand gesture. The features must be able to characterize gesture only, and invariant under translation and rotation of hand gesture to ensure reliable recognition. We propose a method to extract a series of features based on convex defect detection, catching advantage of the close relationship of convex defect and fingertips. This method is mere, efficient and free from gesture direction and position. We have tested five hand gestures classes to show using one, two, three, four, and five fingers one by one.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123223415","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354081
Meriem Bahi, M. Batouche
Drug repositioning is the process of recycling existing drugs for new indications by identifying the potential drug-target interactions (DTIs). However, in silico predicting new associations between drugs and target proteins is a challenging issue, due to the scarcity of known DTIs and no experimentally true negative drug-target interaction sample. Furthermore, the volume of genomic sequences and chemical structures data is growing in an exponential manner, which consumes relatively too much time and effort. For these reasons, we propose a new computational method based on deep semi-supervised learning called DSSL-DTIs to accurately predict new DTI in post-genome era using large datasets and Spark-H2O platform. Firstly, we use the stacked autoencoders to convert high-dimensional features to low-dimensional representations. Then, we apply another unsupervised stacked autoencoders model for initializing the weights of a supervised deep neural network model. Comparing to other state-of-the-art methods applied all on the same reference dataset of Drug-Bank, it is found that our approach outperforms these techniques with an overall accuracy performance more than 98%. The DSSL-DTIs can be further used to predict large-scale new drug-target interactions. The highly ranked candidate DTIs obtained from DSSL-DTIs are also confirmed in the DrugBank database and in the literature, which demonstrates the effectiveness of our method.
{"title":"Deep semi-supervised learning for DTI prediction using large datasets and H2O-spark platform","authors":"Meriem Bahi, M. Batouche","doi":"10.1109/ISACV.2018.8354081","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354081","url":null,"abstract":"Drug repositioning is the process of recycling existing drugs for new indications by identifying the potential drug-target interactions (DTIs). However, in silico predicting new associations between drugs and target proteins is a challenging issue, due to the scarcity of known DTIs and no experimentally true negative drug-target interaction sample. Furthermore, the volume of genomic sequences and chemical structures data is growing in an exponential manner, which consumes relatively too much time and effort. For these reasons, we propose a new computational method based on deep semi-supervised learning called DSSL-DTIs to accurately predict new DTI in post-genome era using large datasets and Spark-H2O platform. Firstly, we use the stacked autoencoders to convert high-dimensional features to low-dimensional representations. Then, we apply another unsupervised stacked autoencoders model for initializing the weights of a supervised deep neural network model. Comparing to other state-of-the-art methods applied all on the same reference dataset of Drug-Bank, it is found that our approach outperforms these techniques with an overall accuracy performance more than 98%. The DSSL-DTIs can be further used to predict large-scale new drug-target interactions. The highly ranked candidate DTIs obtained from DSSL-DTIs are also confirmed in the DrugBank database and in the literature, which demonstrates the effectiveness of our method.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131228788","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354065
N. Benaya, N. El-Akchioui, T. Mourabit
Reliability analysis is often based on stochastic discrete event models like Markov models or stochastic Petri nets. For complex dynamical systems with numerous components, analytical expressions of the steady state are tedious to work out because of the combinatory explosion with discrete models. Moreover, the convergence of stochastic estimators is slow. For these reasons, fluidification can be investigated to estimate the asymptotic behavior of stochastic processes with timed continuous Petri nets. The contribution of this paper is to sum up some properties of the asymptotic mean marking and average throughputs of stochastic and timed continuous Petri nets, then to point out the limits of the fluidification.
{"title":"Limits of fluidification for a stochastic Petri nets by timed continuous Petri nets","authors":"N. Benaya, N. El-Akchioui, T. Mourabit","doi":"10.1109/ISACV.2018.8354065","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354065","url":null,"abstract":"Reliability analysis is often based on stochastic discrete event models like Markov models or stochastic Petri nets. For complex dynamical systems with numerous components, analytical expressions of the steady state are tedious to work out because of the combinatory explosion with discrete models. Moreover, the convergence of stochastic estimators is slow. For these reasons, fluidification can be investigated to estimate the asymptotic behavior of stochastic processes with timed continuous Petri nets. The contribution of this paper is to sum up some properties of the asymptotic mean marking and average throughputs of stochastic and timed continuous Petri nets, then to point out the limits of the fluidification.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132283178","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354047
K. Hafed, Y. Fakhri, S. Boulaknadel, A. Moumen, H. Jamil, Badraddine Aghoutane
Business Intelligence is the result of the data analysis applications and technologies with the intention of providing a global view of the activities to an organization managers so as to facilitate their decision-making. When it comes to a collective decision, the contribution of business intelligence systems becomes crucial. In Morocco, and particularly in the Draa-Tafilalet region, each public service follows a strategy and a plan of action in order to contribute to the development of the region, which is one of the most important oasis areas of the country. Thus, given the characteristic of this region, many development projects have been initiated by the local authorities. in most cases, those regional actors are called to work together. But unfortunately in some cases, we find a lack of coordination between them, which negatively impacts the outcome of these projects, and causes a considerable loss of budget resources and a delay in the programs and planning. So, we are going to present a review of business intelligence systems with their attributes and characteristics. Then, in a second step, we will propose an approach to develop a business intelligence system for the actors of the Draa-Tafilalet region to measure their performances and qualities.
{"title":"Decisional information systems of the public actors in Moroccan Oasis Zones: Case study Draa-Tafilalet region: Towards a descriptive approach and a measurement of qualities and performances","authors":"K. Hafed, Y. Fakhri, S. Boulaknadel, A. Moumen, H. Jamil, Badraddine Aghoutane","doi":"10.1109/ISACV.2018.8354047","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354047","url":null,"abstract":"Business Intelligence is the result of the data analysis applications and technologies with the intention of providing a global view of the activities to an organization managers so as to facilitate their decision-making. When it comes to a collective decision, the contribution of business intelligence systems becomes crucial. In Morocco, and particularly in the Draa-Tafilalet region, each public service follows a strategy and a plan of action in order to contribute to the development of the region, which is one of the most important oasis areas of the country. Thus, given the characteristic of this region, many development projects have been initiated by the local authorities. in most cases, those regional actors are called to work together. But unfortunately in some cases, we find a lack of coordination between them, which negatively impacts the outcome of these projects, and causes a considerable loss of budget resources and a delay in the programs and planning. So, we are going to present a review of business intelligence systems with their attributes and characteristics. Then, in a second step, we will propose an approach to develop a business intelligence system for the actors of the Draa-Tafilalet region to measure their performances and qualities.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132868067","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354069
Y. Filali, A. Ennouni, M. A. Sabri, A. Aarab
Among the most dangerous cancer in the world is skin cancer. If not diagnosed in early stages it might be hard to cure. The aim of this work is to present a study of skin segmentation, features selection and classification approaches. In the segmentation stage, we will present the result of the use of a pre-processing based on a multiscale decomposition model where geometrical component is used to get a good segmentation. The features are firstly extracted using the texture component and color of the lesion, and then we will present a comparative study of some features selection approaches that select the relevant ones. In feature classification we will compare between the most and good classifiers used in literature.
{"title":"A study of lesion skin segmentation, features selection and classification approaches","authors":"Y. Filali, A. Ennouni, M. A. Sabri, A. Aarab","doi":"10.1109/ISACV.2018.8354069","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354069","url":null,"abstract":"Among the most dangerous cancer in the world is skin cancer. If not diagnosed in early stages it might be hard to cure. The aim of this work is to present a study of skin segmentation, features selection and classification approaches. In the segmentation stage, we will present the result of the use of a pre-processing based on a multiscale decomposition model where geometrical component is used to get a good segmentation. The features are firstly extracted using the texture component and color of the lesion, and then we will present a comparative study of some features selection approaches that select the relevant ones. In feature classification we will compare between the most and good classifiers used in literature.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127311822","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354077
El Hassane Khabbiza, R. El Alami, H. Qjidaa
With the rapid growth of IPTV (Internet Protocol Television), the need to efficiently disseminate the large volumes of IPTV unicast services such video on Demand (VOD) and Time shift TV (TSTV) has prompted IPTV service providers to search for new solutions to optimize the video bandwidth and service load. This paper describes a new peer-assisted solution to optimize the TSTV bandwidth, a solution that uses the users Set-Top-Boxes (STB) to assist the central TSTV servers in the content delivery, this mean that, after each TSTV request, the STB will receive the TSTV stream from another STB instead of the central server by using this method the unicast traffic will not pass through the IP network, it will be a peer to peer communication via the Access Network only. Extensive simulation results have presented to demonstrate the robustness of our new solution.
随着IPTV (Internet Protocol Television)的快速发展，高效传播VOD (video on Demand)和TSTV (Time shift TV)等海量IPTV单播业务的需求，促使IPTV服务提供商寻求新的解决方案来优化视频带宽和业务负载。本文介绍了一种新的对等辅助的TSTV带宽优化方案，该方案利用用户机顶盒(STB)辅助TSTV中心服务器进行内容分发，即每次TSTV请求后，机顶盒将从另一个机顶盒接收TSTV流，而不是从中央服务器接收，使用这种方法，单播流量将不经过IP网络，而是通过接入网进行点对点通信。大量的仿真结果证明了该方法的鲁棒性。
{"title":"A new solution to optimize the time shift TV bandwidth","authors":"El Hassane Khabbiza, R. El Alami, H. Qjidaa","doi":"10.1109/ISACV.2018.8354077","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354077","url":null,"abstract":"With the rapid growth of IPTV (Internet Protocol Television), the need to efficiently disseminate the large volumes of IPTV unicast services such video on Demand (VOD) and Time shift TV (TSTV) has prompted IPTV service providers to search for new solutions to optimize the video bandwidth and service load. This paper describes a new peer-assisted solution to optimize the TSTV bandwidth, a solution that uses the users Set-Top-Boxes (STB) to assist the central TSTV servers in the content delivery, this mean that, after each TSTV request, the STB will receive the TSTV stream from another STB instead of the central server by using this method the unicast traffic will not pass through the IP network, it will be a peer to peer communication via the Access Network only. Extensive simulation results have presented to demonstrate the robustness of our new solution.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127381668","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 : 2018-04-01DOI: 10.1109/ISACV.2018.8354040
Abderrahim El Bouziady, R. Thami, M. Ghogho, Omar Bourja, S. El Fkihi
In this paper, we present a novel technique to estimate vehicle speed on highway using stereo images. First, traffic images are captured using calibrated and synchronized stereo cameras, then we detect moving vehicles on the left image by subtracting the background image. On each detected vehicle, we extract and match Speed Up Robust Features (SURF) in order to compute sparse depth maps. Finally, we get vehicle speed from vehicle depth variation using some geometric derivations. The experiments shows that the proposed algorithm has a satisfactory estimation of vehicle speed comparing to GPS ground truth with a speed error of 2 Km/h in the Moroccan environment.
{"title":"Vehicle speed estimation using extracted SURF features from stereo images","authors":"Abderrahim El Bouziady, R. Thami, M. Ghogho, Omar Bourja, S. El Fkihi","doi":"10.1109/ISACV.2018.8354040","DOIUrl":"https://doi.org/10.1109/ISACV.2018.8354040","url":null,"abstract":"In this paper, we present a novel technique to estimate vehicle speed on highway using stereo images. First, traffic images are captured using calibrated and synchronized stereo cameras, then we detect moving vehicles on the left image by subtracting the background image. On each detected vehicle, we extract and match Speed Up Robust Features (SURF) in order to compute sparse depth maps. Finally, we get vehicle speed from vehicle depth variation using some geometric derivations. The experiments shows that the proposed algorithm has a satisfactory estimation of vehicle speed comparing to GPS ground truth with a speed error of 2 Km/h in the Moroccan environment.","PeriodicalId":184662,"journal":{"name":"2018 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128923512","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：