Pub Date : 2013-12-01DOI: 10.1109/RAICS.2013.6745447
Rakshith Shetty, Prasanna Sethuraman
One of the fundamental problems in building an autonomous robot is the perception and reconstruction of its environment, which is traditionally achieved with sensory systems that use camera, laser, sonar, or radar. This paper proposes the use of an Orthogonal Frequency Division Multiplexing (OFDM) based radio to sense the environment. Our solution uses an OFDM wireless transmitter, such as the one from Wi-Fi, on the robot to transmit a signal which is then reflected back by obstacles, and the reflected signal is captured with an onboard receiver. The receiver analyzes the incoming signal for multipath delay and angles of arrival of each of these resolvable multipath components. The angle of arrival estimation is achieved without using a large antenna array at the receiver, but with an iterative angle estimation mechanism that can work with just two receive antennas. The resulting range sensor can detect obstacles at multiple directions and multiple distances by analyzing just one received Wi-Fi packet. The generated obstacle map is then improved by combining different map instances estimated by the robot from different positions. Advantages of this sensor includes very fast scan time and, since we can reuse the ubiquitous Wi-Fi radio to transmit the OFDM signal on air, the sensor cost is much lower compared to traditional range sensors.
{"title":"OFDM radio based range and direction sensor for robotics applications","authors":"Rakshith Shetty, Prasanna Sethuraman","doi":"10.1109/RAICS.2013.6745447","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745447","url":null,"abstract":"One of the fundamental problems in building an autonomous robot is the perception and reconstruction of its environment, which is traditionally achieved with sensory systems that use camera, laser, sonar, or radar. This paper proposes the use of an Orthogonal Frequency Division Multiplexing (OFDM) based radio to sense the environment. Our solution uses an OFDM wireless transmitter, such as the one from Wi-Fi, on the robot to transmit a signal which is then reflected back by obstacles, and the reflected signal is captured with an onboard receiver. The receiver analyzes the incoming signal for multipath delay and angles of arrival of each of these resolvable multipath components. The angle of arrival estimation is achieved without using a large antenna array at the receiver, but with an iterative angle estimation mechanism that can work with just two receive antennas. The resulting range sensor can detect obstacles at multiple directions and multiple distances by analyzing just one received Wi-Fi packet. The generated obstacle map is then improved by combining different map instances estimated by the robot from different positions. Advantages of this sensor includes very fast scan time and, since we can reuse the ubiquitous Wi-Fi radio to transmit the OFDM signal on air, the sensor cost is much lower compared to traditional range sensors.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114329922","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745464
S. Biswas, J. Sil
Automatic gender classification has immense applications in many commercial domains. In the paper, spatial and temporal feature based gender classification technique has been proposed. In the first step, texture based features in the spatial domain are extracted by dividing the training images into no. of blocks. Covariance matrix and singular value decomposition method has been applied on each block to extract the features. Discrete Wavelet Transform (DWT) has been introduced in the second step to extract temporal features. The feature vectors of test images are obtained and classified as male or female by Weka tool using 10 fold cross validation technique. The proposed approach provides 98% recognition rate on GTAV database while 91% on FERET database.
{"title":"Gender classification using spatial and temporal features","authors":"S. Biswas, J. Sil","doi":"10.1109/RAICS.2013.6745464","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745464","url":null,"abstract":"Automatic gender classification has immense applications in many commercial domains. In the paper, spatial and temporal feature based gender classification technique has been proposed. In the first step, texture based features in the spatial domain are extracted by dividing the training images into no. of blocks. Covariance matrix and singular value decomposition method has been applied on each block to extract the features. Discrete Wavelet Transform (DWT) has been introduced in the second step to extract temporal features. The feature vectors of test images are obtained and classified as male or female by Weka tool using 10 fold cross validation technique. The proposed approach provides 98% recognition rate on GTAV database while 91% on FERET database.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123079098","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745483
Sijin Mary Joy, S. S. Kumar
Microstrip bandpass filters are used to select or confine the RF/microwave signals within assigned spectral limits so as to share the limited electromagnetic spectrum. Use of dual mode resonator allows the realization of a compact high quality microwave bandpass filter (BPF). The filters designed with fractal geometry are having reduced return loss and good passband performance. This paper presents a triangular microstrip loop resonator BPF constructed using Fractal Koch curve approach. The simulation results show that the proposed fractal triangular microstrip loop resonator can achieve lower resonant frequencies compared to conventional triangular loop resonator filter hence size reduction is possible. Also a better performance is obtained in case of fractal triangular loop resonator bandpass filter.
{"title":"Triangular microstrip loop resonator bandpass filter using Koch curve approach","authors":"Sijin Mary Joy, S. S. Kumar","doi":"10.1109/RAICS.2013.6745483","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745483","url":null,"abstract":"Microstrip bandpass filters are used to select or confine the RF/microwave signals within assigned spectral limits so as to share the limited electromagnetic spectrum. Use of dual mode resonator allows the realization of a compact high quality microwave bandpass filter (BPF). The filters designed with fractal geometry are having reduced return loss and good passband performance. This paper presents a triangular microstrip loop resonator BPF constructed using Fractal Koch curve approach. The simulation results show that the proposed fractal triangular microstrip loop resonator can achieve lower resonant frequencies compared to conventional triangular loop resonator filter hence size reduction is possible. Also a better performance is obtained in case of fractal triangular loop resonator bandpass filter.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124991711","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745439
B. Soniya, M. Wilscy
Botnets are proliferating on the web and are increasingly being used by criminals for data theft, denial of service attacks, spamming and such other activities. Several bot detection approaches have been proposed which can be classified as either host-based or network-based. A hybrid approach which mitigates the disadvantages of the previous two approaches is proposed here. The proposed method aims to identify bots on a single host by looking at the network traffic generated by the host. The detection method is designed for HTTP traffic. A characterization of normal HTTP traffic as well as bot traffic is initially done using features extracted from network packets. A Neural Network Classifier is trained using these traffic features and later used to classify unlabeled traffic as benign or malicious. A normal traffic profile is first used to filter out packets to commonly accessed destinations thereby reducing the workload on the classifier. Stealthy bots which communicate at large time intervals of up to 32 hours are also detected. 120 bots samples were used to evaluate the system. The experimental results demonstrate a high detection rate of 97.4% and a very low false positive rate of 2.5%. The performance of the system is compared with many recent bot detection methods.
{"title":"Using entropy of traffic features to identify bot infected hosts","authors":"B. Soniya, M. Wilscy","doi":"10.1109/RAICS.2013.6745439","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745439","url":null,"abstract":"Botnets are proliferating on the web and are increasingly being used by criminals for data theft, denial of service attacks, spamming and such other activities. Several bot detection approaches have been proposed which can be classified as either host-based or network-based. A hybrid approach which mitigates the disadvantages of the previous two approaches is proposed here. The proposed method aims to identify bots on a single host by looking at the network traffic generated by the host. The detection method is designed for HTTP traffic. A characterization of normal HTTP traffic as well as bot traffic is initially done using features extracted from network packets. A Neural Network Classifier is trained using these traffic features and later used to classify unlabeled traffic as benign or malicious. A normal traffic profile is first used to filter out packets to commonly accessed destinations thereby reducing the workload on the classifier. Stealthy bots which communicate at large time intervals of up to 32 hours are also detected. 120 bots samples were used to evaluate the system. The experimental results demonstrate a high detection rate of 97.4% and a very low false positive rate of 2.5%. The performance of the system is compared with many recent bot detection methods.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131519438","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745479
H. R. Shamna, Naga Lakshmi Appari, L. Jacob
This work investigates a Cooperative Medium Access Control (CoopMAC) protocol that is backward compatible with the legacy 802.11 system, in which high data rate stations assist low data rate stations in their transmission by forwarding their traffic. New mathematical models have been developed in this work for the performance evaluation of this protocol under different channel conditions and for unsaturated traffic loads. Extensive simulation results validate the mathematical models developed and show that CoopMAC protocol can significantly improve system throughput, service delay, and energy efficiency for WLANs operating under realistic communication scenarios.
{"title":"Co-operative MAC protocol: Performance modeling and analysis","authors":"H. R. Shamna, Naga Lakshmi Appari, L. Jacob","doi":"10.1109/RAICS.2013.6745479","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745479","url":null,"abstract":"This work investigates a Cooperative Medium Access Control (CoopMAC) protocol that is backward compatible with the legacy 802.11 system, in which high data rate stations assist low data rate stations in their transmission by forwarding their traffic. New mathematical models have been developed in this work for the performance evaluation of this protocol under different channel conditions and for unsaturated traffic loads. Extensive simulation results validate the mathematical models developed and show that CoopMAC protocol can significantly improve system throughput, service delay, and energy efficiency for WLANs operating under realistic communication scenarios.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131382869","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745438
Sandhya Harikumar, H. Haripriya, M. D. Kaimal
Projected clustering is one of the clustering approaches that determine the clusters in the subspaces of high dimensional data. Although it is possible to efficiently cluster a very large data set outside a relational database, the time and effort to export and import it can be significant. In commercial RDBMSs, there is no SQL query available for any type of subspace clustering, which is more suitable for large databases with high dimensions and large number of records. Integrating clustering with a relational DBMS using SQL is an important and challenging problem in todays world of Big Data. Projected clustering has the ability to find the closely correlated dimensions and find clusters in the corresponding subspaces. We have designed an SQL version of projected clustering which helps to get the clusters of the records in the database using a single SQL statement which in itself calls other SQL functions defined by us. We have used PostgreSQL DBMS to validate our implementation and have done experimentation with synthetic as well as real data.
{"title":"Implementation of projected clustering based on SQL queries and UDFs in relational databases","authors":"Sandhya Harikumar, H. Haripriya, M. D. Kaimal","doi":"10.1109/RAICS.2013.6745438","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745438","url":null,"abstract":"Projected clustering is one of the clustering approaches that determine the clusters in the subspaces of high dimensional data. Although it is possible to efficiently cluster a very large data set outside a relational database, the time and effort to export and import it can be significant. In commercial RDBMSs, there is no SQL query available for any type of subspace clustering, which is more suitable for large databases with high dimensions and large number of records. Integrating clustering with a relational DBMS using SQL is an important and challenging problem in todays world of Big Data. Projected clustering has the ability to find the closely correlated dimensions and find clusters in the corresponding subspaces. We have designed an SQL version of projected clustering which helps to get the clusters of the records in the database using a single SQL statement which in itself calls other SQL functions defined by us. We have used PostgreSQL DBMS to validate our implementation and have done experimentation with synthetic as well as real data.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"113 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120867082","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745463
V. M. Sethu Janaki, S. Babu, S. Sreekanth
Gesture-based user interaction is increasingly relevant today as the use of personal computing devices becomes widespread. Smartphones have several inbuilt sensors like accelerometer, orientation sensor and gyroscope, which are able to provide data on motion of the device in 3D space. This paper proposes a mechanism for real-time recognition of 3D gestures using sensors in mobile devices. 3D gestures are space-drawn gestures computed from 3-axial accelerometer readings. The algorithms discussed in this paper include single value decomposition, dynamic time warping and Mahalanobis distance.
{"title":"Real time recognition of 3D gestures in mobile devices","authors":"V. M. Sethu Janaki, S. Babu, S. Sreekanth","doi":"10.1109/RAICS.2013.6745463","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745463","url":null,"abstract":"Gesture-based user interaction is increasingly relevant today as the use of personal computing devices becomes widespread. Smartphones have several inbuilt sensors like accelerometer, orientation sensor and gyroscope, which are able to provide data on motion of the device in 3D space. This paper proposes a mechanism for real-time recognition of 3D gestures using sensors in mobile devices. 3D gestures are space-drawn gestures computed from 3-axial accelerometer readings. The algorithms discussed in this paper include single value decomposition, dynamic time warping and Mahalanobis distance.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131011194","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745487
P. N. Sharath Kumar, R. R. Kumar, A. Sathar, V. Sahasranamam
Diabetic Retinopathy (DR) is the major cause of blindness caused by the damage to the blood vessels in the retina from diabetes. It cannot be prevented but early detection through fundus imaging by an ophthalmologist can prevent further vision loss. Presence of microaneurysms, hemorrhages, cotton-wool spots and exudates are the symptoms of mild DR. Of these, the detection of exudates is one of the important factors in the early diagnosis of DR. Exudates are fatty deposits on the retina which appear as yellowish regions in fundus image. Fundus images show considerable variation in brightness which makes automatic detection of exudates difficult. In this study, we are proposing a new method for preprocessing and false positive elimination towards the reliable detection of exudates. The brightness of the fundus image was changed by the nonlinear curve with brightness values of the hue saturation value (HSV) space. To emphasize brighter yellow regions (exudates), gamma correction was performed on each red and green components of the image. Subsequently, the histograms of each red and green component were extended. After that, the exudates candidates were detected using histogram analysis. Finally, false positives were removed by using multi-channel histogram analysis. To evaluate the new method for the detection of exudates, we examined 158 fundus images, including 84 abnormal images with exudates and 74 normal images. The sensitivity and specificity for the detection of abnormal and normal cases were 88.45% and 95.5% respectively.
{"title":"Automatic detection of exudates in retinal images using histogram analysis","authors":"P. N. Sharath Kumar, R. R. Kumar, A. Sathar, V. Sahasranamam","doi":"10.1109/RAICS.2013.6745487","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745487","url":null,"abstract":"Diabetic Retinopathy (DR) is the major cause of blindness caused by the damage to the blood vessels in the retina from diabetes. It cannot be prevented but early detection through fundus imaging by an ophthalmologist can prevent further vision loss. Presence of microaneurysms, hemorrhages, cotton-wool spots and exudates are the symptoms of mild DR. Of these, the detection of exudates is one of the important factors in the early diagnosis of DR. Exudates are fatty deposits on the retina which appear as yellowish regions in fundus image. Fundus images show considerable variation in brightness which makes automatic detection of exudates difficult. In this study, we are proposing a new method for preprocessing and false positive elimination towards the reliable detection of exudates. The brightness of the fundus image was changed by the nonlinear curve with brightness values of the hue saturation value (HSV) space. To emphasize brighter yellow regions (exudates), gamma correction was performed on each red and green components of the image. Subsequently, the histograms of each red and green component were extended. After that, the exudates candidates were detected using histogram analysis. Finally, false positives were removed by using multi-channel histogram analysis. To evaluate the new method for the detection of exudates, we examined 158 fundus images, including 84 abnormal images with exudates and 74 normal images. The sensitivity and specificity for the detection of abnormal and normal cases were 88.45% and 95.5% respectively.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133007442","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745458
G. Karmakar, Ashutosh Kabra
Peak energy consumption has impact on upfront capital costs and hence on energy tariffs. Reducing the size of the peaks has been recognized as an important consideration in the design of efficient demand-response systems. A substantial fraction of the energy demand of buildings comes from air-conditioners, refrigerators and room-heaters. These thermostatically controlled electrical devices (TCED) maintain the temperature of the environment under its control within a desired comfort-band. Based on the insight gained by empirical observations, this paper presents a technique, which is energy-aware in scheduling TCEDs for maintaining comfort-band when peak power constraint limits the number of devices that can run at a time.
{"title":"Energy-aware thermal comfort-band maintenance scheduling under peak power constraint","authors":"G. Karmakar, Ashutosh Kabra","doi":"10.1109/RAICS.2013.6745458","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745458","url":null,"abstract":"Peak energy consumption has impact on upfront capital costs and hence on energy tariffs. Reducing the size of the peaks has been recognized as an important consideration in the design of efficient demand-response systems. A substantial fraction of the energy demand of buildings comes from air-conditioners, refrigerators and room-heaters. These thermostatically controlled electrical devices (TCED) maintain the temperature of the environment under its control within a desired comfort-band. Based on the insight gained by empirical observations, this paper presents a technique, which is energy-aware in scheduling TCEDs for maintaining comfort-band when peak power constraint limits the number of devices that can run at a time.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130589093","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 : 2013-12-01DOI: 10.1109/RAICS.2013.6745467
D. K. Rout, S. Puhan
In this paper the problem of video object detection under illumination variation is addressed. Many algorithms have been proposed to cope to this situation. But the major draw back in most of them is misclassified object and background area. Thereby object recognition and tracking process fails many a times due to failure of the detection algorithms. In our previous work we have proposed a supervised approach to increase the correct classification of the object and background regions. Although the results obtained were as per expectation but the model parameters estimation; such as the threshold selection process was manually done. In order to make it adaptive to the scene, we have proposed a classification algorithm which takes the histogram of correlation matrix into account and classify the object. The proposed algorithm computes the inter-plane correlation between three consecutive R, G and B planes by using a correlation function. The correlation matrix obtained is then used to construct a segmented image which gives a rough estimate of the object. The segmentation of the correlation plane is done by a threshold. This threshold selection is made adaptive to the video sequence considered. This segmented plane along with the moving edge image is then taken into consideration to improvise the correct classification of the moving object in the video. It is observed that the proposed algorithm yields quite manageable results in terms of correct classification.
{"title":"Video object detection using inter-frame correlation based background subtraction","authors":"D. K. Rout, S. Puhan","doi":"10.1109/RAICS.2013.6745467","DOIUrl":"https://doi.org/10.1109/RAICS.2013.6745467","url":null,"abstract":"In this paper the problem of video object detection under illumination variation is addressed. Many algorithms have been proposed to cope to this situation. But the major draw back in most of them is misclassified object and background area. Thereby object recognition and tracking process fails many a times due to failure of the detection algorithms. In our previous work we have proposed a supervised approach to increase the correct classification of the object and background regions. Although the results obtained were as per expectation but the model parameters estimation; such as the threshold selection process was manually done. In order to make it adaptive to the scene, we have proposed a classification algorithm which takes the histogram of correlation matrix into account and classify the object. The proposed algorithm computes the inter-plane correlation between three consecutive R, G and B planes by using a correlation function. The correlation matrix obtained is then used to construct a segmented image which gives a rough estimate of the object. The segmentation of the correlation plane is done by a threshold. This threshold selection is made adaptive to the video sequence considered. This segmented plane along with the moving edge image is then taken into consideration to improvise the correct classification of the moving object in the video. It is observed that the proposed algorithm yields quite manageable results in terms of correct classification.","PeriodicalId":184155,"journal":{"name":"2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129911727","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：