Pub Date : 2014-12-01DOI: 10.1109/ICCWAMTIP.2014.7073402
Qing Li, Fan Wang, Xiaopeng Hu
Vision-based lane detection is a critical issue in the field of intelligent transportation and safety driving, and is useful to predict the position of the car on the road. By analyzing many images in database and experimental results, we find that brightness difference between lane marking and road is the stable feature in various challenging scenarios. So in this paper, we propose a new, fast and effective lane detection approach based on the brightness difference. We apply the brightness difference feature in “Verify” phase in order to reduce computation and filter the wrong lines. Experimental results show that the proposed method could perform well in real-time application, and it is robust against cracks on the roads, the curved lanes.
{"title":"A fast lane detection algorithm based on brightness difference","authors":"Qing Li, Fan Wang, Xiaopeng Hu","doi":"10.1109/ICCWAMTIP.2014.7073402","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073402","url":null,"abstract":"Vision-based lane detection is a critical issue in the field of intelligent transportation and safety driving, and is useful to predict the position of the car on the road. By analyzing many images in database and experimental results, we find that brightness difference between lane marking and road is the stable feature in various challenging scenarios. So in this paper, we propose a new, fast and effective lane detection approach based on the brightness difference. We apply the brightness difference feature in “Verify” phase in order to reduce computation and filter the wrong lines. Experimental results show that the proposed method could perform well in real-time application, and it is robust against cracks on the roads, the curved lanes.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126169527","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/ICCWAMTIP.2014.7073447
R. Wu, Lutao Wang
Traditional adaptive beamformers have robustness just for specific error condition. They suffer performance degradation in the presence of multiple errors such as sample covariance matrix estimation error and steering vector mismatch. In this article, a new robust adaptive beamforming algorithm based on jointly estimating the covariance matrix and steering vector mismatch is proposed to overcome both the problems of sample covariance errors and steering vector mismatch. The theoretical covariance matrix is estimated based on the shrinkage method. Subsequently, the difference between the actual and presumed steering vectors is estimated in the sense of that the output signal-to noise plus interference ratio (SINR) is maximized and then is used to obtain the actual steering vectors. The proposed algorithm is preferable to traditional ones in the condition of multiple errors. Both simulation results and performance analysis are presented that illustrated the effectiveness and superiority of the proposed method.
{"title":"Robust adaptive beamforming based on jointly estimating","authors":"R. Wu, Lutao Wang","doi":"10.1109/ICCWAMTIP.2014.7073447","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073447","url":null,"abstract":"Traditional adaptive beamformers have robustness just for specific error condition. They suffer performance degradation in the presence of multiple errors such as sample covariance matrix estimation error and steering vector mismatch. In this article, a new robust adaptive beamforming algorithm based on jointly estimating the covariance matrix and steering vector mismatch is proposed to overcome both the problems of sample covariance errors and steering vector mismatch. The theoretical covariance matrix is estimated based on the shrinkage method. Subsequently, the difference between the actual and presumed steering vectors is estimated in the sense of that the output signal-to noise plus interference ratio (SINR) is maximized and then is used to obtain the actual steering vectors. The proposed algorithm is preferable to traditional ones in the condition of multiple errors. Both simulation results and performance analysis are presented that illustrated the effectiveness and superiority of the proposed method.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128751127","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/ICCWAMTIP.2014.7073378
Xiaoya Zhang, Hongxia Wang, Hui Zhang
Linearized Bregman algorithm is effective on solving l1-minimization problem, but its parameter's selection must rely on prior information. In order to ameliorate this weakness, we proposed a new algorithm in this paper, which combines the proximal point algorithm and the linearized Bregman iterative method. In the second part of the paper, the proposed algorithm is further accelerated through Nestrove's accelerated scheme and parameters' reset skills. Compared with the original linearized Bregman algorithm, the accelerated algorithms have better convergent speed while avoiding selecting model parameter. Simulations on sparse recovery problems show the new algorithms really have robust parameter's selections, and improve the convergent precision at the same time.
{"title":"Accelerated proximal algorithms for L1-minimization problem","authors":"Xiaoya Zhang, Hongxia Wang, Hui Zhang","doi":"10.1109/ICCWAMTIP.2014.7073378","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073378","url":null,"abstract":"Linearized Bregman algorithm is effective on solving l1-minimization problem, but its parameter's selection must rely on prior information. In order to ameliorate this weakness, we proposed a new algorithm in this paper, which combines the proximal point algorithm and the linearized Bregman iterative method. In the second part of the paper, the proposed algorithm is further accelerated through Nestrove's accelerated scheme and parameters' reset skills. Compared with the original linearized Bregman algorithm, the accelerated algorithms have better convergent speed while avoiding selecting model parameter. Simulations on sparse recovery problems show the new algorithms really have robust parameter's selections, and improve the convergent precision at the same time.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129926485","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/ICCWAMTIP.2014.7073449
Zhaoxia Wei, Chunjie Wang
The technology of fingertip tracking is widely used in robot control field, the fingertip of robot can be accurately controlled. But the fingertip tracking is very complicated, there is much uncertainty for the speed and direction during the movement of fingertip, so the fingertip tracking technology becomes one key point in the robot control field. In the early, the feedback tracking algorithm was widely used, but there is big deviation between the tracking result and the actual movement process. With the development of visual image processing, using the image processing method to do the fingertip tracking becomes popular. To avoid the low accuracy defect that comes from the traditional algorithm doesn't consider the light intensity during the fingertip tracking process, this article provides one new fingertip tracking algorithm based on image processing. For the collected image of robot fingertip tracking, first perform the initialization to get vector of the high frequency vector and low frequency vector, then perform the wavelet processing for the collected vector to improve the image quality. Then normalize the pixels of fingertip tracking image to provide accurate data for the finger tracking. At last, use linear analysis method to process the data from normalized data. The experiment result shows that the tracking accuracy can be effectively improved by using the improved algorithm on fingertip tracking.
{"title":"Robot fingertip tracking process analysis and simulation","authors":"Zhaoxia Wei, Chunjie Wang","doi":"10.1109/ICCWAMTIP.2014.7073449","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073449","url":null,"abstract":"The technology of fingertip tracking is widely used in robot control field, the fingertip of robot can be accurately controlled. But the fingertip tracking is very complicated, there is much uncertainty for the speed and direction during the movement of fingertip, so the fingertip tracking technology becomes one key point in the robot control field. In the early, the feedback tracking algorithm was widely used, but there is big deviation between the tracking result and the actual movement process. With the development of visual image processing, using the image processing method to do the fingertip tracking becomes popular. To avoid the low accuracy defect that comes from the traditional algorithm doesn't consider the light intensity during the fingertip tracking process, this article provides one new fingertip tracking algorithm based on image processing. For the collected image of robot fingertip tracking, first perform the initialization to get vector of the high frequency vector and low frequency vector, then perform the wavelet processing for the collected vector to improve the image quality. Then normalize the pixels of fingertip tracking image to provide accurate data for the finger tracking. At last, use linear analysis method to process the data from normalized data. The experiment result shows that the tracking accuracy can be effectively improved by using the improved algorithm on fingertip tracking.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126797394","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/ICCWAMTIP.2014.7073371
Bo Fu, Y. Jin, Fan Wang, Xiaopeng Hu
Object level saliency detection is useful for many content-based computer vision tasks. In this letter, we present a novel bottom-up salient object detection approach by exploiting contrast, and center priors. In the past, the algorithms of saliency detection are generally based on the contrast of the priors, but only using a prior that there are still many problems, if not uniformly outstanding goals. Currently, a lot of work introduce center prior to significant target detection. However, the center prior is very sensitive to the position of the target that once deviation from the center, the center prior will no longer be established. In this paper, we explore the surroundedness cue for saliency detection. The essence of surroundedness is the enclosure topological relationship between the figure and the ground, which is achieved by random threshold color channel of the image. in order to enhance robustness and effectiveness of the center prior. Then fusion contrast prior and new center prior to generate a new saliency map.
{"title":"Prior fusion based salient object detection","authors":"Bo Fu, Y. Jin, Fan Wang, Xiaopeng Hu","doi":"10.1109/ICCWAMTIP.2014.7073371","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073371","url":null,"abstract":"Object level saliency detection is useful for many content-based computer vision tasks. In this letter, we present a novel bottom-up salient object detection approach by exploiting contrast, and center priors. In the past, the algorithms of saliency detection are generally based on the contrast of the priors, but only using a prior that there are still many problems, if not uniformly outstanding goals. Currently, a lot of work introduce center prior to significant target detection. However, the center prior is very sensitive to the position of the target that once deviation from the center, the center prior will no longer be established. In this paper, we explore the surroundedness cue for saliency detection. The essence of surroundedness is the enclosure topological relationship between the figure and the ground, which is achieved by random threshold color channel of the image. in order to enhance robustness and effectiveness of the center prior. Then fusion contrast prior and new center prior to generate a new saliency map.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123325208","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/ICCWAMTIP.2014.7073444
Xin-Ying Chen, Guan-yu Li, Jiahong Yan
As the basis of attribute reduction, core computation is one of the key issues in rough set theory. Actually, decision system is continuously changing, which leads to the inconsistent system. To deal with the problem before core computation, based on bucket sort and equivalence class partition, a new algorithm with time complexity of O(|P||U|) is proposed. After that, an effective approach is proposed to make universe consistent and smaller. According to involved theorems and equivalent propositions, an algorithm for core on the discordant index is proposed also and its time performance is O(|C|2|U/C|). The theoretical analysis and experiment show that the ways proposed here not only can simplify the relevant operations but also can give accurate core results.
{"title":"The practical algorithm for core in decision system","authors":"Xin-Ying Chen, Guan-yu Li, Jiahong Yan","doi":"10.1109/ICCWAMTIP.2014.7073444","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073444","url":null,"abstract":"As the basis of attribute reduction, core computation is one of the key issues in rough set theory. Actually, decision system is continuously changing, which leads to the inconsistent system. To deal with the problem before core computation, based on bucket sort and equivalence class partition, a new algorithm with time complexity of O(|P||U|) is proposed. After that, an effective approach is proposed to make universe consistent and smaller. According to involved theorems and equivalent propositions, an algorithm for core on the discordant index is proposed also and its time performance is O(|C|2|U/C|). The theoretical analysis and experiment show that the ways proposed here not only can simplify the relevant operations but also can give accurate core results.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125226948","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/ICCWAMTIP.2014.7073397
Zhongyu Tao, Xiaolong Tang, Binyu Zhang, Panshi Tang, Yu Tan
Image segmentation is very important in image processing which can segment the images into the different parts, thus, we can focus on the parts in which we are interested. Recent years, there are many models using for the image segmentation, Pulse Coupled Neural Networks model is very popular model which is widely used among many models. Although, PCNN models needs trivial adaptive parameters and network iterations to set, but it has the advantages, such as rotation invariance, intensity invariance, scale invariance, etc. Above advantages make PCNN is very suitable for image segmentation.
{"title":"Image segmentation based on PCNN model","authors":"Zhongyu Tao, Xiaolong Tang, Binyu Zhang, Panshi Tang, Yu Tan","doi":"10.1109/ICCWAMTIP.2014.7073397","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073397","url":null,"abstract":"Image segmentation is very important in image processing which can segment the images into the different parts, thus, we can focus on the parts in which we are interested. Recent years, there are many models using for the image segmentation, Pulse Coupled Neural Networks model is very popular model which is widely used among many models. Although, PCNN models needs trivial adaptive parameters and network iterations to set, but it has the advantages, such as rotation invariance, intensity invariance, scale invariance, etc. Above advantages make PCNN is very suitable for image segmentation.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115148755","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/ICCWAMTIP.2014.7073393
Ping Zhang, Chun Fei
In multi-focus image fusion, the focus regions of different source images are fused into an all-focus image. The focus measure based on sharpness information is very important. In this paper, both global and local phase coherence of source images are used to effectively measure the image sharpness. Then a novel image fusion algorithm is proposed, which combines new sharpness measure and structural similarity characteristics of source images. Experimental results demonstrate that the proposed algorithm has good subjective and objective evaluations compared with other conventional algorithms based on sharpness measure.
{"title":"Multi-focus image fusion based on efficient sharpness measure with global and local phase coherence","authors":"Ping Zhang, Chun Fei","doi":"10.1109/ICCWAMTIP.2014.7073393","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073393","url":null,"abstract":"In multi-focus image fusion, the focus regions of different source images are fused into an all-focus image. The focus measure based on sharpness information is very important. In this paper, both global and local phase coherence of source images are used to effectively measure the image sharpness. Then a novel image fusion algorithm is proposed, which combines new sharpness measure and structural similarity characteristics of source images. Experimental results demonstrate that the proposed algorithm has good subjective and objective evaluations compared with other conventional algorithms based on sharpness measure.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134239266","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/ICCWAMTIP.2014.7073376
Huang Fuyuan
To overcome the curse of dimensionality, Arough fuzzy neural networks (RFNN) model was proposed in this paper, which combined the rough set theory (RST) and fuzzy neural networks (FNN). First, the models' input indices (such as financial ratios, qualitative variables et.al.) were reduced with no information loss through rough set approach. And then data based on the reduced indices was employed to develop fuzzy rules and train the fuzzy neural networks (FNN). The new model, which has advantages of both rough set approach and fuzzy neural networks, can not only avoid curse of dimensionality but also prevent “BlackBox” syndrome. The simulation result indicates that the predictive accuracy of the model is much higher. Furthermore, it has characteristics of simple structure, fast convergence speed, and stronger generalization ability etc.
{"title":"A rough fuzzy neural networks model with application to financial risk early-warning","authors":"Huang Fuyuan","doi":"10.1109/ICCWAMTIP.2014.7073376","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073376","url":null,"abstract":"To overcome the curse of dimensionality, Arough fuzzy neural networks (RFNN) model was proposed in this paper, which combined the rough set theory (RST) and fuzzy neural networks (FNN). First, the models' input indices (such as financial ratios, qualitative variables et.al.) were reduced with no information loss through rough set approach. And then data based on the reduced indices was employed to develop fuzzy rules and train the fuzzy neural networks (FNN). The new model, which has advantages of both rough set approach and fuzzy neural networks, can not only avoid curse of dimensionality but also prevent “BlackBox” syndrome. The simulation result indicates that the predictive accuracy of the model is much higher. Furthermore, it has characteristics of simple structure, fast convergence speed, and stronger generalization ability etc.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134378002","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/ICCWAMTIP.2014.7073391
Senhua Wang, Zhang Li, Xiangzhong Li, Yong-Qing Yang
Image super-resolution reconstruction was an important task in the field of image enhancement and image restoration. In this paper, a new super-resolution reconstruction method which based on wavelet analysis and sub-pixel interpolation was proposed by using wavelet edge detection and polynomial subdivision location. The simulation results showed that the boundary of reconstructed high-resolution image is clear and natural, and the subjective judgment and objective evaluation is better than traditional reconstruction algorithm. The algorithm in this paper achieves good effects and reaches good feasibility and validity.
{"title":"A new method of super-resolution reconstruction based on wavelet and subpixel interpolation","authors":"Senhua Wang, Zhang Li, Xiangzhong Li, Yong-Qing Yang","doi":"10.1109/ICCWAMTIP.2014.7073391","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP.2014.7073391","url":null,"abstract":"Image super-resolution reconstruction was an important task in the field of image enhancement and image restoration. In this paper, a new super-resolution reconstruction method which based on wavelet analysis and sub-pixel interpolation was proposed by using wavelet edge detection and polynomial subdivision location. The simulation results showed that the boundary of reconstructed high-resolution image is clear and natural, and the subjective judgment and objective evaluation is better than traditional reconstruction algorithm. The algorithm in this paper achieves good effects and reaches good feasibility and validity.","PeriodicalId":211273,"journal":{"name":"2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134513282","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：