图像运动估计的平均场理论

1993 IEEE International Conference on Acoustics, Speech, and Signal Processing Pub Date : 1993-04-27 DOI:10.1109/ICASSP.1993.319781

J. Zhang, J. Hanauer

{"title":"图像运动估计的平均场理论","authors":"J. Zhang, J. Hanauer","doi":"10.1109/ICASSP.1993.319781","DOIUrl":null,"url":null,"abstract":"It is shown how the MFT (mean field theory) can be applied to MRF (Markov random field) model-based motion estimation. Specifically, the motion is characterized by a coupled MRF including a displacement field (motion continuity), a line field (motion discontinuity), and a segmentation field (identifying uncovered areas). These fields are estimated by using the MFT. The efficacy of this approach is demonstrated on synthetic and real-world images.<<ETX>>","PeriodicalId":428449,"journal":{"name":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","volume":"342 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1993-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"17","resultStr":"{\"title\":\"The mean field theory for image motion estimation\",\"authors\":\"J. Zhang, J. Hanauer\",\"doi\":\"10.1109/ICASSP.1993.319781\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"It is shown how the MFT (mean field theory) can be applied to MRF (Markov random field) model-based motion estimation. Specifically, the motion is characterized by a coupled MRF including a displacement field (motion continuity), a line field (motion discontinuity), and a segmentation field (identifying uncovered areas). These fields are estimated by using the MFT. The efficacy of this approach is demonstrated on synthetic and real-world images.<<ETX>>\",\"PeriodicalId\":428449,\"journal\":{\"name\":\"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"volume\":\"342 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1993-04-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"17\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASSP.1993.319781\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"1993 IEEE International Conference on Acoustics, Speech, and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.1993.319781","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 17

摘要

展示了如何将MFT(平均场理论)应用于基于马尔可夫随机场模型的运动估计。具体来说，运动的特征是一个耦合的磁流变场，包括位移场(运动连续性)、线场(运动不连续)和分割场(识别未覆盖区域)。这些字段通过使用MFT来估计。这种方法的有效性在合成图像和真实世界的图像上得到了证明。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The mean field theory for image motion estimation

It is shown how the MFT (mean field theory) can be applied to MRF (Markov random field) model-based motion estimation. Specifically, the motion is characterized by a coupled MRF including a displacement field (motion continuity), a line field (motion discontinuity), and a segmentation field (identifying uncovered areas). These fields are estimated by using the MFT. The efficacy of this approach is demonstrated on synthetic and real-world images.<>

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

1993 IEEE International Conference on Acoustics, Speech, and Signal Processing

自引率

0.00%

发文量