Improved Correspondence Point Search and Image Matching Accuracy for Disturbanced Images Using TD(0) Method
This paper presents a novel reinforcement learning approach to enhance image matching, whereby the corresponding point candidates are detected from the feature points extracted from each of the two images. In general, robust estimation methods such as random sample consensus (RANSAC) are used to sel...
Saved in:
| Published in | Journal of Advanced Simulation in Science and Engineering Vol. 12; no. 1; pp. 191 - 200 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Japan Society for Simulation Technology
2025
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2188-5303 2188-5303 |
| DOI | 10.15748/jasse.12.191 |
Cover
| Abstract | This paper presents a novel reinforcement learning approach to enhance image matching, whereby the corresponding point candidates are detected from the feature points extracted from each of the two images. In general, robust estimation methods such as random sample consensus (RANSAC) are used to select valid corresponding points from the candidates. Therefore, we addressed the limitations of RANSAC random selection in the image-matching process, evaluating various reinforcement learning strategies, including deterministic and probabilistic approaches, and different value update mechanisms. The findings indicated that a probabilistic approach with suitable value updates provides a more robust solution for space-based navigation systems. |
|---|---|
| AbstractList | This paper presents a novel reinforcement learning approach to enhance image matching, whereby the corresponding point candidates are detected from the feature points extracted from each of the two images. In general, robust estimation methods such as random sample consensus (RANSAC) are used to select valid corresponding points from the candidates. Therefore, we addressed the limitations of RANSAC random selection in the image-matching process, evaluating various reinforcement learning strategies, including deterministic and probabilistic approaches, and different value update mechanisms. The findings indicated that a probabilistic approach with suitable value updates provides a more robust solution for space-based navigation systems. |
| Author | Omori, Haruki Kamata, Hiroyuki Shimada, Mashiro |
| Author_xml | – sequence: 1 fullname: Kamata, Hiroyuki organization: School of Science and Technology, Meiji University – sequence: 1 fullname: Omori, Haruki organization: Graduate School of Science and Technology, Meiji University – sequence: 1 fullname: Shimada, Mashiro organization: Graduate School of Science and Technology, Meiji University |
| BookMark | eNqFkD1vwjAQhq2KSqWUsbvHdkhqx3GIpwpBP5BArVSYI2NfSGiwIztQ8e-bAkJsne6ke57T3XuLOsYaQOiekpDyQZw-raX3ENIopIJeoW5E0zTgjLDORX-D-t6vCSGMkSRivIu-J5va2R1oPLLOga-t0WAU4E9bmgZ_gXSqwNJoPNnIFeCZbFRRmhUeKrV1Uu1xbh0el77ZuqVsxRPo8cL_YfPxA3nEM2gKq-_QdS4rD_1T7aHF68t89B5MP94mo-E0UCymTSBiYMlSJJEQ0B7NtSQ81UKnOqFxwpY0zSknSjARK-AJ5TqSCY9TUAMQmgProfC4d2tquf-RVZXVrtxIt88oyQ5pZYe0MhplbVqtEBwF5az3DvJ_-ecjv_ZN--uZlq4pVQUX8Mk4T1QhXQaG_QI4OoXo |
| Cites_doi | 10.1006/cviu.1999.0832 10.1007/s12524-020-01163-y 10.1299/jsmesec.2009.18.59 10.1109/ICMLA.2015.59 10.1109/ICCV.2019.00442 10.1007/978-981-97-7225-4_16 10.1109/TPAMI.2012.257 10.1023/B:VISI.0000029664.99615.94 10.1109/CVPR.2005.221 |
| ContentType | Journal Article |
| Copyright | 2025 Japan Society for Simulation Technology |
| Copyright_xml | – notice: 2025 Japan Society for Simulation Technology |
| DBID | AAYXX CITATION ADTOC UNPAY |
| DOI | 10.15748/jasse.12.191 |
| DatabaseName | CrossRef Unpaywall for CDI: Periodical Content Unpaywall |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: UNPAY name: Unpaywall url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/ sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2188-5303 |
| EndPage | 200 |
| ExternalDocumentID | 10.15748/jasse.12.191 10_15748_jasse_12_191 article_jasse_12_1_12_191_article_char_en |
| GroupedDBID | ALMA_UNASSIGNED_HOLDINGS JSF KQ8 RJT AAYXX CITATION ADTOC UNPAY |
| ID | FETCH-LOGICAL-c341t-94e36b96299e5305da058d9d8d61463b18f150c9394ce5615d2a6548ec7e9d5e3 |
| IEDL.DBID | UNPAY |
| ISSN | 2188-5303 |
| IngestDate | Tue Aug 19 23:28:41 EDT 2025 Tue Jul 01 04:59:49 EDT 2025 Wed Sep 03 06:30:37 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c341t-94e36b96299e5305da058d9d8d61463b18f150c9394ce5615d2a6548ec7e9d5e3 |
| OpenAccessLink | https://proxy.k.utb.cz/login?url=https://www.jstage.jst.go.jp/article/jasse/12/1/12_191/_pdf |
| PageCount | 10 |
| ParticipantIDs | unpaywall_primary_10_15748_jasse_12_191 crossref_primary_10_15748_jasse_12_191 jstage_primary_article_jasse_12_1_12_191_article_char_en |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2025 2025-00-00 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of Advanced Simulation in Science and Engineering |
| PublicationTitleAlternate | JASSE |
| PublicationYear | 2025 |
| Publisher | Japan Society for Simulation Technology |
| Publisher_xml | – name: Japan Society for Simulation Technology |
| References | [4] O. Chum, J. Matas: Matching with PROSAC—Progressive Sample Consensus, in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, California 2005, 220-226. [5] P. Torr, A. Zisserman: MLESAC: A new robust estimator with application to estimating image geometry, Comput. Vis. Image Understand., 78:1 (2000), 138–156. [6] E. Brachmann, C. Rother: Neural-guided RANSAC: Learning where to sample model hypotheses, in IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 2019, 4322-4331. [2] S. Sharma, K. Jain: Image Stitching using AKAZE Features. Journal of the Indian Society of Remote Sensing, 48 (2020), 1389-1401. [10] H. Miura, H. Kamata: "Autonomous Navigation with Feature Points Map for Self-position Estimation for High-Accuracy Landing on Unknown Celestial Bodies” in Methods and Applications for Modeling and Simulation of Complex Systems, Springer Nature Singapore, Singapore, 2024, 202-216. [3] R. Raguram, O. Chum, M. Pollefeys, J. Matas: USAC: A Universal Framework for Random Sample Consensus, IEEE Transactions on Software Engineering, 35:8 (2013), 2022-2038. [7] D. Lowe: Distinctive image features from scale invariant keypoints, International Journal of Computer Vision, 60 (2004), 91–110. [1] S. Yoshikawa, M. Kunugi, R. Yasumitsu, S. Sawai, S. Fukuda, T. Mizuno, K. Nakaya, Y. Fujii, N. Takatsuka: Conceptual study on the guidance, navigation and control system of the smart landing for investigating moon (SLIM), in Proceedings of Global Lunar Conference, Beijing, 2010, 59–62. [8] T. Watanabe, Y. Saito: A Fuzzy RANSAC Algorithm Based on Reinforcement Learning, in 28th Fuzzy System Symposium, Nagoya, 2012, 991-993. (in Japanese) [9] K. Saito, A. Notsu, S. Ubukata, K. Honda: Performance Investigation of UCB Policy in Q-learning, in IEEE 14th International Conference on Machine Learning and Applications, Florida, 2015, 777-780. 1 2 3 4 5 6 7 8 9 10 |
| References_xml | – reference: [10] H. Miura, H. Kamata: "Autonomous Navigation with Feature Points Map for Self-position Estimation for High-Accuracy Landing on Unknown Celestial Bodies” in Methods and Applications for Modeling and Simulation of Complex Systems, Springer Nature Singapore, Singapore, 2024, 202-216. – reference: [7] D. Lowe: Distinctive image features from scale invariant keypoints, International Journal of Computer Vision, 60 (2004), 91–110. – reference: [1] S. Yoshikawa, M. Kunugi, R. Yasumitsu, S. Sawai, S. Fukuda, T. Mizuno, K. Nakaya, Y. Fujii, N. Takatsuka: Conceptual study on the guidance, navigation and control system of the smart landing for investigating moon (SLIM), in Proceedings of Global Lunar Conference, Beijing, 2010, 59–62. – reference: [8] T. Watanabe, Y. Saito: A Fuzzy RANSAC Algorithm Based on Reinforcement Learning, in 28th Fuzzy System Symposium, Nagoya, 2012, 991-993. (in Japanese) – reference: [4] O. Chum, J. Matas: Matching with PROSAC—Progressive Sample Consensus, in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, California 2005, 220-226. – reference: [2] S. Sharma, K. Jain: Image Stitching using AKAZE Features. Journal of the Indian Society of Remote Sensing, 48 (2020), 1389-1401. – reference: [6] E. Brachmann, C. Rother: Neural-guided RANSAC: Learning where to sample model hypotheses, in IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 2019, 4322-4331. – reference: [3] R. Raguram, O. Chum, M. Pollefeys, J. Matas: USAC: A Universal Framework for Random Sample Consensus, IEEE Transactions on Software Engineering, 35:8 (2013), 2022-2038. – reference: [9] K. Saito, A. Notsu, S. Ubukata, K. Honda: Performance Investigation of UCB Policy in Q-learning, in IEEE 14th International Conference on Machine Learning and Applications, Florida, 2015, 777-780. – reference: [5] P. Torr, A. Zisserman: MLESAC: A new robust estimator with application to estimating image geometry, Comput. Vis. Image Understand., 78:1 (2000), 138–156. – ident: 5 doi: 10.1006/cviu.1999.0832 – ident: 2 doi: 10.1007/s12524-020-01163-y – ident: 1 doi: 10.1299/jsmesec.2009.18.59 – ident: 9 doi: 10.1109/ICMLA.2015.59 – ident: 6 doi: 10.1109/ICCV.2019.00442 – ident: 8 – ident: 10 doi: 10.1007/978-981-97-7225-4_16 – ident: 3 doi: 10.1109/TPAMI.2012.257 – ident: 7 doi: 10.1023/B:VISI.0000029664.99615.94 – ident: 4 doi: 10.1109/CVPR.2005.221 |
| SSID | ssj0003306235 |
| Score | 2.2820773 |
| Snippet | This paper presents a novel reinforcement learning approach to enhance image matching, whereby the corresponding point candidates are detected from the feature... |
| SourceID | unpaywall crossref jstage |
| SourceType | Open Access Repository Index Database Publisher |
| StartPage | 191 |
| SubjectTerms | Disturbanced images Image matching RANSAC Reinforcement learning |
| Title | Improved Correspondence Point Search and Image Matching Accuracy for Disturbanced Images Using TD(0) Method |
| URI | https://www.jstage.jst.go.jp/article/jasse/12/1/12_191/_article/-char/en https://www.jstage.jst.go.jp/article/jasse/12/1/12_191/_pdf |
| UnpaywallVersion | publishedVersion |
| Volume | 12 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | Journal of Advanced Simulation in Science and Engineering, 2025, Vol.12(1), pp.191-200 |
| journalDatabaseRights | – providerCode: PRVAFT databaseName: Open Access Digital Library customDbUrl: eissn: 2188-5303 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0003306235 issn: 2188-5303 databaseCode: KQ8 dateStart: 20140101 isFulltext: true titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html providerName: Colorado Alliance of Research Libraries |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB60CuLBBypWVPYgPg5pmiabZPFUfOADRcGCghD2VbHWNNQEqb_e2Wxa1IOIlwSSWXaZWWa-mZ2dAdjpdplSnEZOFArloPaLHBG1uEO1jJrcC4TkZbbFdXjWCS7u6f0UHI7vwpi0yh7ioidtXo2nQaOXuRUT3R7iSe16LdfDR4KehptkqjsNM6E5XarBTOf6pv1g2sl5KH-K2rmqqkmjILajTezPY943KzRrJ5yHuSLN-Oid9_tfbMzpIjyOV2dTS14aRS4a8uNH4cZ_Ln8JFirsSdqWcBmmdLoCLzasoBU5Kht1ZIO0bDNKbgbPaU5sOjLhqSLnrzghuULdbaJWpC1lMeRyRBD2kmPcLcVQlOkElvCNlNkI5O54v3lArspG1avQOT25Ozpzqg4MjkTrljss0H4oWIg2SyM7qeJNGiumYoVWPfSFF3cRUErms0BqRGJUtbhpRI-C1kxR7a9BLR2keh2IzzhF16QZBwz1BNci0rqFYzR-9QOm6rA7lkiS2UIbiXFQjOiSknOJZVodYsvhCVnF3y9UFenkj7nBhmqgDnsTCf8-ycafKTehlg8LvYXQJBfbMH15G29XG_ETvzXpyg |
| linkProvider | Unpaywall |
| linkToUnpaywall | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB5qFcSDD1SsqOxBfBzSNE02yeKp-EAFpYcWKghhXxWrpqEmiP56Z7NpUQ8iXhJIZtllZpn5ZnZ2BmB_OGRKcRo5USiUg9ovckTU5g7VMmpxLxCSl9kWt-FlP7ge0EENTqZ3YUxa5Qhx0YM2r-bDuDnK3IqJ7gjxpHa9tuvhI0FPw00yNZyD-dCcLtVhvn_b7dyZdnIeyp-idq6qatIoiO1oE_vzmPfNCi3YCZdgsUgz_v7Gn5-_2JiLFbifrs6mljw1i1w05cePwo3_XP4qLFfYk3Qs4RrUdLoOTzasoBU5LRt1ZOO0bDNKuuPHNCc2HZnwVJGrF5yQ3KDuNlEr0pGymHD5ThD2kjPcLcVElOkElvCVlNkIpHd21DomN2Wj6g3oX5z3Ti-dqgODI9G65Q4LtB8KFqLN0shOqniLxoqpWKFVD33hxUMElJL5LJAakRhVbW4a0aOgNVNU-5tQT8ep3gLiM07RNWnFAUM9wbWItG7jGI1f_YCpBhxMJZJkttBGYhwUI7qk5FximdaA2HJ4Rlbx9wtVRTr7Y26woRpowOFMwr9Psv1nyh2o55NC7yI0ycVetQU_AUnp6NU |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Improved+Correspondence+Point+Search+and+Image+Matching+Accuracy+for+Disturbanced+Images+Using+TD%280%29+Method&rft.jtitle=Journal+of+Advanced+Simulation+in+Science+and+Engineering&rft.au=Kamata%2C+Hiroyuki&rft.au=Omori%2C+Haruki&rft.au=Shimada%2C+Mashiro&rft.date=2025&rft.pub=Japan+Society+for+Simulation+Technology&rft.eissn=2188-5303&rft.volume=12&rft.issue=1&rft.spage=191&rft.epage=200&rft_id=info:doi/10.15748%2Fjasse.12.191&rft.externalDocID=article_jasse_12_1_12_191_article_char_en |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2188-5303&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2188-5303&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2188-5303&client=summon |