{"type":"ScholarlyArticle","title":"Nonrigid Points Alignment with Soft-weighted Selection","authors":[{"name":"Xuelong Li","slug":"xuelong-li","given":"Xuelong","family":"Li","affiliation":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL) , Northwestern Polytechnical University , Xian 710072 , Shaanxi , P. R. China"},{"name":"Jian Yang","slug":"jian-yang","given":"Jian","family":"Yang","affiliation":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL) , Northwestern Polytechnical University , Xian 710072 , Shaanxi , P. R. China"},{"name":"Qi Wang","slug":"qi-wang","given":"Qi","family":"Wang","affiliation":"School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL) , Northwestern Polytechnical University , Xian 710072 , Shaanxi , P. R. China; Unmanned System Research Institute (USRI) , Northwestern Polytechnical University , Xian 710072 , Shaanxi , P. R. China"}],"abstract":"Point set registration (PSR) is a crucial problem in computer vision and pattern recognition. Existing PSR methods cannot align point sets robustly due to degradations, such as deformation, noise, occlusion, outlier, and multi-view changes. In this paper, we present a self-selected regularized Gaussian fields criterion for nonrigid point matching. Unlike most existing methods, we formulate the registration problem as a sparse approximation task with low rank constraint in reproducing kernel Hilbert space (RKHS). A self-selected mechanism is used to dynamically assign real-valued label for each point in an accuracy-aware weighting manner, which makes the model focus more on the reliable points in position. Based on the label, an equivalent matching number optimization is embedded into the non-rigid criterion to enhance the reliability of the approximation. Experimental results show that the proposed method can achieve a better result in both registration accuracy and correct matches compared to state-of-the-art approaches.","doi":"10.24963/ijcai.2018/111","url":"https://ijcai.org/proceedings/2018/111","pdf":"https://ijcai.org/proceedings/2018/0111.pdf","markdown":"https://ijcai.org/proceedings/2018/111.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/111","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":111,"pages":{"first":800,"last":806},"keywords":["Computer Vision: Computer Vision","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Computer Vision: 2D and 3D Computer Vision"],"videos":[],"references":[{"position":1,"raw":"[Bai et al., 2018] Lifei Bai, Xianqiang Yang, and Huijun Gao. Nonrigid point set registration by preserving lo- cal connectivity. IEEE transactions on cybernetics, 48(3):826-835, 2018.","title":"Nonrigid point set registration by preserving local connectivity","authors":"Bai","year":"2018","venue":"IEEE transactions on cybernetics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chou and Wang, 2015] Chih Chung Chou and Chieh-Chih Wang. 2-point ransac for scene image matching under large viewpoint changes. In Robotics and Automation (ICRA), 2015 IEEE International Conference on, pages 3646-3651. IEEE, 2015.","title":"2-point ransac for scene image matching under large viewpoint changes","authors":"Wang ; ] Chou, Chung Chih, Chieh-Chih Chou, Wang","year":"2015","venue":"Robotics and Automation (ICRA), 2015 IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Hong and Kim, 2016] Seonghun Hong and Jinwhan Kim. Efficient visual slam using selective image registration for autonomous inspection of underwater structures. In Au- tonomous Underwater Vehicles (AUV), 2016 IEEE/OES, pages 189-194. IEEE, 2016.","title":"Efficient visual slam using selective image registration for autonomous inspection of underwater structures","authors":"Kim ; Hong, Seonghun Hong, Jinwhan Kim","year":"2016","venue":"Autonomous Underwater Vehicles (AUV)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Jian and Vemuri, 2011] Bing Jian and Baba C Vemuri. Ro- bust point set registration using gaussian mixture models. IEEE Transactions on Pattern Analysis and Machine In- telligence, 33(8):1633-1645, 2011.","title":"Robust point set registration using gaussian mixture models","authors":"Jian, Vemuri, Bing Jian, C Baba, Vemuri","year":"2011","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jiang et al., 2014] Lu Jiang, Deyu Meng, Teruko Mitamura, and Alexander G Hauptmann. Easy samples first: Self- paced reranking for zero-example multimedia search. In Proceedings of the 22nd ACM international conference on Multimedia, pages 547-556. ACM, 2014.","title":"Easy samples first: Selfpaced reranking for zero-example multimedia search","authors":"Lu Jiang, Deyu Meng, Teruko Mitamura, Alexander G Hauptmann","year":"2014","venue":"Proceedings of the 22nd ACM international conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Kahaki et al., 2016] Seyed Mousavi Kahaki, Md Jan Nordin, Amir H Ashtari, and Sophia J Zahra. Deforma- tion invariant image matching based on dissimilarity of spatial features. Neurocomputing, 175:1009-1018, 2016.","title":"Deformation invariant image matching based on dissimilarity of spatial features","authors":"Seyed Mousavi Kahaki, Jan Md, Nordin, Sophia J Amir H Ashtari, Zahra","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Litman et al., 2015] Roee Litman, Simon Korman, Alexan- der Bronstein, and Shai Avidan. Inverting ransac: Global model detection via inlier rate estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5243-5251, 2015.","title":"Inverting ransac: Global model detection via inlier rate estimation","authors":"Roee Litman, Simon Korman, Alexander Bronstein, Shai Avidan","year":"2015","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lowe, 2004] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91-110, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"David G Lowe","year":"2004","venue":"International journal of computer vision","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ma et al., 2015a] Jiayi Ma, Yong Ma, Ji Zhao, and Jinwen Tian. Image feature matching via progressive vector field consensus. IEEE Signal Processing Letters, 22(6):767- 771, 2015.","title":"Image feature matching via progressive vector field consensus","authors":"Ma","year":"2015","venue":"IEEE Signal Processing Letters","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ma et al., 2015b] Jiayi Ma, Weichao Qiu, Ji Zhao, Yong Ma, Alan L Yuille, and Zhuowen Tu. Robust l2e esti- mation of transformation for non-rigid registration. IEEE Trans. Signal Processing, 63(5):1115-1129, 2015.","title":"Robust l2e estimation of transformation for non-rigid registration","authors":"Ma","year":"2015","venue":"IEEE Trans. Signal Processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ma et al., 2015c] Jiayi Ma, Ji Zhao, Yong Ma, and Jinwen Tian. Non-rigid visible and infrared face registration via regularized gaussian fields criterion. Pattern Recognition, 48(3):772-784, 2015.","title":"Non-rigid visible and infrared face registration via regularized gaussian fields criterion","authors":"Ma","year":"2015","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ma et al., 2016] Jiayi Ma, Ji Zhao, and Alan L Yuille. Non- rigid point set registration by preserving global and lo- cal structures. IEEE Transactions on Image Processing, 25(1):53-64, 2016.","title":"Nonrigid point set registration by preserving global and local structures","authors":"Jiayi Ma, Ji Zhao, Alan L Yuille","year":"2016","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Myronenko and Song, 2010] Andriy Myronenko and Xubo Song. Point set registration: Coherent point drift. IEEE transactions on pattern analysis and machine intelligence, 32(12):2262-2275, 2010.","title":"Point set registration: Coherent point drift","authors":"Andriy Myronenko, Xubo Song","year":"2010","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pinheiro et al., 2017] Miguel Amável Pinheiro, Jan Kybic, and Pascal Fua. Geometric graph matching using monte carlo tree search. IEEE transactions on pattern analysis and machine intelligence, 39(11):2171-2185, 2017.","title":"Miguel Amável Pinheiro, Jan Kybic, and Pascal Fua. Geometric graph matching using monte carlo tree search","authors":"Pinheiro","year":"2017","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Qu et al., 2017] Han Bing Qu, Jia Qiang Wang, Bin Li, and Ming Yu. Probabilistic model for robust affine and non- rigid point set matching. IEEE transactions on pattern analysis and machine intelligence, 39(2):371-384, 2017.","title":"Probabilistic model for robust affine and nonrigid point set matching","authors":"Bing Han, Jia Qiang Qu, Bin Wang, Ming Li, Yu","year":"2017","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Tsin and Kanade, 2004] Yanghai Tsin and Takeo Kanade. A correlation-based approach to robust point set registration. In European conference on computer vision, pages 558- 569. Springer, 2004.","title":"A correlation-based approach to robust point set registration","authors":"Kanade Tsin, Yanghai Tsin, Takeo Kanade","year":"2004","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wang et al., 2017] Gang Wang, Qiangqiang Zhou, and Yufei Chen. Robust non-rigid point set registration using spatially constrained gaussian fields. IEEE Transactions on Image Processing, 26(4):1759-1769, 2017.","title":"Robust non-rigid point set registration using spatially constrained gaussian fields","authors":"Wang","year":"2017","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wu et al., 2015] Yue Wu, Wenping Ma, Maoguo Gong, Linzhi Su, and Licheng Jiao. A novel point-matching al- gorithm based on fast sample consensus for image reg- istration. IEEE Geoscience and Remote Sensing Letters, 12(1):43-47, 2015.","title":"A novel point-matching algorithm based on fast sample consensus for image registration","authors":"Yue Wu, Wenping Ma, Maoguo Gong, Linzhi Su, Licheng Jiao","year":"2015","venue":"IEEE Geoscience and Remote Sensing Letters","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhang et al., 2014] Kai Zhang, XuZhi Li, and JiuXing Zhang. A robust point-matching algorithm for remote sensing image registration. IEEE Geoscience and Remote Sensing Letters, 11(2):469-473, 2014.","title":"A robust point-matching algorithm for remote sensing image registration","authors":"Kai Zhang, Xuzhi Li, Jiuxing Zhang","year":"2014","venue":"IEEE Geoscience and Remote Sensing Letters","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zheng and Doermann, 2006] Yefeng Zheng and David Do- ermann. Robust point matching for nonrigid shapes by preserving local neighborhood structures. IEEE trans- actions on pattern analysis and machine intelligence, 28(4):643-649, 2006.","title":"Yefeng Zheng and David Doermann. Robust point matching for nonrigid shapes by preserving local neighborhood structures","authors":"Doermann Zheng","year":"2006","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zheng et al., 2017] Qingqing Zheng, Yi Wang, and Pheng Ann Heng. Online robust image alignment via sub- space learning from gradient orientations. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1753-1762, 2017.","title":"Online robust image alignment via subspace learning from gradient orientations","authors":"Qingqing Zheng, Yi Wang, Pheng, Ann Heng","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhou et al., 2015] Xiaowei Zhou, Menglong Zhu, and Kostas Daniilidis. Multi-image matching via fast alternat- ing minimization. In Proceedings of the IEEE Interna- tional Conference on Computer Vision, pages 4032-4040, 2015.","title":"Multi-image matching via fast alternating minimization","authors":"Xiaowei Zhou, Menglong Zhu, Kostas Daniilidis","year":"2015","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}