Pia Bideau, Aruni RoyChowdhury, Rakesh R Menon, E. Learned-Miller
{"title":"The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation","authors":"Pia Bideau, Aruni RoyChowdhury, Rakesh R Menon, E. Learned-Miller","doi":"10.1109/CVPR.2018.00060","DOIUrl":null,"url":null,"abstract":"Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid motion flow based on classical perspective projection constraints. We then combine piecewise rigid motions into complex deformable and articulated objects, guided by semantic segmentation from CNNs and a second \"object-level\" statistical model. This combination of classical geometric knowledge combined with the pattern recognition abilities of CNNs yields excellent performance on a wide range of motion segmentation benchmarks, from complex geometric scenes to camouflaged animals.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"38","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2018.00060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 38
Abstract
Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid motion flow based on classical perspective projection constraints. We then combine piecewise rigid motions into complex deformable and articulated objects, guided by semantic segmentation from CNNs and a second "object-level" statistical model. This combination of classical geometric knowledge combined with the pattern recognition abilities of CNNs yields excellent performance on a wide range of motion segmentation benchmarks, from complex geometric scenes to camouflaged animals.