Nonparametric Scene Parsing via Label Transfer Tamara Berg非参数的现场分析通过标签转移塔玛拉贝格.pptxVIP

Nonparametric Scene Parsing via Label Transfer Author: Ce Liu Jenny Yuen Antonio Torralba Group 3 Presenter: Hongsheng Yang Adapted from Ce Lius CVPR2009 slides The task of object recognition and scene parsing Adapted from Ce Lius CVPR2009 slides Input Output Training based object recognition and scene parsing Sliding window method - Train a classifier for a fixed-size window (e.g., car vs. non-car) - Try all possible scales and locations, run the classifier - Merge multiple detections Texton method - Extract pixel-wise high-dimensional feature vectors - Train a multi-class classifier - Spatial regularity: neighboring pixels should agree Adapted from Ce Lius CVPR2009 slides J. Shotton et al. Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation. ECCV, 2006 Label Transfer - Intuition I’ve seen and recognized a few similar pictures before. If I could correspond each pixels in the query image to the pixels in the previous seen images, then I could infer how the new query image looks like based on the database images. Adapted from Ce Lius CVPR2009 slides Label Transfer - Pipeline Given a query image Find another annotated image with similar scene Find dense correspondences between these two images Warp the annotation according to the correspondences Two key components: A large, annotated database Good correspondences for label transfer Adapted from Ce Lius CVPR2009 slides Query from Database User annotation Warped annotation Large image databases Adapted from Ce Lius CVPR2009 slides A subset of LabelMe database (outdoor scenes) 2688 in total, 2488 for training, 200 for test 33 object categories + “unlabeled”, including street, beach, mountains, fields, buildings, etc. B. Russell et al. LabelMe: a database and web-based tool for image annotation. IJCV 2008. A good correspondence approach SIFT flow - analogous to - Optical flow Scene level - Image level SIFT Flow – dense SIFT,