PPT-TP12 - Local features: detection and description

Computer Vision FCUP 201819 Miguel Coimbra Slides by Prof Kristen Grauman Today Local invariant features Detection of interest points Harris corner detection Scale invariant blob detection . Discriminative part-based models. Many slides based on . P. . . Felzenszwalb. Challenge: Generic object detection. Pedestrian detection. Features: Histograms of oriented gradients (HOG). Partition image into 8x8 pixel blocks and compute histogram of gradient orientations in each block. Can you detect an abrupt change in this picture?. Ludmila. I . Kuncheva. School of Computer Science. Bangor University. Answer – at the end. Plan. Zeno says there is no such thing as change.... If change exists, is it a good thing?. . Each . feature set increases accuracy over the 69% baseline accuracy. .. Word Prominence Detection using Robust yet Simple Prosodic Features. Prosodic Features . ( . ** denotes novel features. ). 2011/12/08. Robot Detection. Robot Detection. Better Localization and Tracking. No Collisions with others. Goal. Robust . Robot . Detection. Long . Range. Short. . Range. Long Range. C. urrent . M. ethod. Twitter . A Behavioral Modeling . Approach. Ashwin. . Rajadesingan. , Reza Zafarani, and . Huan. . Liu. Sarcasm. . . a . nuanced form of language where usually, the user explicitly states the opposite of what she implies. . Oscar . Danielsson. (osda02@csc.kth.se). Stefan . Carlsson. (. stefanc@csc.kth.se. ). Josephine Sullivan (. sullivan@csc.kth.se. ). DICTA08. The Problem. Object categories are often modeled by collections (bag-of-features) or constellations (pictorial structures) of local features . Source: D. Lowe, L. Fei-Fei. Canny edge detector. Filter image with x, y derivatives of Gaussian . Find magnitude and orientation of gradient. Non-maximum suppression:. Thin multi-pixel wide “ridges” down to single pixel width. Monday March . 7. Prof. Kristen . Grauman. UT-Austin. Midterm Wed.. Covers material up until 3/1. Solutions to practice exam handed out today. Bring a 8.5”x11” sheet of notes if you want. Review the outlines and notes on course website, accompanying reading in textbook. Statistical Features for Image Splicing Detection. Xudong. Zhao, . Shilin. Wang, . Shenghong. Li and . Jianhua. Li. Shanghai Jiao Tong University, Shanghai P. R. China. Introduction. Digital Image Forensics:. on Online Social Networking. Group Members. :. Sunghun Park. Venkat Kotha. Li Wang . Wenzhi Cai. Outline. Problem Overview. Current Solutions. Limitations of Current Solutions. Conclusion . Our Solution. Devi Parikh. Slide credit: Kristen . Grauman. 1. Disclaimer: Most slides have been borrowed from Kristen . Grauman. , who may have borrowed some of them from others. Any time a slide did not already have a credit on it, I have credited it to Kristen. So there is a chance some of these credits are inaccurate.. State-of-the-art face detection demo. (Courtesy . Boris . Babenko. ). Face detection and recognition. Detection. Recognition. “Sally”. Face detection. Where are the faces? . Face Detection. What kind of features?. CS5670: Computer Vision. Announcements. Project 1 code due Thursday, 2/25 at 11:59pm. Turnin. via . Github. Classroom. Project 1 artifact due Monday, 3/1 at 11:59pm. Quiz this Wednesday, 2/24, via Canvas. A Behavioral Modeling . Approach. Ashwin. . Rajadesingan. , Reza Zafarani, and . Huan. . Liu. Sarcasm. . . a . nuanced form of language where usually, the user explicitly states the opposite of what she implies. .