[talks] ​​​​​Linguang Zhang will be presenting his General Exam on Thursday, May 05, 2016 at 10am in CS 402.

[Nicki Gotsis]

Linguang Zhang will be presenting his General Exam on Thursday, May 05, 2016 at 10am in CS 402.

The members of his committee are Szymon Rusinkiewicz (adviser), Adam Finkelstein, and Tom Funkhouser. 

Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so.  His abstract and reading list follow below.

Abstract

The Global Positioning System (GPS) is being widely used on almost every
mobile device nowadays, and it is playing critical roles in many tasks
which require location information. However, GPS is typically used
outdoors, and the accuracy of commercial GPS devices is usually limited to
few meters. In this work, we attempt to design an image-based global
micro-positioning system which can achieve an accuracy of few centimeters
and is reliable both indoors and outdoors. The key idea behind of our
system is that random textures in the real world always have imperfections
such as cracks or scratches which are persistently visible. To capture
these minor details, our system includes a downward-facing camera that
observes fine textures on the ground as well as an image processing unit
that will locate the observed texture patches in a large database
constructed in the training phase. Instead of the images themselves,
distinctive features extracted from the images along with the global
location information are stored in the database using an efficient data
structure so that localization is fast.

-----------------------

Reading list


Textbook : Computer Vision: Algorithms and Applications


[SIFT] Lowe, David G. "Distinctive image features from scale-invariant
keypoints." International journal of computer vision 60.2 (2004): 91-110.


[D-NETS] Von Hundelshausen, Felix, and Rahul Sukthankar. "D-nets: Beyond
patch-based image descriptors." Computer Vision and Pattern Recognition
(CVPR), 2012 IEEE Conference on. IEEE, 2012.


[DISTINCTIVE] Shilane, Philip, and Thomas Funkhouser. "Selecting
distinctive 3D shape descriptors for similarity retrieval." Shape Modeling
and Applications, 2006. SMI 2006. IEEE International Conference on. IEEE,
2006.


[PATCHMATCH] Barnes, Connelly, et al. "The PatchMatch randomized matching
algorithm for image manipulation." Communications of the ACM 54.11 (2011):
103-110.


[FLANN] Muja, Marius, and David G. Lowe. "Fast Approximate Nearest
Neighbors with Automatic Algorithm Configuration." VISAPP (1) 2 (2009):
331-340.


[FINGERPRINT] Clarkson, William, et al. "Fingerprinting blank paper using
commodity scanners." Security and Privacy, 2009 30th IEEE Symposium on.
IEEE, 2009.


[GOOD FEATURES] Shi, Jianbo, and Carlo Tomasi. "Good features to track."
Computer Vision and Pattern Recognition, 1994. Proceedings CVPR'94., 1994
IEEE Computer Society Conference on. IEEE, 1994.


[MATCHABILITY] Hartmann, Wilfried, Michal Havlena, and Konrad Schindler.
"Predicting matchability." Proceedings of the IEEE Conference on Computer
Vision and Pattern Recognition. 2014.


[ROBOT] Kelly, Alonzo, et al. "Field and service applications-an
infrastructure-free automated guided vehicle based on computer vision-an
effort to make an industrial robot vehicle that can operate without
supporting infrastructure." Robotics & Automation Magazine, IEEE 14.3
(2007): 24-34.


[BOLD] Balntas, Vassileios, Lilian Tang, and Krystian Mikolajczyk.
"BOLD-Binary Online Learned Descriptor For Efficient Image Matching."
Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition. 2015.


[4PCS] Aiger, Dror, Niloy J. Mitra, and Daniel Cohen-Or. "4-points
congruent sets for robust pairwise surface registration." ACM Transactions
on Graphics (TOG). Vol. 27. No. 3. ACM, 2008.


[FOURIER] Zhang, Dengsheng, and Guojun Lu. "Generic Fourier descriptor for
shape-based image retrieval." Multimedia and Expo, 2002. ICME'02.
Proceedings. 2002 IEEE International Conference on. Vol. 1. IEEE, 2002.