Alexander Freytag
39deb76c71
supporting save search path without flooding
|
%!s(int64=10) %!d(string=hai) anos | |
|---|---|---|
| data | %!s(int64=11) %!d(string=hai) anos | |
| demos | %!s(int64=11) %!d(string=hai) anos | |
| detect | %!s(int64=11) %!d(string=hai) anos | |
| features | %!s(int64=11) %!d(string=hai) anos | |
| learn | %!s(int64=11) %!d(string=hai) anos | |
| misc | %!s(int64=11) %!d(string=hai) anos | |
| LICENSE | %!s(int64=11) %!d(string=hai) anos | |
| README.md | %!s(int64=10) %!d(string=hai) anos | |
| compileWHOEfficient.m | %!s(int64=11) %!d(string=hai) anos | |
| initWorkspaceWHOGeneric.m | %!s(int64=10) %!d(string=hai) anos | |
| test.jpg | %!s(int64=11) %!d(string=hai) anos | |
| train.jpg | %!s(int64=11) %!d(string=hai) anos |
README.md
Generic version of WHO for object detection with LDA models
COPYRIGHT
This package contains Matlab source code for object detection with LDA models.
This repo is based on the original version of who from (Bharath Hariharan, Jitendra Malik and Deva Ramanan. Discriminative decorrelation for clustering and classification. In ECCV 2012 ). We significantly altered it, making it more flexible, easier to access, and less focused on hog features in general.
START / SETUP
Compile mex-files via
compileWHOEfficient
Setup workspace
initWorkspaceWHOGeneric
RUN DETECTION DEMO
Run a demo which learns an LDA model for detecting bycicles and using HOG features as underlying representation
demoWhitenedHOG