|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
2011 Third International Conference on Knowledge and Systems Engineering
Improved HOG Descriptors
Hanoi, Vietnam
October 14-October 17
ISBN: 978-0-7695-4567-7
| ASCII Text | x | ||
| Linh Dang, Buu Bui, Phong D. Vo, Trung N. Tran, Bac H. Le, "Improved HOG Descriptors," Knowledge and Systems Engineering, International Conference on, pp. 186-189, 2011 Third International Conference on Knowledge and Systems Engineering, 2011. | |||
| BibTex | x | ||
| @article{ 10.1109/KSE.2011.36, author = {Linh Dang and Buu Bui and Phong D. Vo and Trung N. Tran and Bac H. Le}, title = {Improved HOG Descriptors}, journal ={Knowledge and Systems Engineering, International Conference on}, volume = {0}, year = {2011}, isbn = {978-0-7695-4567-7}, pages = {186-189}, doi = {http://doi.ieeecomputersociety.org/10.1109/KSE.2011.36}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Knowledge and Systems Engineering, International Conference on TI - Improved HOG Descriptors SN - 978-0-7695-4567-7 SP186 EP189 A1 - Linh Dang, A1 - Buu Bui, A1 - Phong D. Vo, A1 - Trung N. Tran, A1 - Bac H. Le, PY - 2011 KW - HOG KW - Spatial Selective KW - Multi-level VL - 0 JA - Knowledge and Systems Engineering, International Conference on ER - | |||
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/KSE.2011.36
we study the feature set for object recognition problem, and use human detection as a test case. We propose two improvements based on HOG model which are Spatial Selective Method and Multi-level Method. In Spatial Selective One, we use HOG descriptor to extract feature vector from image window, but we shorten the feature vector size by eliminating less informative region. We get the same performance as Dalal's method, while reducing the extraction running time by 40%. In the Multi-level Method, we enhance the performance of HOG descriptor by 3% by adding more information to feature vector set through using concatenating multi-level on extraction process. All the experiments of this work are evaluated on INRIA pedestrian dataset 2009.
Index Terms:
HOG, Spatial Selective, Multi-level
Citation:
Linh Dang, Buu Bui, Phong D. Vo, Trung N. Tran, Bac H. Le, "Improved HOG Descriptors," kse, pp.186-189, 2011 Third International Conference on Knowledge and Systems Engineering, 2011
Usage of this product signifies your acceptance of the Terms of Use.