Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/CVPR.2005.177 - Corpus ID: 206590483
@article{Dalal2005HistogramsOO, title={Histograms of oriented gradients for human detection}, author={Navneet Dalal and Bill Triggs}, journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)}, year={2005}, volume={1}, pages={886-893 vol. 1}, url={https://api.semanticscholar.org/CorpusID:206590483}}
- Navneet Dalal, B. Triggs
- Published in Computer Vision and Pattern… 20 June 2005
- Computer Science
It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
32,895 Citations
4,811
10,150
15,776
300
Figures from this paper
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
Topics
Human Detection (opens in a new tab)Histograms Of Oriented Gradient (opens in a new tab)MIT Pedestrian Database (opens in a new tab)Histogram Of Oriented Gradient (opens in a new tab)R-HOG (opens in a new tab)Fine Orientation Binning (opens in a new tab)C-HOG (opens in a new tab)L2-Hys (opens in a new tab)Orientation Bins (opens in a new tab)False Positives Per Window (opens in a new tab)
32,895 Citations
- Qiang ZhuMei-Chen YehK. ChengS. Avidan
- 2007
Computer Science
It is shown that the combination of the cascade of rejectors approach and the HoG features led to a fast and accurate human detection system and the integral image representation was used and the rejection cascade significantly speeded up the computation.
- 1,148
- PDF
- Qiang ZhuMei-Chen YehKwang-Ting ChengS. Avidan
- 2006
Computer Science
2006 IEEE Computer Society Conference on Computer…
This work integrates the cascade-of-rejectors approach with the Histograms of Oriented Gradients (HoG) features to achieve a fast and accurate human detection system that can process up to 30 frames per second while maintaining an accuracy level similar to existing methods.
- 510
- PDF
- Yahia SaidMohamed AtriR. Tourki
- 2011
Computer Science
2011 International Conference on Communications…
The Histogram of Oriented Gradients descriptors show experimentally significantly out-performs existing feature sets for human detection and are chosen to extract human feature from visible spectrum images based on OpenCv and MS VC++.
- 28
- PDF
- Zhaojie LuoJinhui ChenT. TakiguchiY. Ariki
- 2015
Computer Science
2015 Asia-Pacific Signal and Information…
This research adopts annular spatial bins type cells and applies radial gradient transform (RGT) to attain gradient binning invariance for feature descriptors and significantly enhances HOG with respect to rotation-invariant ability and feature descripting accuracy.
- 9
- Highly Influenced
- PDF
- Marco PerdersoliJordi GonzàlezBhaskar ChakrabortyJ. Villanueva
- 2007
Computer Science
A human detection framework based on an enhanced version of Histogram of Oriented Gradients features, which outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster.
- 20
- PDF
- Ning HeJiaheng CaoLin Song
- 2008
Computer Science
2008 International Symposium on Information…
A new feature descriptor called scale space histogam of oriented gradients (SS-HOG) is designed, which encodes more information to discriminate human bodies from other object types than traditional uni-scale HOGs.
- 44
- Highly Influenced
- Tejas Rana
- 2020
Computer Science
Comparative experiments show that though HOG is simple feature descriptor, the proposed HOG feature achieves good results with much lower computational time.
- Shih-Shinh HuangHsin-Ming TsaiPei-Yung HsiaoMengru TuEr-Liang Jian
- 2011
Computer Science
MMM
This work uses AdaBoost algorithm to learn local characteristics of human based on HOGs and adopts the head contour as the global feature for improving the detection accuracy.
- 11
- Highly Influenced
- E. ZaytsevaS. SeguíJordi Vitrià
- 2012
Computer Science
CIARP
The new representation, called sketchable-HoG, extends the classical histogram of oriented gradients (HoG) feature by adding two different aspects: the stability of the majority orientation and the continuity of gradient orientations.
- 4
- PDF
- Yuanyuan NanChao LiangWenhua FangXiao WangYuhong YangJun Chen
- 2014
Computer Science
ICIMCS '14
A salience representation for pedestrian detection, Histograms-Of-Salience (HOS) is proposed and investigated, extracted saliency map learned from data by using Histogram Based Contrast, and aggregate salient value and oriented gradients to form local HOS.
- 1
- PDF
...
...
26 References
- Marco PerdersoliJordi GonzàlezBhaskar ChakrabortyJ. Villanueva
- 2007
Computer Science
A human detection framework based on an enhanced version of Histogram of Oriented Gradients features, which outperforms the integral of oriented histograms allowing the calculation of a single feature four times faster.
- 20
- PDF
- K. MikolajczykC. SchmidAndrew Zisserman
- 2004
Computer Science
ECCV
We describe a novel method for human detection in single images which can detect full bodies as well as close-up views in the presence of clutter and occlusion. Humans are modeled as flexible…
- 771
- PDF
- Yan KeR. Sukthankar
- 2004
Computer Science
Proceedings of the 2004 IEEE Computer Society…
This paper examines (and improves upon) the local image descriptor used by SIFT, and demonstrates that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation.
- 3,816
- Highly Influential
- PDF
- Henry SchneidermanT. Kanade
- 2004
Computer Science
International Journal of Computer Vision
A trainable object detector achieves reliable and efficient detection of human faces and passenger cars with out-of-plane rotation.
- 416
- PDF
- D. Lowe
- 2004
Computer Science
International Journal of Computer Vision
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
- 45,279
- Highly Influential
- PDF
- C. PapageorgiouTomaso A. Poggio
- 2004
Computer Science
International Journal of Computer Vision
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in…
- 1,420
- Highly Influential
- PDF
- Rémi RonfardC. SchmidB. Triggs
- 2002
Computer Science
ECCV
This work builds on Forsyth & Fleck's general 'body plan' methodology and Felzenszwalb & Huttenlocher's dynamic programming approach for efficiently assembling candidate parts into 'pictorial structures' but replaces the rather simple part detectors used in these works with dedicated detectors learned for each body part using SupportVector Machines (SVMs) or Relevance Vector Machines (RVMs).
- 290
- PDF
- K. MikolajczykC. Schmid
- 2005
Computer Science
IEEE Transactions on Pattern Analysis and Machine…
It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.
- 5,187
- PDF
- Paul A. ViolaMichael J. JonesDaniel Snow
- 2003
Computer Science
Proceedings Ninth IEEE International Conference…
This pedestrian detection system is the first to combine both sources of information in a single detector, and operates on low resolution images under difficult conditions (such as rain and snow).
- 2,655
- PDF
- W. FreemanMichal Roth
- 1995
Computer Science
A method to recognize hand gestures, based on a pattern recognition technique developed by McConnell employing histograms of local orientation, which is simple and fast to compute, and which can distinguish a small vocabulary of about 10 hand gestures.
- 650
- Highly Influential
- PDF
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers