Histograms of Oriented Gradients for Human Detection
Published 27 July 2005Open access
Navneet Dalal, Bill Triggs
Citations31,896
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
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.
Abstract
We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
Keywords
Computer Science
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
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.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA performance evaluation of local descriptors
6,692 Citations2005Krystian Mikolajczyk, C. Schmid
Technical reportsMaking Large-Scale SVM Learning Practical
4,317 Citations2006Thorsten Joachims
This chapter presents algorithmic and computational results developed for SVM light V 2.0, which make large-scale SVM training more practical and give guidelines for the application of SVMs to large domains.
International Journal of Computer VisionScale & Affine Invariant Interest Point Detectors
3,395 Citations2004Krystian Mikolajczyk, Cordelia Schmid
A comparative evaluation of different detectors is presented and it is shown that the proposed approach for detecting interest points invariant to scale and affine transformations provides better results than existing methods.
PCA-SIFT: a more distinctive representation for local image descriptors
3,210 Citations2004Ke Yan, Rahul Sukthankar
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.
International Journal of Computer VisionDetecting Pedestrians Using Patterns of Motion and Appearance
2,104 Citations2005Paul Viola, Michael Jones +1 more
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).
Computer Vision and Image UnderstandingThe Visual Analysis of Human Movement: A Survey
1,767 Citations1999Dariu M. Gavrila
A number of promising applications are identified and an overview of recent developments in this domain is provided, including work on whole-body or hand motion and the various methodologies.
International Journal of Computer VisionA Trainable System for Object Detection
1,282 Citations2000Constantine Papageorgiou, Tomaso Poggio
Detecting pedestrians using patterns of motion and appearance
987 Citations2003Viola, Jones +1 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceExample-based object detection in images by components
945 Citations2001Anand Mohan, C. Papageorgiou +1 more
Results suggest that the improvement in performance is due to the component-based approach and the ACC data classification architecture, which is capable of locating partially occluded views of people and people whose body parts have little contrast with the background.
Biological CyberneticsSpatial mapping in the primate sensory projection: Analytic structure and relevance to perception
630 Citations1977Eli Schwartz
It is shown that if this global structure is reiterated at the local level, then the sequence regularity of the simple cells of area 17 may be accounted for as well and the observed curve of cortical magnification, the linear scaling of receptive field size with eccentricity, and the mapping of global visual field landmarks.
Real-time object detection for "smart" vehicles
625 Citations1999Dariu M. Gavrila, V. Philomin
An efficient shape-based object detection method based on Distance Transforms is presented and its use for real-time vision on-board vehicles and some hardware-specific implementations of the proposed method as far as SIMD parallelism is concerned are discussed.
Lecture notes in computer scienceHuman Detection Based on a Probabilistic Assembly of Robust Part Detectors
610 Citations2004Krystian Mikolajczyk, Cordelia Schmid +1 more
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 is described.
International Journal of Computer VisionObject Detection Using the Statistics of Parts
350 Citations2004Henry Schneiderman, Takeo Kanade
A trainable object detector achieves reliable and efficient detection of human faces and passenger cars with out-of-plane rotation.
Matching shapes
345 Citations2002Serge Belongie, Jitendra Malik +1 more
A novel approach to measuring similarity between shapes and exploiting it for object recognition in a nearest-neighbor classification framework that applies regularized thin-plate splines to the transformation maps for this purpose.
Efficient matching of pictorial structures
307 Citations2002Pedro F. Felzenszwalb, D.P. Huttenlocher
An efficient algorithm for finding the best global match of a pictorial stucture to an image is presented and it is shown that this approach is suitable for many generic image recognition problems.
Vision-based pedestrian detection: the protector system
213 Citations2004Dariu M. Gavrila, J. Giebel +1 more
The PROTECTOR system combines pedestrian detection, trajectory estimation, risk assessment and driver warning, and an optimization scheme models the system as a succession of individual modules and finds a good overall parameter setting by combining individual ROCs using a convex-hull technique.
Lecture notes in computer scienceLearning to Parse Pictures of People
205 Citations2002Rémi Ronfard, Cordelia Schmid +1 more
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).
International Journal of Computer VisionProbabilistic Methods for Finding People
200 Citations2001Sergey Ioffe, David Forsyth
This work shows how to find people by finding candidate body segments, and then constructing assemblies of segments that are consistent with the constraints on the appearance of a person that result from kinematic properties, using an efficient projection algorithm for one popular classifier.
Computer vision for computer games
179 Citations2002William T. Freeman, Kazuhiro Tanaka +2 more
Two algorithms are described, based on image moments and orientation histograms, which exploit the capabilities of the chip to provide interactive response to the player's hand or body positions at 10 msec frame time and at low-cost.