Histogram of oriented gradients
About: Histogram of oriented gradients is a(n) research topic. Over the lifetime, 2037 publication(s) have been published within this topic receiving 55881 citation(s). The topic is also known as: HOG.
Papers published on a yearly basis
20 Jun 2005
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.
23 Jun 2013
TL;DR: A new descriptor for activity recognition from videos acquired by a depth sensor is presented that better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.
Abstract: We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates. To build the histogram, we create 4D projectors, which quantize the 4D space and represent the possible directions for the 4D normal. We initialize the projectors using the vertices of a regular polychoron. Consequently, we refine the projectors using a discriminative density measure, such that additional projectors are induced in the directions where the 4D normals are more dense and discriminative. Through extensive experiments, we demonstrate that our descriptor better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.
01 Aug 2002
TL;DR: This work discusses the various features of this operator that make it the filter of choice in the area of edge detection, and reviews several linear and nonlinear Gaussian-based edge detection methods.
Abstract: The Gaussian filter has been used extensively in image processing and computer vision for many years. We discuss the various features of this operator that make it the filter of choice in the area of edge detection. Despite these desirable features of the Gaussian filter, edge detection algorithms which use it suffer from many problems. We review several linear and nonlinear Gaussian-based edge detection methods.
01 Jan 1986
TL;DR: This chapter discusses three-Dimensional Shape Representation, Relational Matching, and Machine Learning of Computer Vision Algorithms for 3D Perception of Dynamic Scenes.
Abstract: Principles of Computer Vision. Three-Dimensional Shape Representation. Three-Dimensional Shape Recovery from Line Drawings. Recovery of 3D Shape of Curved Objects. Surface Reflection Mechanism. Extracting Shape from Shading. Range Image Analysis. Stereo Vision. Machine Learning of Computer Vision Algorithms. Image Sequence Analysis for 3D Perception of Dynamic Scenes. Nonrigid Motion Analysis. Analysis and Synthesis of Human Movement. Relational Matching. Three-Dimensional Object Recognition. Fundamental Principles of Robot Vision. Chapter References.
05 Dec 2011
TL;DR: This paper takes inspiration from the Histogram of Oriented Gradients (HOG) detector to design a robust method to detect people in dense depth data, called HOD, and proposes Combo-HOD, a RGB-D detector that probabilistically combines HOD and HOG.
Abstract: People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task. In this paper, we present a novel people detection approach for RGB-D data. We take inspiration from the Histogram of Oriented Gradients (HOG) detector to design a robust method to detect people in dense depth data, called Histogram of Oriented Depths (HOD). HOD locally encodes the direction of depth changes and relies on an depth-informed scale-space search that leads to a 3-fold acceleration of the detection process. We then propose Combo-HOD, a RGB-D detector that probabilistically combines HOD and HOG. The experiments include a comprehensive comparison with several alternative detection approaches including visual HOG, several variants of HOD, a geometric person detector for 3D point clouds, and an Haar-based AdaBoost detector. With an equal error rate of 85% in a range up to 8m, the results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected with a Kinect sensor in a populated indoor environment.
Related Topics (5)
111.8K papers, 2.1M citations
Convolutional neural network
74.7K papers, 2M citations
79.8K papers, 2.1M citations
79.6K papers, 1.8M citations
Feature (computer vision)
128.2K papers, 1.7M citations