Histogram of oriented gradients

About: Histogram of oriented gradients is a research topic. Over the lifetime, 2037 publications have been published within this topic receiving 55881 citations. The topic is also known as: HOG.

Face pose estimation with combined 2D and 3D HOG features

Abstract: This paper describes an approach to location and orientation estimation of a person's face with color image and depth data from a Kinect sensor. The combined 2D and 3D histogram of oriented gradients (HOG) features, called RGBD-HOG features, are extracted and used throughout our approach. We present a coarse-to-fine localization paradigm to obtain localization results efficiently using multiple HOG filters trained in support vector machines (SVMs). A feed-forward multi-layer perception (MLP) network is trained for fine face orientation estimation over a continuous range. The experimental result demonstrates the effectiveness of the RGBD-HOG feature and our face pose estimation approach.

Multiple HOG templates for gait recognition

Abstract: In gait recognition field, template-based approaches such as Gait Energy Image (GEI) and Chrono-Gait Image (CGI) can achieve good recognition performance with low computational cost. Meanwhile, CGI can preserve temporal information better than GEI. However, they pay less attention to the local shape features. To preserve temporal information and generate more abundant local shape features, we generate multiple HOG templates by extracting Histogram of Oriented Gradients (HOG) of GEI and CGI templates. Experiments show that compared with several published approaches, our proposed multiple HOG templates achieve better performance for gait recognition.

Traffic Sign Recognition Using Complementary Features

Abstract: Traffic sign recognition is difficult due to the low resolution of image, illumination variation and shape distortion. On the public dataset GTSRB, the state-of-the-art performance have been obtained by convolutional neural networks (CNNs), which learn discriminative features automatically to achieve high accuracy but suffer from high computation costs in both training and classification. In this paper, we propose an effective traffic sign recognition method using multiple features which have demonstrated effective in computer vision and are computationally efficient. The extracted features are the histogram of oriented gradients (HOG) feature, Gabor filter feature and local binary pattern (LBP) feature. Using a linear support vector machine (SVM) for classification, each feature yields fairly high accuracy. The combination of three features has shown good complementariness and yielded competitively high accuracy. On the GTSRB dataset, our method reports an accuracy of 98.65%.

System and method for human detection and counting using background modeling, hog and haar features

Abstract: A system for adaptive learning based human detection for channel input of captured human image signals, the said system comprises of: a sensor for tracking real time images of environment of interest; a feature extraction and classifiers generation means for extracting a plurality of the features and classifying the features associated with time-space descriptors of image comprising background modeling, Histogram of Oriented Gradients (HOG) and Haar like wavelet; a processor configured to process extracted feature classifiers associated with plurality of real-time images; a means for combining plurality of feature classifiers of time-space descriptors; a means for evaluating linear probability of human detection based on predetermined threshold value of feature classifier in a time window having at least one image frame; a counter for counting the number of human in the image; and a transmission means adapted to send the final human detection decision and number thereof to storage means.

Human Action Recognition in Large-Scale Datasets Using Histogram of Spatiotemporal Gradients

Abstract: Research in human action recognition has advanced along multiple fronts in recent years to address various types of actions including simple, isolated actions in staged data (e.g., KTH dataset), complex actions (e.g., Hollywood dataset) and naturally occurring actions in surveillance videos (e.g, VIRAT dataset). Several techniques including those based on gradient, flow and interest-points have been developed for their recognition. Most perform very well in standard action recognition datasets, but fail to produce similar results in more complex, large-scale datasets. Here we analyze the reasons for this less than successful generalization by considering a state-of-the-art technique, histogram of oriented gradients in spatiotemporal volumes as an example. This analysis may prove useful in developing robust and effective techniques for action recognition.