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.

Pedestrian detection in low resolution night vision images

Abstract: This paper presents a test of pedestrian detection in low resolution night vision infrared images. An image feature extractor based on histograms of oriented gradients followed by a Support Vector Machine (SVM) classifier are evaluated, optimized and used. Tests performed on three different night vision infrared datasets show that the classification quality of the proposed method is very high even in very low resolutions of images. In practice, large frame size for analysis not always improves the classification effectiveness, but always requires more time for processing.

Text detection and recognition in natural scenes and consumer videos

Abstract: We propose an end-to-end system for text detection and recognition in natural scenes and consumer videos. Maximally Stable Extremal Regions which are robust to illumination and viewpoint variations are selected as text candidates. Rich shape descriptors such as Histogram of Oriented Gradients, Gabor filter, corners and geometrical features are used to represent the candidates and classified using a support vector machine. Positively labeled candidates serve as anchor regions for word formation. We then group candidate regions based on geometric and color properties to form word boundaries. To speed up the system for practical applications, we use Partial Least Squares approach for dimensionality reduction. The detected words are binarized, filtered and passed to a hidden Markov model based Optical Character Recognition (OCR) system for recognition. We show significant improvement in text detection and recognition tasks over previous approaches on a large consumer video dataset. Furthermore, the event detection system built upon the OCR output of this approach outperformed multiple other OCR-only based submissions in the recently concluded NIST TRECVID 2013 multimedia event detection evaluations.

Gpu architecture for stationary multisensor pedestrian detection at smart intersections

Abstract: We present a real-time multisensor architecture for combined laser scanner and infra-red video-based pedestrian detection and tracking used within a road side unit for intersection assistance. In order to achieve outmost classification performance we propose a cascaded classifier using laser scanner hypothesis generation and histogram of oriented gradients (HOG) descriptors for video-based classification together with linear and Gaussian kernel support vector machines (SVM). The entire classification cascade is implemented on a graphics processing unit (GPU). Giving real-time performance top priority, we present novel compute unified device architecture (CUDA) implementations of a selective HOG-based feature extraction and background subtraction based on mixture of Gaussians (MOG). The classification cascade is managed by a multi-core CPU that further performs pedestrian tracking using a linear Kalman filter. Evaluation on an infra-red benchmark database and an experimental study on a real-world intersection used within the Ko-PER project confirm excellent classification and real-time performance around the clock without external illumination.

A Comparative Study of Different Feature Extraction Techniques for Offline Malayalam Character Recognition

Abstract: Offline Handwritten Character Recognition of Malayalam scripts have gained remarkable attention in the past few years. The complicated writing style of Malayalam characters with loops and curves make the recognition process highly challenging. This paper presents a comparative study of Malayalam character recognition using 4 different feature sets—Zonal features, Projection histograms, Chain code histograms and Histogram of Oriented Gradients. The performance of these features for isolated Malayalam vowels and 5 consonants are evaluated in this study using feedforward neural networks as classifier. The final recognition results were computed using a 5 fold cross validation scheme. The best recognition accuracy of 94.23 % was obtained in this study using Histogram of Oriented Gradients features.

Fast Human Detection Using Motion Detection and Histogram of Oriented Gradients

Abstract: This paper presents a real-time Human detection algorithm based on HOG (Histograms of Oriented Gradients) features and SVM (Support Vector Machine) architecture. Motion detection is used to extract moving regions, which can be scanned by sliding windows; detecting moving region can subtract unnecessary sliding windows of static background regions under the surveillance conditions, then detection efficiency can be improved. Every sliding window is regarded as an individual image region and HOG features are calculated as classified eigenvectors. At last, the detected video objects can be categorized into pre-defined groups of humans and other objects by using SVM classifier. Experimental results from real-time video are provided which demonstrate the effectiveness of the method.