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.

HOG Feature Extractor Hardware Accelerator for Real-Time Pedestrian Detection

Abstract: Histogram of oriented gradients (HOG) is considered as the most promising algorithm in human detection, however its complexity and intensive computational load is an issue for real-time detection in embedded systems. This paper presents a hardware accelerator for HOG feature extractor to fulfill the requirements of real-time pedestrian detection in driver assistance systems. Parallel and deep pipelined hardware architecture with special defined memory access pattern is employed to improve the throughput while maintaining the accuracy of the original algorithm reasonably high. Adoption of efficient memory access pattern, which provides simultaneous access to the required memory area for different functional blocks, avoids repetitive calculation at different stages of computation, resulting in both higher throughput and lower power. It does not impose any further resource requirements with regard to memory utilization. Our presented hardware accelerator is capable of extracting HOG features for 60 fps (frame per second) of HDTV (1080x1920) frame and could be employed with several instances of support vector machine (SVM) classifier in order to provide multiple object detection.

Classifying Time Series Using Local Descriptors with Hybrid Sampling

Abstract: Time series classification (TSC) arises in many fields and has a wide range of applications. Here, we adopt the bag-of-words (BoW) framework to classify time series. Our algorithm first samples local subsequences from time series at feature-point locations when available. It then builds local descriptors, and models their distribution by Gaussian mixture models (GMM), and at last it computes a Fisher Vector (FV) to encode each time series. The encoded FV representations of time series are readily used by existing classifiers, e.g., SVM, for training and prediction. In our work, we focus on detecting better feature points and crafting better local representations, while using existing techniques to learn codebook and encode time series. Specifically, we develop an efficient and effective peak and valley detection algorithm from real-case time series data. Subsequences are sampled from these peaks and valleys, instead of sampled randomly or uniformly as was done previously. Then, two local descriptors, Histogram of Oriented Gradients (HOG-1D) and Dynamic time warping-Multidimensional scaling (DTW-MDS), are designed to represent sampled subsequences. Both descriptors complement each other, and their fused representation is shown to be more descriptive than individual ones. We test our approach extensively on 43 UCR time series datasets, and obtain significantly improved classification accuracies over existing approaches, including NNDTW and shapelet transform.

Scale Space Histogram of Oriented Gradients for Human Detection

Abstract: Human detection is the task of finding presence and position of human beings in images, In this paper, we apply scale space theory to detection human in still images. By integrating scale space theory with histogram of oriented gradients(HOG), we designed a new feature descriptor called scale space histogam of oriented gradients (SS-HOG). SS-HOG focus on the multiple scale property of describe an object. Using HOGs at multiple scale, SS-HOG encodes more information to discriminate human bodies from other object types than traditional uni-scale HOGs Experiments on INRIA person dataset demonstrate the effectiveness of our method.

Learning Human Actions by Combining Global Dynamics and Local Appearance

Abstract: In this paper, we address the problem of human action recognition through combining global temporal dynamics and local visual spatio-temporal appearance features. For this purpose, in the global temporal dimension, we propose to model the motion dynamics with robust linear dynamical systems (LDSs) and use the model parameters as motion descriptors. Since LDSs live in a non-Euclidean space and the descriptors are in non-vector form, we propose a shift invariant subspace angles based distance to measure the similarity between LDSs. In the local visual dimension, we construct curved spatio-temporal cuboids along the trajectories of densely sampled feature points and describe them using histograms of oriented gradients (HOG). The distance between motion sequences is computed with the Chi-Squared histogram distance in the bag-of-words framework. Finally we perform classification using the maximum margin distance learning method by combining the global dynamic distances and the local visual distances. We evaluate our approach for action recognition on five short clips data sets, namely Weizmann, KTH, UCF sports, Hollywood2 and UCF50, as well as three long continuous data sets, namely VIRAT, ADL and CRIM13. We show competitive results as compared with current state-of-the-art methods.