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.

Service Orchestration of Optimizing Continuous Features in Industrial Surveillance Using Big Data Based Fog-Enabled Internet of Things

Abstract: Video-based surveillance pedestrian detection is playing a key role in emerging technologies, such as Internet of Things and Big Data for use in smart industries and cities. In pedestrian detection, factors, such as lighting, object collisions, backgrounds, clothes, and occlusion cause complications because of inconsistent classification. To address these problems, enhancements in feature extraction are required. These features should arise from multiple variations of pedestrians. Well-known features used for pedestrian detection involve histogram of gradients, scale-invariant feature transform, and Haar built to represent boundary level classifications. Occlusion feature extraction supports identification of regions involving pedestrian detection. Classifiers, such as support vector machine and random forests are also used to classify pedestrians. All these feature extraction and pedestrian detection methods are now being automated using deep learning methods known as convolutional neural networks (CNNs). A model is trained by providing positive and negative image data sets, and larger data sets provide more accurate results when a CNN-based approach is used. Additionally, Extensible Markup Language cascading is used for detecting faces from detected pedestrian.

Age, gender and handedness prediction from handwriting using gradient features

Abstract: This work introduces two gradient features for writer's gender, handedness, and age range prediction. The first feature is the Histogram of Oriented Gradients, which highlights the distribution of gradient orientations within images. The second feature is the so-called gradient local binary patterns, which is an improved gradient feature that incorporates the local binary pattern neighborhood in the gradient calculation. The prediction task is achieved by using SVM classifier. Experiments are performed on two corpuses of English and Arabic handwritten text. The results obtained in terms of classification accuracy highlight the effectiveness of the proposed features, which overcome the state of the art.

Action recognition using rank-1 approximation of Joint Self-Similarity Volume

Abstract: In this paper, we make three main contributions in the area of action recognition: (i) We introduce the concept of Joint Self-Similarity Volume (Joint SSV) for modeling dynamical systems, and show that by using a new optimized rank-1 tensor approximation of Joint SSV one can obtain compact low-dimensional descriptors that very accurately preserve the dynamics of the original system, e.g. an action video sequence; (ii) The descriptor vectors derived from the optimized rank-1 approximation make it possible to recognize actions without explicitly aligning the action sequences of varying speed of execution or different frame rates; (iii) The method is generic and can be applied using different low-level features such as silhouettes, histogram of oriented gradients, etc. Hence, it does not necessarily require explicit tracking of features in the space-time volume. Our experimental results on three public datasets demonstrate that our method produces remarkably good results and outperforms all baseline methods.