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.

Underwater Fish Tracking for Moving Cameras Based on Deformable Multiple Kernels

Abstract: Fishery surveys that call for the use of single or multiple underwater cameras have been an emerging technology as a nonextractive mean to estimate the abundance of fish stocks. Tracking live fish in an open aquatic environment posts challenges that are different from general pedestrian or vehicle tracking in surveillance applications. In many rough habitats, fish are monitored by cameras installed on moving platforms, where tracking is even more challenging due to inapplicability of background models. In this paper, a novel tracking algorithm based on the deformable multiple kernels is proposed to address these challenges. Inspired by the deformable part model technique, a set of kernels is defined to represent the holistic object and several parts that are arranged in a deformable configuration. Color histogram, texture histogram, and the histogram of oriented gradients (HOGs) are extracted and serve as object features. Kernel motion is efficiently estimated by the mean-shift algorithm on color and texture features to realize tracking. Furthermore, the HOG-feature deformation costs are adopted as soft constraints on kernel positions to maintain the part configuration. Experimental results on practical video set from underwater moving cameras show the reliable performance of the proposed method with much less computational cost comparing with state-of-the-art techniques.

Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision

Abstract: Computer vision enables a wide range of applications in robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. For many of these applications, local embedded processing is preferred due to privacy and/or latency concerns. Accordingly, energy-efficient embedded vision hardware delivering real-time and robust performance is crucial. While deep learning is gaining popularity in several computer vision algorithms, a significant energy consumption difference exists compared to traditional hand-crafted approaches. In this paper, we provide an in-depth analysis of the computation, energy and accuracy trade-offs between learned features such as deep Convolutional Neural Networks (CNN) and hand-crafted features such as Histogram of Oriented Gradients (HOG). This analysis is supported by measurements from two chips that implement these algorithms. Our goal is to understand the source of the energy discrepancy between the two approaches and to provide insight about the potential areas where CNNs can be improved and eventually approach the energy-efficiency of HOG while maintaining its outstanding performance accuracy.

A Low-Complexity Pedestrian Detection Framework for Smart Video Surveillance Systems

Abstract: Pedestrian detection is a key problem in computer vision and is currently addressed with increasingly complex solutions involving compute-intensive features and classification schemes. In this scope, histogram of oriented gradients (HOG) in conjunction with linear support vector machine (SVM) classifier is considered to be the single most discriminative feature that has been adopted as a stand-alone detector as well as a key instrument in advance systems involving hybrid features and cascaded detectors. In this paper, we propose a pedestrian detection framework that is computationally less expensive as well as more accurate than HOG-linear SVM. The proposed scheme exploits the discriminating power of the locally significant gradients in building orientation histograms without involving complex floating point operations while computing the feature. The integer-only feature allows the use of powerful histogram inter-section kernel SVM classifier in a fast lookup-table-based implementation. Resultantly, the proposed framework achieves at least 3% more accurate detection results than HOG on standard data sets while being 1.8 and 2.6 times faster on conventional desktop PC and embedded ARM platforms, respectively, for a single scale pedestrian detection on VGA resolution video. In addition, hardware implementation on Altera Cyclone IV field-programmable gate array results in more than 40% savings in logic resources compared with its HOG-linear SVM competitor. Hence, the proposed feature and classification setup is shown to be a better candidate as the single most discriminative pedestrian detector than the currently accepted HOG-linear SVM.

An efficient vision-based traffic light detection and state recognition for autonomous vehicles

Abstract: Traffic Light Detection(TLD) and understanding their state semantics at intersections plays a pivotal role in driver assistance systems and, by extension, autonomous vehicles. Despite of several reliable traffic light state detection approaches in literature, traffic light state recognition still remains an open problem due to outdoor perception challenge which includes occlusions, illumination and scale variations. This paper presents a vision-based traffic light structure detection and convolutional neural network (CNN) based state recognition method, which is robust under different illumination and weather conditions. In the first step, traffic light candidate regions are generated by performing HSV based color segmentation, which are then filtered out using shape and area analysis. Further, in order to incorporate the structural information of traffic light in diverse background scenarios, Maximally Stable Extremal Region (MSER) approach is employed, which helps to localize the correct traffic light structure in the image. To further validate the traffic light candidate regions, Histogram of Oriented Gradients (HOG) features are extracted for each region and traffic light structures are validated using Support Vector Machine (SVM). The state of the traffic lights are then recognized using CNN. To evaluate the performance of the proposed method, we present several results under a variety of lighting conditions in a real-world environment. Experimental result shows that the proposed method outperforms other vision based conventional methods under varying light and weather conditions.

Human Detection by Quadratic Classification on Subspace of Extended Histogram of Gradients

Abstract: This paper proposes a quadratic classification approach on the subspace of Extended Histogram of Gradients (ExHoG) for human detection. By investigating the limitations of Histogram of Gradients (HG) and Histogram of Oriented Gradients (HOG), ExHoG is proposed as a new feature for human detection. ExHoG alleviates the problem of discrimination between a dark object against a bright background and vice versa inherent in HG. It also resolves an issue of HOG whereby gradients of opposite directions in the same cell are mapped into the same histogram bin. We reduce the dimensionality of ExHoG using Asymmetric Principal Component Analysis (APCA) for improved quadratic classification. APCA also addresses the asymmetry issue in training sets of human detection where there are much fewer human samples than non-human samples. Our proposed approach is tested on three established benchmarking data sets - INRIA, Caltech, and Daimler - using a modified Minimum Mahalanobis distance classifier. Results indicate that the proposed approach outperforms current state-of-the-art human detection methods.