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.

An Optimized and Fast Scheme for Real-Time Human Detection Using Raspberry Pi

Abstract: Real-time human detection is a challenging task due to appearance variance, occlusion and rapidly changing content; therefore it requires efficient hardware and optimized software. This paper presents a real-time human detection scheme on a Raspberry Pi. An efficient algorithm for human detection is proposed by processing regions of interest (ROI) based upon foreground estimation. Different number of scales have been considered for computing Histogram of Oriented Gradients (HOG) features for the selected ROI. Support vector machine (SVM) is employed for classification of HOG feature vectors into detected and non-detected human regions. Detected human regions are further filtered by analyzing the area of overlapping regions. Considering the limited capabilities of Raspberry Pi, the proposed scheme is evaluated using six different testing schemes on Town Centre and CAVIAR datasets. Out of these six testing schemes, Single Window with two Scales (SW2S) processes 3 frames per second with acceptable less accuracy than the original HOG. The proposed algorithm is about 8 times faster than the original multi-scale HOG and recommended to be used for real-time human detection on a Raspberry Pi.

Hybrid three-dimensional and support vector machine approach for automatic vehicle tracking and classification using a single camera

Abstract: Using video in traffic monitoring is one of the most active research domains in the computer vision community. TrafficMonitor, a system that employs a hybrid approach for automatic vehicle tracking and classification on highways using a simple stationary calibrated camera, is presented. The proposed system consists of three modules: vehicle detection, vehicle tracking, and vehicle classification. Moving vehicles are detected by an enhanced Gaussian mixture model background estimation algorithm. The design includes a technique to resolve the occlusion problem by using a combination of two-dimensional proximity tracking algorithm and the Kanade–Lucas–Tomasi feature tracking algorithm. The last module classifies the shapes identified into five vehicle categories: motorcycle, car, van, bus, and truck by using three-dimensional templates and an algorithm based on histogram of oriented gradients and the support vector machine classifier. Several experiments have been performed using both real and simulated traffic in order to validate the system. The experiments were conducted on GRAM-RTM dataset and a proper real video dataset which is made publicly available as part of this work.

Multiple objects tracking with HOGs matching in circular windows

Abstract: In recent years tracking applications with development of new technologies like smart TVs, Kinect, Google Glass and Oculus Rift become very important. When tracking uses a matching algorithm, a good prediction algorithm is required to reduce the search area for each object to be tracked as well as processing time. In this work, we analyze the performance of different tracking algorithms based on prediction and matching for a real-time tracking multiple objects. The used matching algorithm utilizes histograms of oriented gradients. It carries out matching in circular windows, and possesses rotation invariance and tolerance to viewpoint and scale changes. The proposed algorithm is implemented in a personal computer with GPU, and its performance is analyzed in terms of processing time in real scenarios. Such implementation takes advantage of current technologies and helps to process video sequences in real-time for tracking several objects at the same time.

High-Throughput Fixed-Point Object Detection on FPGAs

Abstract: The reliance on object or people detection is rapidly growing beyond surveillance to industrial and social applications. The Histogram of Oriented Gradients (HOG), one of the most popular detection algorithms, achieves a high detection accuracy but delivers just under 1 frame-per-second (fps) on a high-end CPU. In this paper we explore the FPGA implementation of HOG using reduced bit-width fixed-point representation to lessen the required area resources on the FPGA, increase the clock frequency and hence the throughput per device. We evaluate the detection accuracy of the fixed-point HOG by applying the state of the art computer vision object detection evaluation methodology and show it performs as well as the original floating-point code from OpenCV. We then show our implementation achieves a 37x higher throughput than a high-end CPU, 2.7x higher than a high-end GPU and 16x higher than the same implementation using floating-point on the same FPGA.

A novel rotation-invariant template matching based on HOG and AMDF for industrial laser cutting applications

Abstract: A new real-time rotation-invariant template matching is proposed for industrial laser cutting applications. The technique is based on Histogram of Oriented Gradients (HOG) algorithm to remove rotational angle before the template matching process. It exploits the HOG and the Average Magnitude Difference Function (AMDF) features for rotation-invariance. Since HOG features are robust against illumination effects, the proposed algorithm is suitable for harsh industrial environments. The final aim of this study is to devise a method to detect the contour of an object, which will automatically be cut from a sheet of material.