Histogram of Oriented Gradients with Cell Average Brightness for Human Detection

Abstract

A modification of the descriptor in a human detector using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is presented. The proposed modification requires inserting the values of average cell brightness resulting in the increase of the descriptor length from 3780 to 3908 values, but it is easy to compute and instantly gives ≈25% improvement of the miss rate at 10 -4 False Positives Per Window (FPPW). The modification has been tested on two versions of HOG-based descriptors: the classic Dalal-Triggs and the modified one, where, instead of spatial Gaussian masks for blocks, an additional central cell has been used. The proposed modification is suitable for hardware implementations of HOG-based detectors, enabling an increase of the detection accuracy or resignation from the use of some hardware-unfriendly operations, such as a spatial Gaussian mask. The results of testing its influence on the brightness changes of test images are also presented. The descriptor may be used in sensor networks equipped with hardware acceleration of image processing to detect humans in the images.

Classifying fabric defects with evolving Inception v3 by improved L2,1-norm regularized extreme learning machine

“…Local binary pattern (LBP) 32 extract features, and SVM is used for feature classification. HOG_SVM Histogram of oriented gradient (HOG) 33 extract features, and SVM is used for feature classification. number of all kinds of data equal and avoid the problem of class imbalance.…”

Clothing image classification algorithm based on convolutional neural network and optimized regularized extreme learning machine

“…The RUN is a new population-based optimization algorithm proposed by Ahmadianfar et al., 3 and is in view of the mathematical basis and idea of the Runge Kutta (RK) method. In this algorithm, the slope transformation logic calculated by the RK method is used as the global optimization search mechanism.…”

“…2 Deep learning is often applied to image processing, in which convolutional neural networks (CNNs) are often used to extract image features. Traditional methods focus mainly on extracting low-level features, for example, color, texture, and edge of clothing images, including mainly the histogram of oriented gradients (HOG), 3 local binary pattern (LBP), 4 gray-level co-occurrence matrix (GLCM), 5 and a Gabor filter. 6 Yamazaki 7 used a Gabor filter to abstract the traits of clothing pictures and assort a single clothing image.…”

Evaluating Sector Ring Histogram of Oriented Gradients Filter in Locating Humans Within Uav Images

“…To evaluate the performance of the algorithm, three indices Recall, Recall_neg, and Precision (Wójcikowski, 2016), were used which are computed using TP, TN, FP, and FN figures ( Table 1). The Recall index shows the ratio of the correctly identified positive windows over the total number of positive windows and is computed by:…”