Estimation of human orientation is considered a key configuration to study and understand human behaviours. There have been many works focusing on this. However, most of previous works are sensor-based technologies but visual-based technologies. In this paper, we proposed a method to estimate the orientation of human in a given image patch. We have observed the performance of a feature called H...

In this paper, an algorithm to track night pedestrians in real time is proposed. First, data is converted into a night L * a * b * color space, and then the L area is extracted. This data combined with image subtraction creates preprocessing data. Then, using the Cascade Histogram of Oriented Gradient (HOG) algorithm detects the pedestrian at night.

Face recognition has become an important issue in many applications such as security systems, credit card verification and criminal identification. The recently proposed shape descriptor, Pyramid Histogram of Oriented Gradients (PHOG) features, counts occurrences of gradient orientation in localized portions of an image and has been proved as an efficient tool for providing spatial distribution...

Automatic modulation recognition (AMR) of radar signals plays a critical role in electronic reconnaissance. Current AMR algorithms are mainly based on convolutional neural networks (CNN), which can learn the feature hierarchy by establishing high-level features from low-level features. However, for time–frequency analysis-based methods, distinct spectrum already reflect characteristics. Thus, t...

Automated rebar detection in images from groundpenetrating radar (GPR) is a challenging problem and difficult to perform in real-time as a result of relatively low contrast images and the size of the images. This paper presents a rebar localization algorithm, which can accurately locate the pixel locations of rebar within a GPR scan image. The proposed algorithm uses image classification and st...

The Histograms of Oriented Gradients (HOG) can produce good results in an image target recognition mission, but it requires the same size images for classification inputs. In response to this shortcoming, paper performs spatial pyramid segmentation on any size, gets pixel each block dynamically, and further calculates normalizes gradient oriented feature region layer. new is called Histogram Sp...