Histogram of oriented gradients for human detection in video

Abstract

Currently, Computer Vision (CV) is one of the most popular research topics in the world. This is because it can support the human daily life. Moreover, CV can also apply to various theories and researches. Human Detection is one of the most popular research topics in Computer Vision. In this paper, we present a study of technique for human detection from video, which is the Histograms of Oriented Gradients or HOG by developing a piece of application to import and detect the human from the video. We use the HOG Algorithm to analyze every frame from the video to find and count people. After analyzing video from starting to the end, the program generate histogram to show the number of detected people versus playing period of the video. As a result, the expected results are obtained, including the detection of people in the video and the histogram generation to show the appearance of human detected in the video file.