期刊导航

论文摘要

一种改进的梯度直方图远红外行人检测方法

A Far Infrared Detection Recognition Description Method Based On Improved Gradient Histogram

作者:周红志(阜阳师范学院信息工程学院);刘祺(华南理工大学计算机科学与工程学院)

Author:ZHOU Hong-Zhi(College of Information Engineering, Fuyang Teachers' College);LIU Qi(School of Computer and Engineering, South China University of Technology)

收稿日期:2015-09-10          年卷(期)页码:2016,53(5):1018-1026

期刊名称:四川大学学报: 自然科学版

Journal Name:Journal of Sichuan University (Natural Science Edition)

关键字:行人检测;ROIs ;像素梯度;双阀值;梯度直方图;SVM算法

Key words:Pedestrian detection ; ROIs ;Pixel gradient ; Dual Threshold ; Gradient histogram ; SVM algorithm

基金项目:国家自然科学基金(61171141);安徽省自然科学研究项目(2015FXTZK03)

中文摘要

针对远红外行人检测实时性和鲁棒性仍然极具挑战性的问题,本文从感兴趣区域(Regions of Interests 简称ROIs)提取的角度出发,提出一种基于像素梯度的垂直投影方法。该方法利用图像梯度信息对可能包含行人的竖直带状图像区域进行初定位,在得到的图像里面通过局部双阈值图像分割算法形成相对可靠的ROIs。在行人识别过程中,结合基于金字塔熵加权的梯度直方图方法和全局信息对远红外行人进行描述,同时辅助以支持向量机(Support Vector Machines SVM)算法来完成整个识别过程。实验表明该方法能够提高ROIs提取阶段的搜索效率,并能够抑制部分仅包含背景目标的候选区域。

英文摘要

For the real-time and robustness of far-infrared pedestrian detection remains a very challenging problem, the paper presents a vertical gradient projection method based on the pixels from ROIs (Regions of Interest) extracted angle. This method utilizes the image gradient information to conduct early positioning for the vertical banded image area which may contain pedestrians, then forms relatively reliable ROIs by partial dual-threshold image segmentation algorithm inside obtained image. In the pedestrian recognition process, it combines global information and gradient histogram method based on pyramid weighted entropy to describe the far-infrared pedestrian, at the same time assist in SVM algorithm to complete the identification process. Experiments show that the method can improve the search efficiency of ROIs extraction stage, and suppress portion of the candidate region included in the background target.

关闭

Copyright © 2020四川大学期刊社 版权所有.

地址:成都市一环路南一段24号

邮编:610065