| 基于改进的粒子滤波的红外视频行人跟踪 |
| |
| 引用本文： | 张绍明,胡建平,施扬. 基于改进的粒子滤波的红外视频行人跟踪[J]. 同济大学学报(自然科学版), 2015, 43(12): 1883-1887 |
| |
| 作者姓名： | 张绍明 胡建平 施扬 |
| |
| 作者单位： | 同济大学 测绘与地理信息学院，上海 200092,同济大学 测绘与地理信息学院，上海 200092,同济大学 测绘与地理信息学院，上海 200092 |
| |
| 基金项目： | 国家自然科学基金(41301361、41171327)，国家“九七三”重点基础研究发展计划（2012CB719903），国家高分辨率对地观测系统重大专项（07-Y30B10-9001-14/16），教育部高等学校博士学科点专项科研基金（20120072120057） |
| |
| 摘 要： | 提出了一种基于改进的粒子滤波的红外视频行人跟踪算法,实现了在传统粒子滤波算法的框架下,使用有向梯度直方图(histograms of oriented gradients,HOG)来描述跟踪目标的特征.算法在粒子权值和相似度计算中使用HOG,替代现有的颜色空间欧式距离测度,克服了红外视频中颜色信息缺失的困难.试验表明,与传统的粒子滤波算法相比,本文算法更能准确有效地跟踪复杂场景中的行人,提高了跟踪的鲁棒性.
|
| 关 键 词： | 红外视频 粒子滤波 有向梯度直方图(HOG) 行人跟踪 |
| 收稿时间： | 2014-06-05 |
| 修稿时间： | 2015-11-09 |
Pedestrian Tracking in Infrared Video Based on Improved Particle Filter |
| |
| ZHANG Shaoming,HU Jianping and SHI Yang. Pedestrian Tracking in Infrared Video Based on Improved Particle Filter[J]. Journal of Tongji University(Natural Science), 2015, 43(12): 1883-1887 |
| |
| Authors: | ZHANG Shaoming HU Jianping SHI Yang |
| |
| Affiliation: | College of Surveying and Geo Informatics, Tongji University, Shanghai, 200092, China,College of Surveying and Geo Informatics, Tongji University, Shanghai, 200092, China and College of Surveying and Geo Informatics, Tongji University, Shanghai, 200092, China |
| |
| Abstract: | An improved particle filter method for pedestrian tracking in infrared video is proposed. The objects are described in the scheme of particle filter using Histogram of Oriented Gradients(HOG). Instead of the Euclidean distance in color space, the HOG is employed to describe the similarity and compute the weights of the samples, which solves the issue of lack of color information for infrared video. Experimental results show that the method is more accurate and effective tracking of moving targets in complex scenes than traditional particle filter algorithm in infrared video. |
| |
| Keywords: | infrared video particle filter histogram of oriented gradients(HOG) pedestrian tracking |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《同济大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《同济大学学报(自然科学版)》下载全文 |
|
