计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 210-214.

• 模式识别与图像处理 • 上一篇    下一篇

基于似物性和空时协方差特征的行人检测算法

刘春阳,吴泽民,胡磊,刘熹   

  1. 解放军理工大学通信工程学院 南京210007
  • 出版日期:2018-06-20 发布日期:2018-08-03
  • 作者简介:刘春阳(1993-),男,硕士,主要研究方向为计算机视觉、机器学习,E-mail:plaust_liu@163.com;吴泽民(1973-),男,教授,硕士生导师,主要研究方向为数据融合、视觉信息处理;胡 磊(1985-),男,讲师,主要研究方向为压缩感知、视频信息处理;刘 熹(1972-),男,副教授,主要研究方向为数据链信息处理。
  • 基金资助:
    国家自然科学基金(61501509)资助

Pedestrian Detection Based on Objectness and Sapce-Time Covariance Features

LIU Chun-yang,WU Ze-min,HU Lei, LIU Xi   

  1. College of Communications Engineering,PLAUST,Nanjing 210007,China
  • Online:2018-06-20 Published:2018-08-03

摘要: 针对行人检测算法中缺少空时信息融合、检测区域过大等问题,提出了一种联合似物性检测和基于通道协方差信息的改进算法。该算法首先对图像进行二进制梯度归一化的似物性检测,并形成行人检测候选区域,缩小检测区域;然后提取待测目标的空间和时间特征;最后基于协方差信息构造一种融合空时特征的检测器,以提高检测精度。在公开的数据集INRIA和Caltech上的实验结果表明:该算法的性能优于目前主流的行人检测算法。

关键词: 计算机视觉, 似物性, 协方差特征, 行人检测

Abstract: In order to solve the fusion of space-time information and excessive detection area in pedestrian detection,a pedestrian detection method was proposed based on objectness and space-time covariance features.Firstly,binarized normed gradients algorithm is used for a test image to get objectness evaluations,and a pedestrian detection candidate area is formed.Secondly,the spatial and temporal features are extracted.Finally,a space-time detector based on cova-riance information was proposed to improve the accuracy.Experimental results on the INRIA and Caltech demonstrate that the proposed method outperforms the state-of-art pedestrian detectors in accuracy.

Key words: Computer vision, Covariance features, Objectness, Pedestrian detection

中图分类号: 

  • TP391
[1]IKEUCHI K.Computer Vision:A Reference Guide[M].Sprin- ger Publishing Company,Incorporated,2014.
[2]苏松志,李绍滋,陈淑媛,等.行人检测技术综述[J].电子学报,2012,40(4):814-820.
[3]CAO J,PANG Y,LI X.Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry[J].IEEE Transactions on Image Processing,2016,25(12):5538-5551.
[4]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥Computer Vision and Pattern Recognition.IEEE,2014:580-587.
[5]HE K,ZHANG X,REN S,et al.Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(9):1904-1916.
[6]GIRSHICK R.Fast R-CNN[C]∥Proceedings of the 2015 IEEE International Conference on Computer Vision.Santiago,Chile:IEEE,2015:1440-1448.
[7]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[8]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection[C]∥Computer Vision and Pattern Recognition.IEEE,2016:779-788.
[9]ANGELOVA A,KRIZHEVSKY A,VANHOUCKE V,et al. Real-Time Pedestrian Detection with Deep Network Cascades[C]∥British Machine Vision Conference.2015:1-32.
[10]ZHANG S,BAUCKHAGE C,CREMERS A B.Informed Haar-Like Features Improve Pedestrian Detection[C]∥IEEEConfe-rence on Computer Vision and Pattern Recognition.2014:947-954.
[11]DOLLAR P,APPEL R,BELONGIE S,et al.Fast Feature Pyramids for Object Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,36(8):1532-1545.
[12]ZHANG S,BAUCKHAGE C,CREMERS A B.Informed Haar-Like Features Improve Pedestrian Detection[C]∥IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2014:947-954.
[13]NAM W,DOLLAR P,HAN J H.Local Decorrelation For Improved Pedestrian Detection[J].Advances in Neural Information Processing Systems,2014,1:424-432.
[14]PAISITKRIANGKRAI S,SHEN C,HENGEL A V D.Pedes- trian Detection with Spatially Pooled Features and Structured Ensemble Learning[J].IEEE Transactions on Pattern Analysis &Machine Intelligence,2016,38(6):1243.
[15]ZHANG S,BENENSON R,OMRAN M,et al.How Far are We from Solving Pedestrian Detection?[C]∥IEEE Conference on Computer Vision & Pattern Recognition.2016:1259-1267.
[16]ZHANG H,XU M,ZHUO L,et al.A novel optimization framework for salient object detection[J].The Visual Computer,2016,32(1):31-41.
[17]CHENG M M,ZHANG Z,LIN W Y,et al.BING:Binarized Normed Gradients for Objectness Estimation at 300fps[C]∥Computer Vision and Pattern Recognition.IEEE,2014:3286-3293.
[18]刘涛,吴泽民,姜青竹,等.基于似物性的快速视觉目标识别算法[J].计算机科学,2016,43(7):73-76.
[19]BROX T,BREGLER C,MALIK J.Large displacement optical flow[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009.(CVPR 2009).IEEE,2009:41-48.
[20]DOLLAR P,WOJEK C,SCHIELE B,et al.Pedestrian detec- tion:A benchmark[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2009(CVPR 2009).IEEE,2009:304-311.
[1] 张继凯, 李琦, 王月明, 吕晓琪.
基于单目RGB图像的三维手势跟踪算法综述
Survey of 3D Gesture Tracking Algorithms Based on Monocular RGB Images
计算机科学, 2022, 49(4): 174-187. https://doi.org/10.11896/jsjkx.210700084
[2] 谈馨悦, 何小海, 王正勇, 罗晓东, 卿粼波.
基于Transformer交叉注意力的文本生成图像技术
Text-to-Image Generation Technology Based on Transformer Cross Attention
计算机科学, 2022, 49(2): 107-115. https://doi.org/10.11896/jsjkx.210600085
[3] 干创, 吴桂兴, 詹庆原, 王鹏焜, 彭志磊.
基于骨架模态的多级门控图卷积动作识别网络
Multi-scale Gated Graph Convolutional Network for Skeleton-based Action Recognition
计算机科学, 2022, 49(1): 181-186. https://doi.org/10.11896/jsjkx.201100164
[4] 冯芙蓉, 张兆功.
目标轮廓检测技术新进展
Recent Advances for Object Contour Detection Technology
计算机科学, 2021, 48(6A): 1-9. https://doi.org/10.11896/jsjkx.201000044
[5] 张开华, 樊佳庆, 刘青山.
视觉目标跟踪十年研究进展
Advances on Visual Object Tracking in Past Decade
计算机科学, 2021, 48(3): 40-49. https://doi.org/10.11896/jsjkx.201100186
[6] 李亚泽, 刘宏哲.
基于相邻特征融合的目标检测
Object Detection Based on Neighbour Feature Fusion
计算机科学, 2021, 48(12): 264-268. https://doi.org/10.11896/jsjkx.201200196
[7] 程铭, 马佩, 何儒汉.
基于流形结构神经网络的服装图像集分类方法
Clothing Image Sets Classification Based on Manifold Structure Neural Network
计算机科学, 2021, 48(11A): 391-395. https://doi.org/10.11896/jsjkx.201200127
[8] 陈浩楠, 雷印杰, 王浩.
基于行列解耦采样的轻量车道线检测模型
Lightweight Lane Detection Model Based on Row-column Decoupled Sampling
计算机科学, 2021, 48(11A): 416-419. https://doi.org/10.11896/jsjkx.201100206
[9] 谢海平, 李高源, 杨海涛, 赵洪利.
超分辨率重构遥感图像分类研究
Classification Research of Remote Sensing Image Based on Super Resolution Reconstruction
计算机科学, 2021, 48(11A): 424-428. https://doi.org/10.11896/jsjkx.210300132
[10] 何鑫, 许娟, 金莹莹.
行为关联网络:完整的变化行为建模
Action-related Network:Towards Modeling Complete Changeable Action
计算机科学, 2020, 47(9): 123-128. https://doi.org/10.161896/jsjkx.190800101
[11] 李泽文, 李子铭, 费天禄, 王瑞琳, 谢在鹏.
基于残差生成对抗网络的人脸图像复原
Face Image Restoration Based on Residual Generative Adversarial Network
计算机科学, 2020, 47(6A): 230-236. https://doi.org/10.11896/JsJkx.190400118
[12] 张鹏, 宋一凡, 宗立波, 刘立波.
3D目标检测进展综述
Advances in 3D Object Detection:A Brief Survey
计算机科学, 2020, 47(4): 94-102. https://doi.org/10.11896/jsjkx.190400142
[13] 苗益, 赵增顺, 杨雨露, 徐宁, 杨皓然, 孙骞.
图像描述技术综述
Survey of Image Captioning Methods
计算机科学, 2020, 47(12): 149-160. https://doi.org/10.11896/jsjkx.200500039
[14] 李煌, 王晓莉, 项欣光.
基于文本三区域分割的场景文本检测方法
Scene Text Detection Based on Triple Segmentation
计算机科学, 2020, 47(11): 142-147. https://doi.org/10.11896/jsjkx.200800157
[15] 王晓媛, 张文涛.
屏幕防窃拍方法综述
Overview of Preventing Candid Photos Methods for Electronic Screens
计算机科学, 2019, 46(6A): 41-44.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!