位置：成果数据库 > 期刊 > 期刊详情页
基于视频流的复杂场景公车人头对象计数研究
  • 期刊名称：山东大学学报(哲学社会科学版)
  • 时间：2013.1.1
  • 页码：39-45
  • 分类：TP301[自动化与计算机技术—计算机系统结构;自动化与计算机技术—计算机科学与技术]
  • 作者机构：[1]南京航空航天大学计算机科学与技术学院,江苏南京210016
  • 相关基金：国家自然科学基金资助项目（61073112,61035003）;江苏省自然科学基金资助项目（BK2012793）
  • 相关项目：困难光照下基于结构化预测学习的层次化人脸可形变模型研究
作者： 张国华|谭晓阳|陈松灿|
关键词： 公车, 人头检测, 视频流分析, CENTRIST, LBP, bus , head detection , video analysis , CENTRIST, LBP
中文摘要：

以安装于公车内顶棚的单目摄像为研究对象，首先结合 CENTRIST （ census transform histogram）及LBP（local binary patterns）特征描述子对输入图像进行快速人头检测，然后结合视频流中包含的目标运动信息、被检测对象的外观信息、以及上车时间先验信息等来得到准确的人头数目。通过在现实场景下采集的真实公车视频流数据上的实验结果表明，该方法以接近实时的速度工作，在保证准确率的同时，能够有效减少复杂场景下人头计数中的误检率及漏检率。

英文摘要：

A novel method for head counting was presented based on the video streams coming from the single-camera installed on the roof of buses. The key idea of this method was based on the principal of count-by-detection method while taking account other sources of information available. First, a fast and effective head detection method was pro- posed using multi-modal feature sets, including CENTRIST and LBP. Second, a decision for a valid head count was made by fusing the information from head motion and the prior knowledge of the length of time needed for an event of interested. Extensive experiments on a series of video streams collected under real-life scenarios demonstrated the feasi- bility and effectiveness of the proposed method.

同期刊论文项目
基于云计算的海量数据挖掘
期刊论文 172 会议论文 96 获奖 10 专利 3 著作 7
困难光照下基于结构化预测学习的层次化人脸可形变模型研究
期刊论文 12 会议论文 4
同项目期刊论文
<span>Using Artificial Plant Optimization Algorithm to Solve Coverage Problem in WSN</span&
一种基于跨领域典型相关性分析的迁移学习方法<br />
A Hybrid P2P Approach to Service Discovery in the Cloud
<span>An Adaptive Approach to Learning Optimal Neighborhood Kernels</span>
<span>A Literature Survey on Robust and Efficient Eye Localization in Real-life Scenarios</
基于MapReduce的并行PLSA算法及在文本挖掘中的应用
<span>Simultaneous clustering and classification over cluster structure representation</spa
<span>Minimum cost attribute reduction in decision-theoretic rough set models</span>
Combining supervised and unsupervised models via unconstrained probabilistic embedding
<span>Graph optimization for dimensionality reduction with sparsity constraints</span>
Accelerating Multi-agent Reinforcement Learning by Equilibrium Transfer
<span>An Improved Artificial Plant Optimization Algorithm for Coverage Problem in WSN</span
<span>Maximum Volume Clustering: A New Discriminative Clustering Approach</span>
<span>Multi-objective Evolutionary Algorithms for filter Based Feature Selection in Classifica
<span>Online Selective Kernel-Based Temporal Difference Learning</span>
<span>Query-dependent cross-domain ranking in heterogeneous network</span>
Special Issue on Recent Advances on Swarm Intelligence: Theory and Applications
Using Gravitropism Artificial Plant Optimization Algorithm to Solve Toy Model of Protein Folding
Using Splitting Artificial Plant Optimization Algorithm to Solve Toy Model of Protein Folding
三维网格空间上的自组装模型
Cognitive Cycle in Mind Model CAM
A Mind Model CAM in Intelligence Science
基于Hadoop 云平台的并行数据挖掘方法
Hybrid Designing of a Neural System by Combining Fuzzy Logical Framework and PSVM for Visual Haze-Fr
<span>Multimodal Sparse Representation-Based Classification for Lung Needle Biopsy Images</
<span>TRASMIL: A local anomaly detection framework based on trajectory segmentation and multi-
<span>On an optimization representation of decision-theoretic rough set model</span>
<span>Visual Word Coding Based on Difference Maximization</span>
<span>Adaptive support framework for wisdom web of things</span>
<span>Safety-Aware Semi-Supervised Classification</span>
<span>Co-metric: A Metric Learning Algorithm for Data with Multiple Views</span>
<span>Analysis of Non-Local Euclidean Medians and Its Improvement</span>
基于聚度的PSO参数分析
联机核模糊C均值聚类方法
<span>Image annotation by modeling Supporting Region Graph</span>
计算文本的情感描述值的算法
Rete算法<span>: </span>研究现状与挑战
三维网格模型的边界性度量方法
STRUCTURALLY ENHANCED INCREMENTAL NEURAL LEARNING FOR IMAGE CLASSIFICATION WITH SUBGRAPH EXTRACTION
基于人脸图像的年龄估计
Computational Cognitive Models for Brain-Machine Collaborations
Structural regularized support vector machine: a framework for structural large margin classifier
<span>A novel multi-view learning developed from single-view patterns</span>
Sparse non-negative tensor factorization using columnwise coordinate descent
混合概率典型相关性分析<br />
<div> 基于威胁传播采样的复杂信息系统风险评估 </div>
Foundations of Intelligence Science
<span>Support Vector Machine with Mixture of Kernels for Automatic Image Annotation</span&g
Video Behavior Analysis Using Topic Models and Rough Sets
<span>Image Retrieval Based on Augmented Relational Graph Representation</span>
<span>Soft large margin clustering</span>
特征采样和特征融合的子图像人脸识别方法
Social Emotional Optimization Algorithm with Gaussian Distribution for Optimal Coverage Problem
大数据下的机器学习算法综述
基于动态描述逻辑的语义Web服务组合
中国数据挖掘研究进展
基于特征融合的多模态身份识别方法研究
颌面战创伤救治智能决策支持系统的构建(下)
基于社区发现的多主体信任评估
面向服务的云数据挖掘引擎的研究
A Cognitive Model for Multi-Agent Collaboration
Multi-agent Reinforcement Learning with Unshared Value Functions
基于<span>LDA</span>主题模型的社会网络链接预测
利用图像类标信息的自调式字典学习方法
一种基于耦合对象相似度的项目推荐算法
不完美信息扩展式博弈中在线虚拟遗憾最小化
基于数据共性的鲁棒特征表示
一种基于深度信念网络的二代身份证异构人脸核实算法
A Novel Multi-view Classifier based on Nystrom Approximation
SCIHTBB: Sparsity constrained iterative hard thresholding with Barzilai–Borwein step size
<span>New semi-supervised classification based on modified clustering assumption</span>
XCSc: A Novel Approach of Clustering with Extended Classifier System
New trends on bio-inspired computation
A Family of Dynamic Description Logics for Representing and Reasoning About Actions
基于Hadoop平台的海量文本分类的并行化
一种基于MapReduce的频繁闭项集挖掘算法
A parallel incremental extreme SVM classifier
一种基于语义轨迹的事件规则学习算法
权衡熵和相关度的自动摘要技术研究
A Posteriori Approach for Community Detection
Parallel Web Mining System Based on Cloud Platform
D3L_(ccy)的属性及分布式Tableaux推理算法的研究
<span>Parallel extreme learning machine for regression based on MapReduce</span>
基于三支决策粗糙集的视频异常行为检测
一种自适应求三枝决策中决策阈值的算法
多模态张量数据挖掘算法及应用
LDA-CRF:一种基于概率图模型的目标检测方法
Support Vector Machine incorporated with feature discrimination
A structurally motivated framework for discriminant analysis
Newman and Watts Small World Social Emotional Optimization Algorithm with WSN
Exploiting relevance, coverage, and novelty for query-focused multi-document summarization
<span>Transductive cost-sensitive lung cancer image classification</span>
<span>Orthogonality-based Label Correction in Multi-class Classification</span>
基于相容粒度空间模型的自适应图像语义分类方法
基于Hadoop云平台的并行数据挖掘方法
Eyes Closeness Detection from Still Images with Multi-scale Histograms of Principal Oriented Gradien
代价敏感分类策略在肺癌细胞识别诊断中的应用
可判定的时序动态描述逻辑
RCSM:多主体系统中的可靠关键子系统模型
mPadal: a joint local-and-global multi-view feature selection method for activity recognition
一种基于子空间学习的图像语义哈希索引算法
基于分布相似度迁移的关键路由设备检测
SSXCS：半监督学习分类系统
一种求三支决策阈值的模拟退火算法
基于LDA主题模型的社会网络链接预测
基于核方法的连续动作Actor-Critic学习
Two-dimensional bar code out-of-focus deblurring via the Increment Constrained Least Squares filter
A literature survey on robust and efficient eye localization in real-life scenarios
Comparative study among three strategies of incorporating spatial structures to ordinal image regres
基于LARK特征提取的人脸检测方法
改进的三维人脸稠密对齐方法
SVM及其鲁棒性研究
可形变人脸模型研究进展综述
Part-Based Pose Estimation with Local and Non-Local Contextual Information
联机局部自适应模糊C均值聚类算法
离散线性一致性算法噪声问题研究
线性均方一致性问题的偏差估计
基于弱匹配概率典型相关性分析的图像自动标注
一种基于子空间学习的图像语义哈希索引方法
视频人脸识别中判别性联合多流形分析
基于多示例学习的异常行为检测方法
一种基于跨领域典型相关性分析的迁移学习方法
基于语义轨迹的视频事件探测
基于维基百科和条件随机场的领域主题词抽取方法
基于动态描述逻辑的Web自动化服务组合
支持链式桥规则的分布式动态描述逻辑
链式桥规则导致的D3L知识传播及推理
基于内容图像检索中的优化鉴别特征
基于大间隔编码的空间非负矩阵分解
基于流形的约束局部模型拟合
Support vector machine with mixture of kernels for automatic image annotation
Fusing PLSA model and Markov random fields for automatic image annotation
LDA—CRF：一种基于概率图模型的目标检测方法
A visual awareness pathway in cognitive model ABGP
元数据存储库系统中违背良格式约束潜在操作的推理