公开(公告)号：US20120290526A1

公开(公告)日：2012-11-15

申请号：US13219345

申请日：2011-08-26

申请人： Rohit Kumar Gupta ,  Sandeep Gattani ,  Aniruddha Sinha ,  Ayan Chaki ,  Arpan Pal

发明人： Rohit Kumar Gupta ,  Sandeep Gattani ,  Aniruddha Sinha ,  Ayan Chaki ,  Arpan Pal

IPC分类号： G06N5/02

CPC分类号： G06N7/00 ,  G06K9/6293 ,  G06N99/005

摘要： A computer-based system and method to improve the multimodal fusion output at the decision level is disclosed. The method proposes computation of a confidence weighted measure for the individual score values obtained for each modality and fuse these new updated scores to get the final decision. These confidence weights are the performance parameters (measured in terms of F-measure) during the offline training step. The process significantly increases the accuracy of the multimodal system.

摘要翻译： 公开了一种基于计算机的系统和方法，用于在决策级别改进多模态融合输出。 该方法提出了对于每个模态获得的各个得分值的置信度加权度量的计算，并且将这些新的更新得分融合以获得最终决定。 这些置信度权重是在离线训练步骤期间的性能参数（以F度测量）。 该过程显着提高了多模态系统的准确性。

公开(公告)号：US08700557B2

公开(公告)日：2014-04-15

申请号：US13219345

申请日：2011-08-26

申请人： Rohit Kumar Gupta ,  Sandeep Gattani ,  Aniruddha Sinha ,  Ayan Chaki ,  Arpan Pal

发明人： Rohit Kumar Gupta ,  Sandeep Gattani ,  Aniruddha Sinha ,  Ayan Chaki ,  Arpan Pal

IPC分类号： G06N5/02

CPC分类号： G06N7/00 ,  G06K9/6293 ,  G06N99/005

摘要： A computer-based system and method to improve the multimodal fusion output at the decision level is disclosed. The method proposes computation of a confidence weighted measure for the individual score values obtained for each modality and fuse these new updated scores to get the final decision. These confidence weights are the performance parameters (measured in terms of F-measure) during the offline training step. The process significantly increases the accuracy of the multimodal system.

摘要翻译： 公开了一种基于计算机的系统和方法，用于在决策级别改进多模态融合输出。 该方法提出了对于每个模态获得的各个得分值的置信度加权度量的计算，并且将这些新的更新得分融合以获得最终决定。 这些置信度权重是在离线训练步骤期间的性能参数（以F度测量）。 该过程显着提高了多模态系统的准确性。

公开(公告)号：US09001199B2

公开(公告)日：2015-04-07

申请号：US13160743

申请日：2011-06-15

申请人： Aniruddha Sinha ,  Rohit Gupta ,  Ayan Chaki ,  Arpan Pal

发明人： Aniruddha Sinha ,  Rohit Gupta ,  Ayan Chaki ,  Arpan Pal

IPC分类号： H04N9/47 ,  G06K9/00

CPC分类号： G06K9/00369

摘要： A system for adaptive learning based human detection for channel input of captured human image signals, the system comprising: a sensor for tracking real-time images of an environment of interest; a feature extraction and classifiers generation processor for extracting a plurality of features and classifying the features associated with time-space descriptors of image comprising background modeling, Histogram of Oriented Gradients (HOG) and Haar like wavelet; a processor configured to process extracted feature classifiers associated with plurality of real-time images; combine the plurality of feature classifiers of time-space descriptors; evaluate a linear probability of human detection based on a predetermined threshold value of the feature classifiers in a time window having at least one image frame; a counter for counting the number of humans in the real-time images; and a transmission device configured to send the final human detection decision and number thereof to a storage device.

摘要翻译： 一种用于基于捕获的人类图像信号的信道输入的用于自适应学习的人类检测的系统，所述系统包括：用于跟踪感兴趣的环境的实时图像的传感器; 特征提取和分类器生成处理器，用于提取多个特征并对与图像的时间 - 空间描述符相关联的特征进行分类，该图像包括背景建模，定向梯度（HOG）直方图和哈尔像小波; 处理器，被配置为处理与多个实时图像相关联的提取的特征分类器; 组合时空描述符的多个要素分类器; 基于具有至少一个图像帧的时间窗中的特征分类器的预定阈值来评估人类检测的线性概率; 用于计数实时图像中的人数的计数器; 以及发送装置，被配置为将最终的人类检测决定及其数量发送到存储装置。

公开(公告)号：US20120274755A1

公开(公告)日：2012-11-01

申请号：US13160743

申请日：2011-06-15

申请人： Aniruddha Sinha ,  Rohit Gupta ,  Ayan Chaki ,  Arpan Pal

发明人： Aniruddha Sinha ,  Rohit Gupta ,  Ayan Chaki ,  Arpan Pal

IPC分类号： G06K9/00 ,  H04N7/18

CPC分类号： G06K9/00369

摘要： A system for adaptive learning based human detection for channel input of captured human image signals, the system comprising: a sensor for tracking real-time images of an environment of interest; a feature extraction and classifiers generation processor for extracting a plurality of features and classifying the features associated with time-space descriptors of image comprising background modeling, Histogram of Oriented Gradients (HOG) and Haar like wavelet; a processor configured to process extracted feature classifiers associated with plurality of real-time images; combine the plurality of feature classifiers of time-space descriptors; evaluate a linear probability of human detection based on a predetermined threshold value of the feature classifiers in a time window having at least one image frame; a counter for counting the number of humans in the real-time images; and a transmission device configured to send the final human detection decision and number thereof to a storage device.

摘要翻译： 一种用于基于捕获的人类图像信号的信道输入的用于自适应学习的人类检测的系统，所述系统包括：用于跟踪感兴趣的环境的实时图像的传感器; 特征提取和分类器生成处理器，用于提取多个特征并对与图像的时间 - 空间描述符相关联的特征进行分类，该图像包括背景建模，定向梯度（HOG）直方图和哈尔像小波; 处理器，被配置为处理与多个实时图像相关联的提取的特征分类器; 组合时空描述符的多个要素分类器; 基于具有至少一个图像帧的时间窗中的特征分类器的预定阈值来评估人类检测的线性概率; 用于计数实时图像中的人数的计数器; 以及发送装置，被配置为将最终的人类检测决定及其数量发送到存储装置。