Method and apparatus for performing object detection
    1.
    发明授权
    Method and apparatus for performing object detection 有权
    用于执行物体检测的方法和装置

    公开(公告)号:US07697752B2

    公开(公告)日:2010-04-13

    申请号:US11312219

    申请日:2005-12-20

    IPC分类号: G06K9/62

    CPC分类号: G06K9/00248

    摘要: An object detection algorithm that generates a two-layer Gaussian Mixture Model (GMM) during a training session, and subsequent to the training session, uses the two-layer GMM to perform face detection. No labeling of local features is needed. The only input that is provided by a user is the setting of a few global parameters for the image being captured during the training session, such as, for example, the person's facial pose.

    摘要翻译: 在训练阶段和训练阶段之后生成双层高斯混合模型(GMM)的对象检测算法使用双层GMM进行人脸检测。 不需要标记局部特征。 由用户提供的唯一输入是在训练会话期间为例如人的面部姿势捕获的图像的几个全局参数的设置。

    METHOD AND APPARATUS FOR VIDEO CLIP SEARCHING AND MINING
    2.
    发明申请
    METHOD AND APPARATUS FOR VIDEO CLIP SEARCHING AND MINING 审中-公开
    视频剪辑搜索和采矿的方法和装置

    公开(公告)号:US20080226173A1

    公开(公告)日:2008-09-18

    申请号:US11685720

    申请日:2007-03-13

    IPC分类号: G06K9/46

    摘要: A method, apparatus, and electronic device for searching for repetitive video content are disclosed. A memory may store a set of video data. A processor may match a premier query window to a trellis match video window of the set of video data. The processor may compare a successive query window to a successive trellis match video window. The processor may disregard the trellis match video window if the successive trellis match video window does not match the successive query window.

    摘要翻译: 公开了一种用于搜索重复视频内容的方法,装置和电子设备。 存储器可以存储一组视频数据。 处理器可将首要查询窗口与视频数据集合的网格匹配视频窗口相匹配。 处理器可以将连续查询窗口与连续网格匹配视频窗口进行比较。 如果连续网格匹配视频窗口与连续查询窗口不匹配,则处理器可以忽略网格匹配视频窗口。

    Method and apparatus for performing object detection
    3.
    发明申请
    Method and apparatus for performing object detection 有权
    用于执行物体检测的方法和装置

    公开(公告)号:US20070140550A1

    公开(公告)日:2007-06-21

    申请号:US11312219

    申请日:2005-12-20

    IPC分类号: G06K9/62 G06K9/46

    CPC分类号: G06K9/00248

    摘要: An object detection algorithm that generates a two-layer Gaussian Mixture Model (GMM) during a training session, and subsequent to the training session, uses the two-layer GMM to perform face detection. No labeling of local features is needed. The only input that is provided by a user is the setting of a few global parameters for the image being captured during the training session, such as, for example, the person's facial pose.

    摘要翻译: 在训练阶段和训练阶段之后生成双层高斯混合模型(GMM)的对象检测算法使用双层GMM进行人脸检测。 不需要标记局部特征。 由用户提供的唯一输入是在训练会话期间为例如人的面部姿势捕获的图像的几个全局参数的设置。

    METHOD AND APPARATUS FOR MULTICASTING WITHIN A WIRELESS COMMUNICATION NETWORK
    4.
    发明申请
    METHOD AND APPARATUS FOR MULTICASTING WITHIN A WIRELESS COMMUNICATION NETWORK 审中-公开
    用于在无线通信网络中进行组播的方法和装置

    公开(公告)号:US20090323575A1

    公开(公告)日:2009-12-31

    申请号:US12147809

    申请日:2008-06-27

    IPC分类号: H04H20/71

    摘要: A number of uplink transmissions from multiple remote devices is received. The remote devices correspond to a single network node, and each of the uplink transmissions corresponds to a request for content. A subset of remote devices whose uplink transmissions correspond to requests for common content is identified and a Quality of Service (QoS) level corresponding to the number of remote devices in the identified subset is determined. The common content is transmitted to the single network node at the determined QoS level.

    摘要翻译: 接收来自多个远程设备的多个上行链路传输。 远程设备对应于单个网络节点,并且每个上行链路传输对应于对内容的请求。 识别其上行链路传输对应于公共内容的请求的远程设备的子集,并且确定与所识别的子集中的远程设备的数量相对应的服务质量(QoS)级别。 公共内容以确定的QoS级别发送到单个网络节点。

    Video encoding system and method for providing content adaptive rate control
    5.
    发明申请
    Video encoding system and method for providing content adaptive rate control 审中-公开
    用于提供内容自适应速率控制的视频编码系统和方法

    公开(公告)号:US20070036227A1

    公开(公告)日:2007-02-15

    申请号:US11204212

    申请日:2005-08-15

    IPC分类号: H04N7/12

    摘要: A video encoding system (200) provides content adaptive rate control that includes a visual analyzer (208) utilizing at least one visual analysis tool for processing a video frame to provide visual information describing the video frame. An encoder (204) generates encoding status information relating to the video frame being processed. A rate controller (206) is responsive to the encoding status information generated by the encoder (204) and the visual information generated by the visual analyzer (208) to generate a rate control adjustment signal. The encoder (204) is responsive to the rate control adjustment signal for encoding the video frame.

    摘要翻译: 视频编码系统(200)提供内容自适应速率控制,其包括使用至少一个视觉分析工具的视觉分析器(208),用于处理视频帧以提供描述视频帧的视觉信息。 编码器(204)生成与被处理的视频帧有关的编码状态信息。 速率控制器(206)响应于由编码器(204)产生的编码状态信息和由视觉分析器(208)生成的视觉信息,以产生速率控制调整信号。 编码器(204)响应用于编码视频帧的速率控制调整信号。

    Method for fuzzy logic rule based multimedia information retrival with text and perceptual features
    7.
    发明授权
    Method for fuzzy logic rule based multimedia information retrival with text and perceptual features 失效
    基于模糊逻辑规则的多媒体信息检索方法,具有文本和感知特征

    公开(公告)号:US07065521B2

    公开(公告)日:2006-06-20

    申请号:US10383897

    申请日:2003-03-07

    IPC分类号: G06F17/30

    摘要: A search system (200) for a database (224) including records having a multiple disparate types of media is provided. The search system supports queries, that include different types of search criteria, including content based retrieval search criteria. A fuzzy logic method (400) is provided for effectively combining the results of different types of search criteria. The fuzzy logic method also allows confidence levels entered by the user for search criteria to be considered in combining results. Retrieval relevance values for documents for at least some search criteria are used in the fuzzy logic method. For content based image retrieval searches, the retrieval relevance values are computed by mapping a distance between quantitative characterizations of a search basis image, and other images into a finite range.

    摘要翻译: 提供了包括具有多种不同类型的媒体的记录的数据库(224)的搜索系统(200)。 搜索系统支持查询,包括不同类型的搜索条件,包括基于内容的检索搜索条件。 提供了一种模糊逻辑方法(400),用于有效地组合不同类型的搜索标准的结果。 模糊逻辑方法还允许在组合结果时考虑用户输入的搜索条件的置信度。 在模糊逻辑方法中使用至少一些搜索条件的文档的检索相关性值。 对于基于内容的图像检索搜索,通过将搜索基础图像和其他图像的定量表征之间的距离映射到有限范围来计算检索相关性值。

    Method and apparatus for multimedia queue management
    8.
    发明授权
    Method and apparatus for multimedia queue management 有权
    多媒体队列管理方法与装置

    公开(公告)号:US09246830B2

    公开(公告)日:2016-01-26

    申请号:US13253654

    申请日:2011-10-05

    摘要: Methods and systems for a multimedia queue management solution that maintaining graceful Quality of Experience (QoE) degradation are provided. The method selects a frame from all weighted queues based on a gradient function indicating a network performance rate change and a distortion rate caused by the frame and its related frames in the queue, and dropping the selected frame and all its related frames, and continues to drop similarly chosen frame until a network performance rate change caused by the dropping frame and its related frames meets a predetermined performance metric. A frame gradient is a distortion rate divided by a network performance rate change caused by the frame and its related frames, and a distortion rate is based on a sum of each individual frame distortion rate when the frame and its related frames are replaced by some other frames derived from remaining frames based on a replacement method.

    摘要翻译: 提供了维护优雅的体验质量(QoE)降级的多媒体队列管理解决方案和方法。 该方法基于指示网络性能速率变化的梯度函数和由帧及其相关帧在队列中引起的失真率,并且丢弃所选帧及其所有相关帧,从所有加权队列中选择一帧,并继续 丢弃类似地选择的帧,直到由丢弃帧及其相关帧引起的网络性能速率变化满足预定的性能度量。 帧梯度是由帧及其相关帧引起的网络性能速率变化除以失真率,并且当帧和其相关帧被其他一些替换时,失真率基于每个单独的帧失真率的和 基于替换方法从剩余帧导出的帧。

    One-piece core manufacturing method for swing bolster and sideframe of lorry
    10.
    发明授权
    One-piece core manufacturing method for swing bolster and sideframe of lorry 失效
    一体式摇篮和侧架的核心制造方法

    公开(公告)号:US08151861B2

    公开(公告)日:2012-04-10

    申请号:US12596148

    申请日:2008-03-06

    IPC分类号: B22C9/10

    摘要: A one-piece core-making technique used in producing railway truck bolsters and side frames, which includes the following steps: 1. After scraping the top of a core box, applying a shaped top mould (11), which is precisely located, from top to bottom. 2. Press or slightly hit the top mould (11) to make sure the top mould covers/caps the scraping surface. 3. Keep pressing to make sure that the flat scraping surface was pressed to a required curved shape, like the shape of the top mould (11). 4. Last, it will become a one-piece core with a partially integrated inner cavity section. The one-piece core made by this technique has a smooth surface. This technique also can improve the internal quality of the product and ease work intensity.

    摘要翻译: 一种用于生产铁路货车枕头和侧框架的一体式制芯技术,包括以下步骤:1.在将芯盒的顶部刮下后,将精确定位的成形顶模(11)从 从上到下。 2.按压或轻轻敲击上模(11),以确保顶模覆盖/盖上刮削表面。 3.按压,确保平面刮面按压到所需的弯曲形状,如顶模(11)的形状。 最后,它将成为具有部分集成的内腔部分的单件式核心。 这种技术制成的一体式芯片表面光滑。 这种技术也可以提高产品的内部质量,减轻工作强度。