知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

44 records (took 0.035 seconds)

    Automatic scene calibration method for video analytics
    21.
    发明授权
    Automatic scene calibration method for video analytics 有权

    公开(公告)号：US10372970B2

    公开(公告)日：2019-08-06

    申请号：US15266747

    申请日：2016-09-15

    Applicant: QUALCOMM Incorporated

    Inventor： Lei Wang ,  Dashan Gao ,  Lei Ma ,  Chinchuan Chiu

    IPC: G06T7/00 ,  G06K9/00 ,  H04N13/261 ,  G06T7/80 ,  G06T7/70 ,  G06T7/73 ,  G06T7/246

    Abstract: To determine real-world information about objects moving in a scene, the camera capturing the scene is typically calibrated to the scene. Automatic scene calibration can be accomplished using people that are found moving about in the scene. During a calibration period, a video content analysis system processing video frames from a camera can identify blobs that are associated with people. Using an estimated height of a typical person, the video content analysis system can use the location of the person's head and feet to determine a mapping between the person's location in the 2-D video frame and the person's location in the 3-D real world. This mapping can be used to determine a cost for estimated extrinsic parameters for the camera. Using a hierarchical global estimation mechanism, the video content analysis system can determine the estimated extrinsic parameters with the lowest cost.

    Systems and methods for image processing in a deep convolution network
    26.
    发明授权
    Systems and methods for image processing in a deep convolution network 有权
    深卷积网络中图像处理的系统和方法

    公开(公告)号：US09582726B2

    公开(公告)日：2017-02-28

    申请号：US14749387

    申请日：2015-06-24

    Applicant: QUALCOMM Incorporated

    Inventor： Yunke Pan ,  Dashan Gao ,  Xin Zhong ,  Shuxue Quan

    IPC: G06K9/00 ,  G06T5/20 ,  G06T11/60

    CPC classification number: G06K9/00986 ,  G06K9/4623 ,  G06K9/6273 ,  G06N3/0454 ,  G06T5/20

    Abstract: A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.

    Abstract translation: 描述由电子设备执行的方法。 该方法包括交织多个输入图像通道以产生交织的多通道输入。 该方法还包括将交织的多通道输入加载到单指令多数据（SIMD）处理器。 该方法还包括用交错多通道输入与多通道滤波器进行卷积。

    Systems and methods for object classification, object detection and memory management
    27.
    发明授权
    Systems and methods for object classification, object detection and memory management 有权
    对象分类，对象检测和内存管理的系统和方法

    公开(公告)号：US09489598B2

    公开(公告)日：2016-11-08

    申请号：US14609104

    申请日：2015-01-29

    Applicant: QUALCOMM Incorporated

    Inventor： Dashan Gao ,  Yang Yang ,  Xin Zhong ,  Yingyong Qi

    IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  G06N7/00 ,  G06N99/00

    CPC classification number: G06K9/6269 ,  G06K9/4604 ,  G06N7/00 ,  G06N99/005

    Abstract: A method for object classification by an electronic device is described. The method includes obtaining an image frame that includes an object. The method also includes determining samples from the image frame. Each of the samples represents a multidimensional feature vector. The method further includes adding the samples to a training set for the image frame. The method additionally includes pruning one or more samples from the training set to produce a pruned training set. One or more non-support vector negative samples are pruned first. One or more non-support vector positive samples are pruned second if necessary to avoid exceeding a sample number threshold. One or more support vector samples are pruned third if necessary to avoid exceeding the sample number threshold. The method also includes updating classifier model weights based on the pruned training set.

    Abstract translation: 描述了一种通过电子设备进行物体分类的方法。 该方法包括获得包括对象的图像帧。 该方法还包括从图像帧确定样本。 每个样本表示多维特征向量。 该方法还包括将样本添加到图像帧的训练集合中。 该方法还包括从训练集修剪一个或多个样本以产生修剪的训练集。 首先修剪一个或多个非支持向量负样本。 如果必要，一个或多个非支持向量阳性样本被修剪，以避免超过样本数阈值。 如果需要，一个或多个支持向量样本被修剪为第三，以避免超过样本数阈值。 该方法还包括基于修剪的训练集更新分类器模型权重。

    SYSTEMS AND METHODS FOR OBJECT TRACKING
    28.
    发明申请
    SYSTEMS AND METHODS FOR OBJECT TRACKING 有权
    用于对象跟踪的系统和方法

    公开(公告)号：US20160267325A1

    公开(公告)日：2016-09-15

    申请号：US14792436

    申请日：2015-07-06

    Applicant: QUALCOMM Incorporated

    Inventor： Sairam Sundaresan ,  Dashan Gao ,  Xin Zhong ,  Yingyong Qi

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/52

    CPC classification number: G06K9/00624 ,  G06K9/46 ,  G06K9/52 ,  G06K2009/4666 ,  G06T7/215 ,  G06T2207/10016 ,  G06T2210/12

    Abstract: A method performed by an electronic device is described. The method includes determining a local motion pattern by determining a set of local motion vectors within a region of interest between a previous frame and a current frame. The method also includes determining a global motion pattern by determining a set of global motion vectors between the previous frame and the current frame. The method further includes calculating a separation metric based on the local motion pattern and the global motion pattern. The separation metric indicates a motion difference between the local motion pattern and the global motion pattern. The method additionally includes tracking an object based on the separation metric.

    Abstract translation: 描述由电子设备执行的方法。 该方法包括通过确定在先前帧和当前帧之间的感兴趣区域内的一组局部运动矢量来确定局部运动模式。 该方法还包括通过确定前一帧和当前帧之间的一组全局运动矢量来确定全局运动模式。 该方法还包括基于局部运动模式和全局运动模式来计算分离度量。 分离度量指示局部运动模式和全局运动模式之间的运动差异。 该方法还包括基于分离度量跟踪对象。

    SYSTEMS AND METHODS FOR IMAGE SCANNING
    29.
    发明申请
    SYSTEMS AND METHODS FOR IMAGE SCANNING 有权
    用于图像扫描的系统和方法

    公开(公告)号：US20160063727A1

    公开(公告)日：2016-03-03

    申请号：US14624291

    申请日：2015-02-17

    Applicant: QUALCOMM Incorporated

    Inventor： Dashan Gao ,  Xin Zhong ,  Ananthapadmanabhan Arasanipalai Kandhadai

    IPC: G06T7/20 ,  G06K9/00 ,  G06K9/32

    CPC classification number: G06T7/20 ,  G06K9/00335 ,  G06K9/00771 ,  G06K9/3241 ,  G06K9/4642 ,  G06T7/207 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/20016

    Abstract: A method for image scanning by an electronic device is described. The method includes obtaining an image pyramid including a plurality of scale levels and at least a first pyramid level for a frame. The method also includes providing a scanning window. The method further includes scanning at least two of the plurality of scale levels of the frame at a plurality of scanning window locations. A number of scanning window locations is equal for each scale level of the at least two scale levels of the first pyramid level.

    Abstract translation: 描述了一种通过电子设备进行图像扫描的方法。 该方法包括获得包括多个缩放级别和至少一帧的第一金字塔级别的图像金字塔。 该方法还包括提供扫描窗口。 该方法还包括在多个扫描窗口位置扫描帧的多个刻度级中的至少两个。 多个扫描窗口位置对于第一金字塔级别的至少两个缩放级别的每个缩放级别是相等的。

    SYSTEMS AND METHODS FOR OBJECT CLASSIFICATION, OBJECT DETECTION AND MEMORY MANAGEMENT
    30.
    发明申请
    SYSTEMS AND METHODS FOR OBJECT CLASSIFICATION, OBJECT DETECTION AND MEMORY MANAGEMENT 有权
    用于对象分类，对象检测和内存管理的系统和方法

    公开(公告)号：US20160063357A1

    公开(公告)日：2016-03-03

    申请号：US14609104

    申请日：2015-01-29

    Applicant: QUALCOMM Incorporated

    Inventor： Dashan Gao ,  Yang Yang ,  Xin Zhong ,  Yingyong Qi

    IPC: G06K9/62 ,  G06N7/00 ,  G06K9/46 ,  G06N99/00

    CPC classification number: G06K9/6269 ,  G06K9/4604 ,  G06N7/00 ,  G06N99/005

    Abstract: A method for object classification by an electronic device is described. The method includes obtaining an image frame that includes an object. The method also includes determining samples from the image frame. Each of the samples represents a multidimensional feature vector. The method further includes adding the samples to a training set for the image frame. The method additionally includes pruning one or more samples from the training set to produce a pruned training set. One or more non-support vector negative samples are pruned first. One or more non-support vector positive samples are pruned second if necessary to avoid exceeding a sample number threshold. One or more support vector samples are pruned third if necessary to avoid exceeding the sample number threshold. The method also includes updating classifier model weights based on the pruned training set.

    Abstract translation: 描述了一种通过电子设备进行物体分类的方法。 该方法包括获得包括对象的图像帧。 该方法还包括从图像帧确定样本。 每个样本表示多维特征向量。 该方法还包括将样本添加到图像帧的训练集合中。 该方法还包括从训练集修剪一个或多个样本以产生修剪的训练集。 首先修剪一个或多个非支持向量负样本。 如果必要，一个或多个非支持向量阳性样本被修剪，以避免超过样本数阈值。 如果需要，一个或多个支持向量样本被修剪为第三，以避免超过样本数阈值。 该方法还包括基于修剪的训练集更新分类器模型权重。

Patent Agency Ranking