公开(公告)号：US20150199572A1

公开(公告)日：2015-07-16

申请号：US14157110

申请日：2014-01-16

Applicant: QUALCOMM Incorporated

Inventor： Kiyoung Kim ,  Yanghai Tsin

IPC: G06K9/00 ,  G06K9/48 ,  G06K9/46

CPC classification number: G06K9/00624 ,  G06K9/4604 ,  G06K9/48 ,  G06T7/194 ,  G06T7/207 ,  G06T7/246 ,  G06T7/251 ,  G06T7/292 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20016 ,  G06T2207/20061 ,  G06T2207/20076 ,  G06T2207/30244

Abstract: Embodiments disclosed pertain to object tracking based, in part, on occluding contours associated with the tracked object. In some embodiments, a 6 Degrees of Freedom (6-DoF) initial camera pose relative to a tracked object in a first image may be obtained. A 6-DoF updated camera pose relative to the tracked object for a second image subsequent to the first image may then be obtained based, at least, on the initial camera pose and one or more features associated with the tracked object and an occluding contour associated with the tracked object in the second image. The occluding contour associated with the tracked object in the second image may be derived from a closed form function.

Abstract translation: 所公开的实施例部分地基于与跟踪对象相关联的遮挡轮廓的对象跟踪。 在一些实施例中，可以获得相对于第一图像中的被跟踪物体的6自由度（6-DoF）初始摄像机姿态。 可以至少基于初始摄像机姿态和与跟踪对象相关联的一个或多个特征以及与被跟踪的对象相关联的一个或多个特征，获得针对第一图像之后的第二图像相对于跟踪对象的6-DoF更新的摄像机姿态 跟踪对象在第二个图像。 与第二图像中的跟踪对象相关联的闭塞轮廓可以从闭合形式函数导出。

公开(公告)号：US20140369557A1

公开(公告)日：2014-12-18

申请号：US14263866

申请日：2014-04-28

Applicant: QUALCOMM Incorporated

Inventor： Guy-Richard Kayombya ,  Seyed Hesameddin Najafi Shoushtari ,  Dheeraj Ahuja ,  Yanghai Tsin

IPC: G06K9/00

CPC classification number: G06K9/00624 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/30244

Abstract: Disclosed embodiments pertain to feature based tracking. In some embodiments, a camera pose may be obtained relative to a tracked object in a first image and a predicted camera pose relative to the tracked object may be determined for a second image subsequent to the first image based, in part, on a motion model of the tracked object. An updated SE(3) camera pose may then be obtained based, in part on the predicted camera pose, by estimating a plane induced homography using an equation of a dominant plane of the tracked object, wherein the plane induced homography is used to align a first lower resolution version of the first image and a first lower resolution version of the second image by minimizing the sum of their squared intensity differences. A feature tracker may be initialized with the updated SE(3) camera pose.

Abstract translation: 公开的实施例涉及基于特征的跟踪。 在一些实施例中，可以相对于第一图像中的跟踪对象获得相机姿态，并且可以针对基于运动模型的第一图像之后的第二图像来确定相对于被跟踪对象的预测相机姿态 的跟踪对象。 然后可以部分地基于预测的摄像机姿态通过使用跟踪对象的主平面的方程估计平面诱导的单应性来获得更新的SE（3）相机姿态，其中使用平面诱导的单应性来对齐 第一图像的第一低分辨率版本和第二图像的第一较低分辨率版本，通过最小化其平方强度差的总和。 功能跟踪器可以用更新的SE（3）相机姿态来初始化。

公开(公告)号：US20140280184A1

公开(公告)日：2014-09-18

申请号：US13836070

申请日：2013-03-15

Applicant: QUALCOMM INCORPORATED

Inventor： Ashwin Swaminathan ,  Jose Jeronimo Moreira Rodrigues ,  Raghuraman Krishnamoorthi ,  Yanghai Tsin ,  Murali Ramaswamy Chari

IPC: G06F17/30

CPC classification number: G06F17/30321

Abstract: In several aspects, an electronic device and method index a repository of N documents by W words, by not storing between queries, N*W numbers that are specific to each word i and each document j, normally used to compute a score of relevance to a query, of each document j. Instead, the electronic device and method generate the N*W word-specific-document-specific numbers dynamically at query time, based on a set of W numbers corresponding to the W words, and one or more sets (e.g. x sets) of N numbers corresponding to the N documents. Query-time generation of word-specific-document-specific numbers reduces memory otherwise required, e.g. to store these numbers. Hence, in certain aspects W+xN numbers are maintained between queries, and these numbers are changed incrementally when a new document is added to the set or an existing document is removed. Maintaining W+xN numbers reduces processing otherwise required, to start from scratch.

Abstract translation: 在几个方面，电子设备和方法通过W字来索引N个文档的存储库，通过不存储查询之间的N * W数字，每个单词i和每个文档j都是特定的，通常用于计算与 每个文件的查询j。 相反，电子设备和方法基于与W字相对应的一组W数字，以及一个或多个（例如x集）的N个集合（例如x集合），在查询时间动态地生成N * W个字特定文档特定号码 与N个文件相对应的数字。 单词特定文档特定号码的查询时间生成减少了所需的内存，例如。 存储这些数字。 因此，在某些方面，在查询之间维护W + xN个数，并且当将新文档添加到集合或删除现有文档时，这些数字将逐渐更改。 维护W + xN数字可以减少否则需要的处理，从头开始。

公开(公告)号：US20140270346A1

公开(公告)日：2014-09-18

申请号：US13797742

申请日：2013-03-12

Applicant: QUALCOMM INCORPORATED

Inventor： Yanghai Tsin ,  Kiyoung Kim

IPC: G06T7/00

CPC classification number: G06T7/0042 ,  G06T7/251 ,  G06T2207/30244

Abstract: A method of real-time tracking of an object includes capturing a first and a second image of the object. The object is detected in the first image and movement of the object is tracked between the images. Tracking of the object includes obtaining an initial pose of the camera; projecting an image of a model object onto the second image; determining a gradient profile of the second image from an edge point of the model object along a first direction that is normal to the edge of the model object; computing a radius on the gradient profile; determining a rank order of the peaks of the gradient profile along the radius; comparing the rank order with a predetermined rank order to generate a feature candidate point; and reducing a distance along the first direction between the feature candidate point and the edge point on the edge of the model object.

Abstract translation: 对对象的实时跟踪的方法包括捕获对象的第一和第二图像。 在第一图像中检测到物体，并且在图像之间追踪对象的移动。 对象的跟踪包括获得相机的初始姿态; 将模型对象的图像投影到第二图像上; 沿着与模型对象的边缘正交的第一方向从模型对象的边缘点确定第二图像的渐变分布; 计算梯度轮廓上的半径; 确定沿半径的梯度轮廓的峰值的等级次序; 将秩顺序与预定秩次进行比较以生成特征候选点; 并且减少特征候选点与模型对象边缘上的边缘点之间沿第一方向的距离。

公开(公告)号：US09406137B2

公开(公告)日：2016-08-02

申请号：US14278928

申请日：2014-05-15

Applicant: QUALCOMM Incorporated

Inventor： Dheeraj Ahuja ,  Kiyoung Kim ,  Yanghai Tsin ,  Seyed Hesameddin Najafi Shoushtari

IPC: G06K9/00 ,  G06T7/00 ,  H04N7/18 ,  G06T7/20

CPC classification number: G06T7/0044 ,  G06T7/246 ,  G06T7/75 ,  G06T2207/20021 ,  G06T2207/30244 ,  H04N7/183

Abstract: Disclosed embodiments pertain to apparatus, systems, and methods for robust feature based tracking. In some embodiments, a score may be computed for a camera captured current image comprising a target object. The score may be based on one or more metrics determined from a comparison of features in the current image and a prior image captured by the camera. The comparison may be based on an estimated camera pose for the current image. In some embodiments, one of a point based, an edge based, or a combined point and edge based feature correspondence method may be selected based on a comparison of the score with a point threshold and/or a line threshold, the point and line thresholds being obtained from a model of the target. The camera pose may be refined by establishing feature correspondences using the selected method between the current image and a model image.

Abstract translation: 公开的实施例涉及用于基于鲁棒特征的跟踪的装置，系统和方法。 在一些实施例中，可以针对包括目标对象的摄像机拍摄的当前图像计算得分。 得分可以基于从当前图像中的特征与由相机捕获的先前图像的比较确定的一个或多个度量。 比较可以基于当前图像的估计的摄像机姿态。 在一些实施例中，可以基于得分与点阈值和/或线阈值的比较来选择基于点，基于边缘的或基于组合的基于点和边缘的特征对应方法中的一个，点和线阈值 从目标的模型中获得。 可以通过使用当前图像和模型图像之间的所选方法建立特征对应来改进相机姿态。

公开(公告)号：US09147122B2

公开(公告)日：2015-09-29

申请号：US13829099

申请日：2013-03-14

Applicant: QUALCOMM Incorporated

Inventor： Hui Chao ,  Yanghai Tsin ,  Faraz Mohammad Mirzaei

IPC: G06K9/62 ,  G06K9/46 ,  G06T7/00

CPC classification number: G06K9/4604 ,  G06T7/73 ,  G06T2207/10004 ,  G06T2207/30244

Abstract: A method for estimating camera pose includes: obtaining an image of a location captured via a camera, where the image includes a target object and edge line features outside of the target object; and calculating a pose of the camera with respect to the target object based on the edge line features.

Abstract translation: 一种用于估计摄像机姿势的方法包括：获得通过照相机拍摄的位置的图像，其中图像包括目标对象，并且边缘线特征在目标对象外部; 以及基于所述边缘线特征来计算相机相对于所述目标对象的姿态。

公开(公告)号：US09025823B2

公开(公告)日：2015-05-05

申请号：US13797742

申请日：2013-03-12

Applicant: QUALCOMM Incorporated

Inventor： Yanghai Tsin ,  Kiyoung Kim

IPC: G06K9/00 ,  G06T7/00

CPC classification number: G06T7/0042 ,  G06T7/251 ,  G06T2207/30244

Abstract: A method of real-time tracking of an object includes capturing a first and a second image of the object. The object is detected in the first image and movement of the object is tracked between the images. Tracking of the object includes obtaining an initial pose of the camera; projecting an image of a model object onto the second image; determining a gradient profile of the second image from an edge point of the model object along a first direction that is normal to the edge of the model object; computing a radius on the gradient profile; determining a rank order of the peaks of the gradient profile along the radius; comparing the rank order with a predetermined rank order to generate a feature candidate point; and reducing a distance along the first direction between the feature candidate point and the edge point on the edge of the model object.

Abstract translation: 对对象的实时跟踪的方法包括捕获对象的第一和第二图像。 在第一图像中检测到物体，并且在图像之间追踪对象的移动。 对象的跟踪包括获得相机的初始姿态; 将模型对象的图像投影到第二图像上; 沿着与模型对象的边缘正交的第一方向从模型对象的边缘点确定第二图像的渐变分布; 计算梯度轮廓上的半径; 确定沿半径的梯度轮廓的峰值的等级次序; 将秩顺序与预定秩次进行比较以生成特征候选点; 并且减少特征候选点与模型对象边缘上的边缘点之间沿第一方向的距离。

公开(公告)号：US20140270362A1

公开(公告)日：2014-09-18

申请号：US13844692

申请日：2013-03-15

Applicant: QUALCOMM INCORPORATED

Inventor： Seyed Hesameddin Najafi Shoushtari ,  Yanghai Tsin ,  Murali Ramaswamy Chari ,  Serafin Diaz Spindola

IPC: G06K9/00

CPC classification number: G06K9/6204

Abstract: Embodiments include detection or relocalization of an object in a current image from a reference image, such as using a simple and relatively fast and invariant edge orientation based edge feature extraction, then a weak initial matching combined with a strong contextual filtering framework, and then a pose estimation framework based on edge segments. Embodiments include fast edge-based object detection using instant learning with a sufficiently large coverage area for object re-localization. Embodiments provide a good trade-off between computational efficiency of the extraction and matching processes.

Abstract translation: 实施例包括从参考图像中检测或重新定位当前图像中的对象，例如使用简单且相对快速且不变的基于边缘取向的边缘特征提取，然后将弱初始匹配与强的上下文过滤框架组合，然后 基于边缘段的姿态估计框架。 实施例包括使用具有足够大的覆盖区域的即时学习的快速边缘对象检测用于对象重新定位。 实施例提供了提取和匹配过程的计算效率之间的良好折衷。

公开(公告)号：US09116938B2

公开(公告)日：2015-08-25

申请号：US13836070

申请日：2013-03-15

Applicant: QUALCOMM Incorporated

Inventor： Ashwin Swaminathan ,  Jose Jeronimo Moreira Rodrigues ,  Raghuraman Krishnamoorthi ,  Yanghai Tsin ,  Murali Ramaswamy Chari

IPC: G06F17/30

CPC classification number: G06F17/30321

Abstract: In several aspects, an electronic device and method index a repository of N documents by W words, by not storing between queries, N*W numbers that are specific to each word i and each document j, normally used to compute a score of relevance to a query, of each document j. Instead, the electronic device and method generate the N*W word-specific -document-specific numbers dynamically at query time, based on a set of W numbers corresponding to the W words, and one or more sets (e.g. x sets) of N numbers corresponding to the N documents. Query-time generation of word-specific-document-specific numbers reduces memory otherwise required, e.g. to store these numbers. Hence, in certain aspects W+xN numbers are maintained between queries, and these numbers are changed incrementally when a new document is added to the set or an existing document is removed. Maintaining W+xN numbers reduces processing otherwise required, to start from scratch.

Abstract translation: 在几个方面，电子设备和方法通过W字来索引N个文档的存储库，通过不存储查询之间的N * W数字，每个单词i和每个文档j都是特定的，通常用于计算与 每个文件的查询j。 相反，电子设备和方法基于与W字对应的一组W数字，并且在一个或多个集合（例如，x集合）N的基础上，在查询时间动态地生成N * W字特定的文档特定号码 与N个文件相对应的数字。 单词特定文档特定号码的查询时间生成减少了所需的内存，例如。 存储这些数字。 因此，在某些方面，在查询之间维护W + xN个数，并且当将新文档添加到集合或删除现有文档时，这些数字将逐渐更改。 维护W + xN数字可以减少否则需要的处理，从头开始。