-
公开(公告)号:US20150154450A1
公开(公告)日:2015-06-04
申请号:US14618155
申请日:2015-02-10
Applicant: Huawei Technologies Co., Ltd.
Inventor: Guoxiong Yan
CPC classification number: G06K9/00624 , G06K9/4604 , G06K9/4642 , G06K9/48 , G06T7/20 , G06T7/251 , G06T7/269 , G06T11/20 , G06T2207/10016 , G06T2207/20016 , G06T2207/30232
Abstract: An optical flow tracking method includes generating a random structure according to an object to be tracked in an image, where the random structure includes at least two structure blocks with fixed relative positions; tracking all structure blocks in the random structure using an optical flow tracking algorithm to obtain a position offset of the random structure; and estimating a target position of the object according to the position offset of the random structure. According to the optical flow tracking method and apparatus provided in embodiments of the present invention, characteristic points of an object in an image are obtained, and a random structure is generated according to the characteristic points, and each random structure is tracked to obtain a position offset of the random structure, so as to estimate a position of the object, thereby reducing tracking errors and effectively improving tracking precision.
Abstract translation: 光流跟踪方法包括根据图像中要跟踪的对象生成随机结构,其中所述随机结构包括具有固定相对位置的至少两个结构块; 使用光流跟踪算法跟踪随机结构中的所有结构块,以获得随机结构的位置偏移; 以及根据随机结构的位置偏移来估计对象的目标位置。 根据本发明实施例提供的光流跟踪方法和装置,获得图像中的对象的特征点,并根据特征点生成随机结构,并且跟踪每个随机结构以获得位置 随机结构的偏移,从而估计对象的位置,从而减少跟踪误差并有效提高跟踪精度。
-
公开(公告)号:US11184646B2
公开(公告)日:2021-11-23
申请号:US16434387
申请日:2019-06-07
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Guoxiong Yan , Xiaohui Bie , Xiaojun Duan
IPC: H04N21/218 , H04N5/232 , H04N21/258 , H04N21/81 , H04N21/472 , H04N21/6587 , H04N21/422 , H04N21/431 , H04N21/4728
Abstract: Embodiments of the present disclosure provide a 360-degree panoramic video playing method, an apparatus, and a system. The method includes: receiving, by a video player, a search instruction, and displaying, according to the search instruction, locating information of a 360-degree panoramic video, where the locating information includes descriptive information of playing content in multiple angle ranges of the 360-degree panoramic video, and the descriptive information is used for determining the playing content in the multiple angle ranges; and receiving a switching instruction, and switching a playing angle range of the 360-degree panoramic video from an angle range of current playing content to a first angle range according to the switching instruction, where the first angle range is an angle range selected by a user from the multiple angle ranges.
-
公开(公告)号:US09536147B2
公开(公告)日:2017-01-03
申请号:US14618155
申请日:2015-02-10
Applicant: Huawei Technologies Co., Ltd.
Inventor: Guoxiong Yan
CPC classification number: G06K9/00624 , G06K9/4604 , G06K9/4642 , G06K9/48 , G06T7/20 , G06T7/251 , G06T7/269 , G06T11/20 , G06T2207/10016 , G06T2207/20016 , G06T2207/30232
Abstract: An optical flow tracking method includes generating a random structure according to an object to be tracked in an image, where the random structure includes at least two structure blocks with fixed relative positions; tracking all structure blocks in the random structure using an optical flow tracking algorithm to obtain a position offset of the random structure; and estimating a target position of the object according to the position offset of the random structure. According to the optical flow tracking method and apparatus provided in embodiments of the present invention, characteristic points of an object in an image are obtained, and a random structure is generated according to the characteristic points, and each random structure is tracked to obtain a position offset of the random structure, so as to estimate a position of the object, thereby reducing tracking errors and effectively improving tracking precision.
Abstract translation: 光流跟踪方法包括根据图像中要跟踪的对象生成随机结构,其中所述随机结构包括具有固定相对位置的至少两个结构块; 使用光流跟踪算法跟踪随机结构中的所有结构块,以获得随机结构的位置偏移; 以及根据随机结构的位置偏移来估计对象的目标位置。 根据本发明实施例提供的光流跟踪方法和装置,获得图像中的对象的特征点,并根据特征点生成随机结构,并且跟踪每个随机结构以获得位置 随机结构的偏移,从而估计对象的位置,从而减少跟踪误差并有效提高跟踪精度。
-
-