Iterative multi-directional image search supporting large template matching

    公开(公告)号:US11210551B2

    公开(公告)日:2021-12-28

    申请号:US16524802

    申请日:2019-07-29

    发明人: Tian Qiu

    摘要: Systems and methods which provide iterative multi-directional image searching are described. Embodiments utilize a multi-directional searching pattern for defining one or more searching areas within a source image. A searching area of embodiments provides a searching area within a source image for searching for a template image in the multiple directions of the multi-directional searching pattern. A location of the searching area within the source image may be updated iteratively, such as based upon motion vectors derived from the searching, until a template image match position is identified within the source image. Embodiments transform the template image and the searching area within a source image to 1D representations corresponding to each direction of the multi-directional image search. Embodiments accommodate rotation and scale variance of the subject (e.g., object of interest) of the template image within the source image.

    Systems and methods for obtaining templates for tessellated images

    公开(公告)号:US11023770B2

    公开(公告)日:2021-06-01

    申请号:US16579111

    申请日:2019-09-23

    摘要: Systems and methods which obtain template images corresponding to pattern units of tessellated images using a template unit boundary identification technique are described. Template unit boundary identification techniques of embodiments operate to analyze a sample of a tessellated image to determine a template unit size for the template image, use the determined template unit size to define pixel analysis line segments for identifying template unit boundaries in the tessellated image, and select a template image based on the template unit boundaries identified using the pixel analysis line segments. One or more sample area images may be selected for use in determining a template unit size. Pixel analysis line segments, configured based upon a determined template unit size, may be used for identifying boundaries of a template unit. Moreover, dynamic template image updating may be provided.

    Systems and methods for block based edgel detection with false edge elimination

    公开(公告)号:US10510148B2

    公开(公告)日:2019-12-17

    申请号:US15845846

    申请日:2017-12-18

    发明人: Tian Qiu

    IPC分类号: G06T7/13 G06T7/11 G06T7/136

    摘要: Methods and systems which provide object edge image representation generation using block based edgel techniques implementing post edgel detection processing to eliminate false edges are described. Embodiments subdivide image data (e.g., image point clouds) to facilitate separate edgel detection processing of a plurality of sub-blocks of the image data. A false edge elimination algorithm of embodiments is applied in recombining the object edge image representation sub-blocks resulting from the sub-block edgel detection processing to eliminate false edge artifacts associated with use of block based edgel detection.

    SYSTEMS AND METHODS FOR OBTAINING TEMPLATES FOR TESSELLATED IMAGES

    公开(公告)号:US20210089806A1

    公开(公告)日:2021-03-25

    申请号:US16579111

    申请日:2019-09-23

    摘要: Systems and methods which obtain template images corresponding to pattern units of tessellated images using a template unit boundary identification technique are described. Template unit boundary identification techniques of embodiments operate to analyze a sample of a tessellated image to determine a template unit size for the template image, use the determined template unit size to define pixel analysis line segments for identifying template unit boundaries in the tessellated image, and select a template image based on the template unit boundaries identified using the pixel analysis line segments. One or more sample area images may be selected for use in determining a template unit size. Pixel analysis line segments, configured based upon a determined template unit size, may be used for identifying boundaries of a template unit. Moreover, dynamic template image updating may be provided.

    ITERATIVE MULTI-DIRECTIONAL IMAGE SEARCH SUPPORTING LARGE TEMPLATE MATCHING

    公开(公告)号:US20210034911A1

    公开(公告)日:2021-02-04

    申请号:US16524802

    申请日:2019-07-29

    发明人: Tian Qiu

    摘要: Systems and methods which provide iterative multi-directional image searching are described. Embodiments utilize a multi-directional searching pattern for defining one or more searching areas within a source image. A searching area of embodiments provides a searching area within a source image for searching for a template image in the multiple directions of the multi-directional searching pattern. A location of the searching area within the source image may be updated iteratively, such as based upon motion vectors derived from the searching, until a template image match position is identified within the source image. Embodiments transform the template image and the searching area within a source image to 1D representations corresponding to each direction of the multi-directional image search. Embodiments accommodate rotation and scale variance of the subject (e.g., object of interest) of the template image within the source image.

    SYSTEMS AND METHODS FOR BLOCK BASED EDGEL DETECTION WITH FALSE EDGE ELIMINATION

    公开(公告)号:US20190188856A1

    公开(公告)日:2019-06-20

    申请号:US15845846

    申请日:2017-12-18

    发明人: Tian Qiu

    IPC分类号: G06T7/13 G06T7/11 G06T7/136

    摘要: Methods and systems which provide object edge image representation generation using block based edgel techniques implementing post edgel detection processing to eliminate false edges are described. Embodiments subdivide image data (e.g., image point clouds) to facilitate separate edgel detection processing of a plurality of sub-blocks of the image data. A false edge elimination algorithm of embodiments is applied in recombining the object edge image representation sub-blocks resulting from the sub-block edgel detection processing to eliminate false edge artifacts associated with use of block based edgel detection.