Visual tracking and positioning method for motion blur object in real-time video stream
A real-time video stream and motion blur technology, applied in character and pattern recognition, biological neural network model, image data processing, etc., can solve the problems of imaging motion blur, background confusion, and unobvious appearance features, so as to improve accuracy, avoid confusing effects
Pending Publication Date: 2021-04-02
丰颂教育科技(江苏)有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] For fast-moving small motion-blurred objects, there are the following difficulties in positioning: the relatively fast motion of the motion-blurred object and the camera is prone to imaging motion blur, resulting in the change or loss of the appearance characteristics of the motion-blurred object; for small motion-blurred objects, the appearance The features are less obvious and are easily confused with the background, so there is a problem of inaccurate positioning of motion blurred objects
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0044] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0045] The appearance of SIAMNET in the following embodiments represents a twin network (Siamese Networks, SIAMNET).
[0046] Such as figure 1 As shown, the present invention discloses a method for visual trackin...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a visual tracking and positioning method for a motion blur object in a real-time video stream. The method comprises the following steps: firstly, acquiring a motion blur objectvideo in real time; secondly, determining a tth frame of picture according to the video; inputting the tth frame of picture into the detection model again for object position detection to obtain a first object position detection result corresponding to the tth frame of picture; performing motion blur object position tracking by using SIAMNET to obtain a second object position detection result corresponding to the tth frame of picture; according to the motion blur object tracking method, the motion blur object of the small object is tracked twice, the object and the background are prevented from being confused by combining the motion information of the object, the position of the motion blur object is accurately obtained, and the motion blur object tracking accuracy is improved. The positioning accuracy of the motion blur object is improved.
Description
technical field [0001] The invention relates to the technical field of tracking motion blur objects, in particular to a visual tracking and positioning method for motion blur objects in real-time video streams. Background technique [0002] For fast-moving small motion-blurred objects, there are the following difficulties in positioning: the relatively fast motion of the motion-blurred object and the camera is prone to imaging motion blur, resulting in the change or loss of the appearance characteristics of the motion-blurred object; for small motion-blurred objects, the appearance The features are less obvious and are easily confused with the background, so there is a problem of inaccurate positioning of motion blurred objects. Contents of the invention [0003] In order to solve the various problems above, the present invention provides a visual tracking and positioning method for motion blurred objects in real-time video streams, so as to improve the accuracy of trackin...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06T7/20G06T7/70
CPCG06T7/70G06T7/20G06V20/40G06N3/045G06F18/214
Inventor 梁栋吴宝健田志虎吴飞
Owner 丰颂教育科技(江苏)有限公司