Target recognition method and target recognition device
A target recognition and target technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of small number of feature points, low confidence of matching results, etc., and achieve high recognition accuracy
Active Publication Date: 2018-06-22
RICOH KK
View PDF5 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] However, this technical solution has the following problems: since the feature points are detected by a detection algorithm, the number of feature points is often very small
Therefore, if only a few feature points are detected, the expression of the target image area (also known as the shooting target) will be limited, resulting in a correspondingly lower confidence in the matching result
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
[0036] Various embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Here, it is to be noted that, in the drawings, the same reference numerals are assigned to components having substantially the same or similar structures and functions, and repeated descriptions about them will be omitted.
[0037] In the following, the main idea of the present application will be briefly described.
[0038] In order to solve the technical problem in the prior art, that is, for the situation where only a small number of feature points can be detected, a new type of target recognition method is proposed in this application, which can directly increase the feature points according to the predetermined sampling method Number of. In this way, due to the increase in the number of feature points, the expression of the target image region becomes more abundant, thereby improving the confidence of the matching result to a certain ex...
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 target recognition method and device. The method is used to identify a target image area of an unknown category based on at least one sample image area of a known category, and includes: sampling the target image area through a predetermined sampling method to obtain multiple target sampling points; calculating the target sampling The stability weight of the point is used to express the stability of the target sampling point in the feature space; to obtain a weighted feature description of the target image area based on the target sampling point with stability weight; and based on the weighted features of the target image area The weighted feature description model of the description and sample image area is used to identify the target image area, where the weighted feature description model of the sample image area is obtained based on the sample sampling points with stability weights. Therefore, the present invention has higher recognition accuracy and is more robust to various degradations of feature points due to various factors in real scenes.
Description
technical field [0001] The present invention relates to the field of digital image processing, and more specifically, the present invention relates to a target recognition method and a target recognition device. Background technique [0002] In recent years, target recognition has gradually become an active research field of computer vision, because it provides the core processing power for the computer to automatically perceive the category of the target, maintain a tracking process, and automatically recover after the tracking is lost, so that Provide services for high-level applications, such as human activity (behavior) analysis, etc. [0003] Although there is currently active research on object recognition, there are still some well-known problems to be overcome. For example, since target recognition in real scenes has high requirements on local features, it is required that these features cannot be affected by factors such as interference and occlusion of nearby obje...
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 Patents(China)
IPC IPC(8): G06K9/62
Inventor 乔刚王鑫范圣印王千诸加丹
Owner RICOH KK