Image semantic classification method, medium and device and computing device
A classification method and semantic segmentation technology, applied in computing, computer components, character and pattern recognition, etc., can solve problems such as difficulty in ensuring real-time operation, high implementation complexity, difficulty in transmitting and updating semantic analysis results, etc., to achieve a good experience , Simplify the process, reduce the effect of difficulty
Inactive Publication Date: 2018-12-14
杭州易现先进科技有限公司
View PDF6 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing technical solutions for semantic classification of 3D scenes have problems such as high implementation complexity, difficulty in transmitting and updating semantic analysis results, and difficulty in ensuring real-time operation.
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
[0049] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present invention, rather than to limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0050] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, device, method or computer program product for image semantic classification. Therefore, the present disclosure may be embodied in the form of complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.
[0051] According to the embodiments of the present inven...
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
Embodiments of the present invention provide an image semantic classification method, medium and device, and a computing device. The method comprises the following steps of: performing semantic segmentation of an image to be recognized to generate a first semantic tag, wherein the first semantic tag is used for indicating the semantic classification of at least one pixel in the image to be recognized; storing the first semantic tag in at least one voxel of a three-dimensional space, at least one pixel corresponding to at least one voxel one-to-one; and storing a first effective distance fieldvalue of the at least one voxel into the at least one voxel. Through the method of the invention, the semantic classification of the same object in the three-dimensional space constructed by the images to be recognized at different times (or from different angles of view) is kept consistent, the accuracy of the semantic classification of the images is improved, the process of the semantic classification of the images is simplified, and the semantic classification in the dynamic changing scene is realized.
Description
technical field [0001] Embodiments of the present invention relate to the field of software technology, and more specifically, embodiments of the present invention relate to an image semantic classification method, medium, device, and computing device. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Image semantic classification, that is, semantic classification, is the basis of image recognition and can usually be used in scenarios such as automatic driving systems (such as street view recognition and understanding), unmanned aerial vehicles (such as the judgment of UAV landing sites) and wearable devices. . Image semantic classification mainly includes 2D image semantic classification and 3D scene semantic classification. 2D image semantic classification refers to th...
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 IPC IPC(8): G06K9/62
CPCG06F18/25G06F18/24
Inventor 王加芳刘海伟丛林
Owner 杭州易现先进科技有限公司