A kind of labeling system and labeling method for image segmentation
An image segmentation and image technology, which is applied in the field of truck image target segmentation, can solve the problems of long time and high cost, and achieve the effect of accelerating the research and development progress, reducing the workload, and improving the labeling progress
Active Publication Date: 2021-06-04
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the time-consuming and high-cost problems of manual labeling in the existing target segmentation, the present invention provides a semi-automatic labeling system and labeling method for image segmentation
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
[0048] 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 creative efforts fall within the protection scope of the present invention.
[0049] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.
[0050] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.
[0051] A labeling method for image segmentation in this embodiment includes:
[0052] Step 1. Obtain a data set...
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
A labeling system and labeling method for image segmentation solves the problems of long time and high cost of manual labeling in existing target segmentation, and belongs to the field of truck image target segmentation. The present invention comprises: first manually labeling a small part of the data set, then performing data amplification on the data set to obtain a training set, utilizing the training set and adopting hyperparameter search and network structure to train an optimal segmentation model, utilizing the optimal segmentation model to treat labeling The data is predicted, and the labeling personnel modify the labeling results predicted by the optimal segmentation model for a second time, and finally conduct an acceptance review on the labeling data set results after the secondary modification, and then complete the entire labeling task.
Description
technical field [0001] The invention relates to a semi-automatic labeling system and labeling method realized by deep learning, belonging to the field of truck image target segmentation. Background technique [0002] For a long time, the traditional manual inspection of images for fault judgment has high cost and low efficiency. It is of great significance to use automatic fault detection for trucks. At present, deep learning is an important technology to realize automatic fault detection of trucks. Deep learning technology mainly includes three technologies: target classification, target detection and target segmentation. [0003] Target segmentation is a long-term challenging technical problem in deep learning to realize the automatic identification of truck faults. The use of target segmentation can accurately segment the outline information of the target of the truck to be recognized, and then judge whether the target has a fault according to the outline information of t...
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): G06K9/34G06K9/46G06K9/62G06N3/04
CPCG06V10/267G06V10/44G06V2201/08G06N3/045G06F18/214
Inventor 孙晶庞博
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD