Garment standardized detection method and device

Abstract

The invention provides a garment standardized detection method and device, relates to the field of artificial intelligence, and can reduce the model customization cost and improve the garment standardized detection accuracy. The method comprises the following steps: acquiring a video frame sub-graph and a reference sub-graph by the clothes standardization detection device; the video frame sub-graph is from a video frame image of the first scene, the video frame image comprises an image of the target object, and the video frame sub-graph comprises an image of a first wearing style of a target part of the target object in the first scene. The reference sub-graph is from a target reference set of the first scene, the target reference set comprises an image of a reference object, and the reference sub-graph comprises an image of a standard wearing pattern of a target part of the reference object in the first scene. Then, processing the video frame sub-image and the reference sub-image by adopting a target model to obtain a first processing result; the target model is a trained artificial intelligence AI model, and the first processing result indicates the similarity between the first wearing style of the target object and the standard wearing style of the reference object.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method and device for clothing normalization detection. Background technique [0002] Clothing standardization refers to the uniform requirements for the target object's dress based on some considerations (such as safety factors) in a specific scenario. For example, construction workers on construction sites need to wear work clothes, work caps, etc. Clothing normalization detection refers to identifying whether the target object is dressed according to the regulations through the processing method of computer vision. For example, the computer uses a classifier to identify the dress of the target object and judge whether the dress of the target object is standard. Among them, the classifier is customized training, that is, the classifier is trained for a certain style of clothing. [0003] However, in different scenarios, the target object need...

AI Technical Summary

Problems solved by technology

[0003] However, in different scenarios, the target object needs to wear different styles of clothing, so the cost of customizing the training classifier is large

If the classifier is not trained for a certain style of clothing, it will not be possible to determine whether the target object is wearing that style of clothing in accordance with the regulations, resulting in a low accuracy rate of clothing standardized detection

Images