Image-based article stacking detection method and system and electronic equipment

Abstract

The invention relates to an image-based article stacking detection method and system and electronic equipment The method comprises the following steps of: preparing a substrate; acquiring depth data and RGB data of an image by using a depth camera, identifying the image by using the RGB data to obtain the category and position of a to-be-detected non-standard article, acquiring the height of the to-be-detected non-standard article by using the depth data, comparing the height with the height interval of the same category of non-standard article, and judging whether the to-be-detected non-standard article is stacked. Whether non-standard articles are stacked or not during settlement is detected through the depth camera, so that when the non-standard articles are subjected to self-service settlement, stacked food is detected through the stacking detection method, wrong recognition on the quantity and types of the food is avoided, and settlement failures or settlement errors are prevented. The non-standard article is a non-standard product, and the surface of the non-standard article is in a non-planar form, so that the plane corresponding to the three-dimensional point cloud where the non-standard article is located can be accurately estimated by the method, the height information of the non-standard article can be accurately solved, and whether the non-standard article is stacked or not can be accurately judged.

Description

【Technical field】 [0001] The invention belongs to the field of image recognition, and in particular relates to an image-based object stacking detection method, system and electronic equipment. 【Background technique】 [0002] In the field of non-standard item identification, many commodities such as bread and biscuits are often not labeled when they are sold, and when the commodity is settled, it is often necessary for the salesperson to confirm the type of commodity and then confirm the price. And through image recognition technology, identify the type of goods, and carry out self-service settlement for the goods purchased by customers, which can reduce the labor cost of the cash register and bring convenience to life. [0003] In the field of identification of non-standard items, such as bread, biscuits and other non-standard items, when purchased and packaged, there are often states of stacking or blocking, which will cause misidentification of the quantity and type of bre...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the current problem of unrecognizable stacking of non-standard items in images, the present invention provides an image-based method, system and electronic equipment for stacking detection of items

Images