Robot and inventory management method thereof

Abstract

The invention discloses a robot and an inventory management method thereof. The invention management method comprises the steps that a front image of a to-be-recognized object is collected, and firstlocal invariant features of the to-be-recognized object are extracted according to the front image; an environment image is acquired, and environment local invariant features of the environment imageare extracted; the environment local invariant features are matched with the first local invariant features, matching feature points are mapped to a reference center to obtain an effective reference center, and a scale ratio and a reference clustering radius corresponding to the effective reference center are acquired; second local invariant features of the front image of the to-be-recognized object are extracted again according to the scale ratio, then the environment image is matched with newly extracted the second local invariant features, and feature points obtained after matching are mapped to the reference center; and finally clustering is performed on the reference center of the object according to the reference clustering radius. In this way, the precision and speed of detection and recognition can be improved in terms of article recognition.

Description

technical field [0001] The invention relates to the technical field of robots, in particular to a robot and its inventory management method. Background technique [0002] At present, service robots have been used in hospitals, shopping malls and other places to complete tasks such as explaining and handling. Due to limitations in sensing, intelligence, etc., the application of service robots is still at a relatively low stage of intelligence, which also limits the application of service robots. For example, in supermarkets, pharmacies, etc., a lot of boring work such as counting and displaying goods still needs manual participation. [0003] At present, there are two main schemes for automatic inventory counting. The first one is based on the product’s own label data, and the robot completes the identification and inventory of materials by scanning the label; the second is to use the image matching of objects to realize the identification and inventory of materials. invent...

AI Technical Summary

Problems solved by technology

However, for the placement of items on the shelves in shopping malls, the front of the items is usually facing outward, while the own label code of the product is facing inward, which leads to the failure of the material identification and counting method using the product's own label code identification

A solution in the prior art is to solve the above-mentioned difficulties by manually pasting labels on the front of the items in the later stage. However, the method of post-labeling will not only lead to an increase in the cost of manpower and material resources, but also cause unsightly problems to the products.

Images