Article pick-and-place detection system, method and device

Abstract

The present application discloses an article pick-and-place detection system, method and device. An article pick-and-place detection system includes: an article pick-and-place cabinet, an image acquisition unit, and a pick-and-place detection unit; the edge of the entrance and exit of the article pick-and-place cabinet has markers, and the image acquisition unit is used to collect images of the entrance and exit of the article pick-and-place cabinet; The detection unit is connected with the image acquisition unit, and is used for picking and placing an item based on the marker information in the image acquired by the image acquisition unit. By setting markers on the edge of the entrance and exit of the item pick-and-place cabinet, the marker information in the entrance and exit images of the item pick-and-place cabinet is detected, and the item pick-and-place detection is performed based on the detection results, without the detection and tracking of the target item, reducing the scene and target. According to the requirements of items, it can cope with frequently changing scenes and pick and place at any speed, and the detection robustness is high. In addition, the present application performs pick-and-place detection through marker information, which improves the authenticity and accuracy of the pick-and-place detection operation.

Description

technical field [0001] The embodiments of the present application relate to the technical field of image processing, and in particular, to a system, method, and device for picking and placing an item. Background technique [0002] With the development of artificial intelligence, item pick-and-place cabinets are gradually being widely used. For example, an item pick-and-place cabinet can be used to store items, and when there is a pick-and-place demand, items are taken out from the item pick-and-place cabinet or placed in the item pick-and-place cabinet. Therefore, how to realize the pick-and-place detection of items is a relatively critical issue. [0003] In the related art, a deep learning network is used to identify the user's action posture or to detect the target item frame by frame to achieve the target item tracking, and achieve the purpose of picking and placing the item. [0004] However, this type of method uses a deep learning network for video data analysis, wh...

AI Technical Summary

Problems solved by technology

[0004] However, this type of method uses a deep learning network for video data analysis, which requires a large amount of calculation, and the computing resources are often deployed on cloud servers. The large amount of video transmission data results in low detection efficiency, high requirements for transmission bandwidth, and high deployment costs.

Images