Intelligent order generation method for fusion after multi-view image acquisition and intelligent vending machine
A technology for collecting images and multiple viewing angles, applied in the field of image analysis, can solve problems such as poor user experience, abnormal orders, and complicated operations, so as to improve detection accuracy and user experience, and prevent order abnormality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0062] The existing full-door intelligent vending machine has the advantages of traditional vending machines, which is convenient for purchasing multiple items at one time and changing items multiple times during one shopping. At the same time, it can quickly generate orders when users complete a complicated shopping process, and quickly settle through independent settlement methods , compared with the existing one-time scan code that can only purchase one product, and cannot be re-selected after purchase, the full-door smart vending machine has the advantages of simple operation and stronger shopping options for users; however, because the full-door smart vending machine During a single shopping, the user can purchase multiple items, and at the same time put the items on and off the shelves multiple times. Due to the occlusion problem, during the process of loading or unloading a large number of items, due to the different occlusion positions, the front and back of the same ite...
Embodiment 2
[0118] In Example 1, the first main camera and the second main camera with different viewing angles are set for the product area of the smart vending machine. However, the imaging positions of the products in different product areas are different in each frame image, which often leads to There are false detections or mixed detections of commodities, which affect the accuracy of detection. Therefore, Embodiment 2 of the present invention further improves the method for automatically generating order information by an intelligent vending machine on the basis of Embodiment 1; please refer to image 3 , the method includes:
[0119] S20: Obtain the first main video obtained by capturing the product area captured by the first main camera, the second main video obtained by capturing the product area by the second main camera, and at least one first sub-video obtained by capturing the product area by the first sub-camera and at least one The second sub-camera captures the second s...
Embodiment 3
[0160] Embodiment 3 of the present invention is based on the methods of Embodiment 1 to Embodiment 2, and also provides an intelligent order generation device that fuses images collected from multiple perspectives. Please refer to Figure 4 ,include:
[0161] Video acquisition module: used to acquire the first main video obtained by the first main camera capturing the product area at a first viewing angle and the second main video obtained by capturing the product area at a second viewing angle different from the first viewing angle by the second main camera. Main video, wherein the frame rate of the first main camera and the second main camera are the same and the first main video and the second main video with the same number of frames are collected;
[0162] Video synthesis module: for merging each frame image of the first main video with each frame image corresponding to the acquisition time sequence in the second main video to generate a target video, wherein each frame i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More