Commodity falling detection method of automatic vending machine based on double cameras

Abstract

The invention discloses a commodity falling detection method of an automatic vending machine based on double cameras. The method comprises detection steps that (1) when a facility detects that a usercompletes payment, a holder rises to a layer where a commodity is positioned and is stopped, and the cameras at the two sides of the holder are started for snapshot; (2) a local processing module of the facility is started to process each snapshot image cutting the snapshot image according to a pre-determined monochrome chequer position of a side plate of the holder, removing irrelevant areas, graying the cut image, carrying out edge detection on the grayed image via a sobel edge detection operator to generate an edge image, and storing the edge image as a background image; (3) after that thebackground is shot, a commodity channel conveyor belt is started, and the cameras at the two sides of the holder are started to shoot the state of the holder; and (4) the conveyor belt is stopped andthe cameras are switched off. The method can be used to detect small, flat and transparent commodities, and influence of the ambient light on commodity detection can be avoided effectively.

Description

technical field [0001] The invention relates to a method for detecting goods falling of an automatic vending machine, in particular to a method for detecting goods falling of an automatic vending machine based on dual cameras. Background technique [0002] Vending machines have the characteristics of simple deployment, low site requirements, and labor cost savings, and are gradually becoming the mainstream of the new retail industry. [0003] The delivery of the vending machine is controlled by the machine tool. Whether the goods are successfully dropped will directly affect the interests of the merchant and the user experience. Therefore, the detection of goods falling is a very important problem to be solved by the vending machine. [0004] Traditional cargo drop detection methods are generally divided into three types: the first is the infrared grating method, which installs infrared emitting and receiving devices at both ends of the cargo platform to form an infrared gra...

AI Technical Summary

Problems solved by technology

[0004] Traditional cargo drop detection methods are generally divided into three types: the first is the infrared grating method, which installs infrared emitting and receiving devices at both ends of the cargo platform to form an infrared grating. When placed on the platform, the infrared rays will be blocked, and the system will determine whether the goods have fallen according to the degree of blocking. The disadvantages of this method are: (1) there is a gap between the infrared sensors, which cannot detect slender objects; (2) the infrared sensors can only Detect objects on the grating plane. If the goods are flat (such as chewing gum) and are under the detection plane, they cannot be detected; (3) For transparent goods (such as glass cups), they cannot effectively block infrared rays and are difficult to detect

[0005] The second is the weighing method of the pan-tilt. In this method, a weighing device is installed on the pan-tilt to determine whether there is any cargo falling by detecting the weight change of the pan-tilt. The problem with this method is that the weighing sensitivity is difficult to control. If the sensitivity is too high, it is easy to cause misjudgment; if the sensitivity is too low, it will not be able to detect light weight goods

[0006] The third is the picture comparison method. This method first takes an empty pan-tilt in advance to form a standard picture, and then captures the pan-tilt during the falling of the goods, and finally compares the difference between the captured picture and the standard picture, and judges whether the goods have fallen. , the problems of this method are: (1) the patent uses a preset standard picture, and for vending machines with transparent panels, due to the influence of external light, the standard pictures taken in different time periods and in different weathers are often very different , if the lighting environment of the picture taken by the whereabouts of the goods is inconsistent with the preset picture, it is easy to cause misjudgment; (2) the patent proposes to install the camera on the top of the vending machine. It is far away, so the objects captured are small, and it is difficult to distinguish unless a high-definition camera is used; (3) The vending machine uses a preset time to control the delivery of the conveyor belt (spring); Especially after multiple shipments, the accumulation of empty trips will increase, and it is difficult to determine the shipping time; if the preset time is too long, it will easily cause over-shipments and cause losses to the merchant; if the preset time is too short, the will cause the shipment to fail

Images