Material falling detection method, device and equipment and storage medium
A detection method and material technology, applied in the field of detection, can solve the problems of detection failure, false detection, inability to separate the material from the background area, etc., and achieve the effect of avoiding false detection, fast detection speed and high accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] Please refer to figure 1 , figure 1 It is a schematic flowchart of a material drop detection method provided in Embodiment 1 of the present invention.
[0059] A method for detecting material falling includes steps S11 to S15, which will be described in detail below.
[0060] Step S11 , acquiring a detection image of the station to be detected.
[0061] In the embodiment of the present invention, step S11 acquires the detection image of the station to be detected, which may be that the camera unit shoots the station to be detected in real time, and the image obtained by the camera unit may also be in the early stage of material drop detection, by The imaging unit stores the image of the station to be inspected in the memory after photographing the station to be inspected, and obtains the inspection image of the station to be inspected from the memory, which is not specifically limited in the present invention.
[0062] Step S12, acquiring the detection area of the ...
Embodiment 2
[0076] On the basis of Embodiment 1, the acquisition of the detection area of the detection image includes:
[0077] inputting the detection image into a pre-established shape matching model to locate the detection area of the detection image;
[0078] When the positioning fails, it is determined that the material is dropped from the station to be detected;
[0079] When the positioning is successful, the detection area of the detection image is acquired.
[0080] In the embodiment of the present invention, the detection image is input into a pre-established shape matching model to locate the detection area of the detection image. When the positioning fails, it is likely that the detection area is blocked by falling materials and cannot be located Out of the detection area, because considering that the obtained detection image and template image are rarely blurred, it can be directly determined that there is material drop and return.
[0081] Further, refer to Figu...
Embodiment 3
[0096] On the basis of Embodiment 1, the calculation of the difference between the detection image and the template image to obtain the difference image includes:
[0097] Projecting and matching the corner points of the detected image with the corner points of the template image to calculate a homography matrix;
[0098] Registering the template image to the detection image by using the homography matrix, and calculating a difference between the detection image and the registered template image to obtain a difference image.
[0099] It should be noted that the template matching method described in Embodiment 2 may not be used to locate the detection area or the neglected area in the map, and the effective area registered by the template image through perspective transformation is the detection area by default, and the ignored The area is empty, and the detection area is directly detected, which is not specifically limited in the present invention.
[0100] Exemplarily, the d...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


