US 12,190,545 B2
Intelligent manufacturing industrial internet of things with front split service platform, control method and medium thereof
Zehua Shao, Chengdu (CN); Haitang Xiang, Chengdu (CN); Lei Zhang, Chengdu (CN); Yaqiang Quan, Chengdu (CN); and Junyan Zhou, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Oct. 26, 2022, as Appl. No. 18/049,642.
Prior Publication US 2023/0069949 A1, Mar. 9, 2023
Int. Cl. G06T 7/80 (2017.01); G06T 7/00 (2017.01); H04N 13/239 (2018.01)
CPC G06T 7/85 (2017.01) [G06T 7/0004 (2013.01); H04N 13/239 (2018.05); G06T 2207/10012 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30108 (2013.01); G06T 2207/30168 (2013.01)] 17 Claims
OG exemplary drawing
 
1. An intelligent manufacturing industrial Internet of Things with a front split service platform, comprising a service platform, a management platform, and a sensor network platform which interact in sequence, wherein the management platform includes:
an obtaining module configured to obtain an image taken by a first camera on a production line as first image data and an image taken by a second camera as second image data through the sensor network platform; the first camera and the second camera forming a binocular camera;
a three-dimensional module configured to process the first image data and the second image data into three-dimensional image data;
a recognition module configured to obtain a plurality of point positions of a distortion part as judgment point positions when detecting the distortion of the three-dimensional image data; wherein the recognition module is further configured to:
detect whether the three-dimensional image data is distorted according to a preset template;
establish a region of interest with a point of maximum distortion as a center when detecting the distortion of the three-dimensional image data;
recognize at least two continuous distortion edges from the region of interest according to the preset template, and if at least two continuous distortion edges are not recognized, redefine the region of interest and perform recognition again;
recognize a separation edge and a common edge from the distortion edges according to the preset template, extract a plurality of point positions from the separation edge as first point positions, and extract a plurality of point positions from the common edge as second point positions, wherein the separation edge is an edge where the same point positions in the first image data and the second image data do not overlap in the three-dimensional image data, and the common edge is an edge where the same point positions in the first image data and the second image data overlap in the three-dimensional image data; and
use the first point positions and the second point positions as the judgment point positions;
a mapping module configured to map the judgment point positions to the first image data to form first calibration point positions, and map the judgment point positions to the second image data to form second calibration point positions; and
a calibration module configured to calibrate the first camera and the second camera based on the first calibration point positions and the second calibration point positions; and
the service platform includes:
a plurality of service sub-platforms configured to respectively receive different calibration data of the binocular camera; and
a general service platform configured to summarize all the calibration data and display the calibration data through a user platform.