Visual measuring system based on self-adapting targets and calibrating method thereof

Abstract

The invention provides a visual measuring system based on self-adapting targets and a calibration method thereof, wherein the system and method provided by the invention are applicable to the technical field of computer vision. In the embodiment of the invention, the targets are constructed based on the samples of the to-be-detected workpieces by sticking a code mark on the surface of the workpiece, so that the manufacturing is simple without mechanical processing. Digital cameras and scales are used for regulating the target and can be recycled for regulating a plurality of targets, so that the cost is low. The cameras in the system ensure that the targets can be seen during a measuring process, so the cameras in the system can be calibrated simultaneously; and the calibration error is not delivered and accumulated, so that the calibration precision is high. The targets can be directly moved and placed by a mechanical device in a production line; and the method is especially applicable to online calibration.

Description

Technical field [0001] The invention belongs to the application field of computer vision technology, and particularly relates to a vision measurement system based on an adaptive target and a calibration method thereof. Background technique [0002] The structured light-based visual measurement system has the advantages of non-contact, fast speed, high accuracy, and high data density. It has a wide range of applications in industrial production fields such as reverse engineering, quality control, and defect detection. For the vision measurement system, system calibration is the main factor that affects the measurement accuracy, and precise system calibration ensures the measurement accuracy of the system to a large extent. [0003] In the vision measurement system, the camera is the basic unit of the system. System calibration is the process of determining the internal parameters of each camera in the system and determining the positional relationship (structural parameters) betwee...

AI Technical Summary

Problems solved by technology

However, the number of marker points on this type of target is often very small, and the constraints on the external parameters of the camera that can be provided are correspondingly reduced. It requires the target to change its posture multiple times in the public field of view, which increases the operational complexity of the calibration process. , will also have an adverse effect on the calibration accuracy

The calibration of some systems also requires that the target and the camera maintain an inherent positional relationship, and there are also specific requirements for the movement of the camera. These additional requirements often bring operational difficulties and introduce errors, resulting in a decrease in calibration accuracy.

Images