Terms and Concepts

This section introduces the key terms and concepts related to machine vision.

Solution and Project

Solution library

A resource library that provides typical solutions or projects (with example data) coming from different application scenarios.


A solution is a collection of functional configurations and data for robot, communication, vision processing, and path planning required for a vision application.


A project refers to a Mech-Vision project. One or more projects constitute a solution. Projects cannot be used independently and must belong to a solution.


Steps are the basics of a project. A Step is a minimum algorithm unit for data processing. By connecting different Steps in a project, you can achieve different data process tasks.


A Procedure groups the Steps whose functions are closely related and achieve a specific purpose concertedly in the project.

Parameter recipe

Parameter recipes are sets of parameter settings that need to be adjusted according to different situations for the same project. With parameter recipes, you do not need to build multiple projects with the same logic and configure their parameters differently to meet different on-site requirements. Instead, you will only need to switch between parameter recipes in one project to make it applicable to various scenarios and therefore the productivity can be increased.

Hand-Eye Calibration

Hand-eye calibration

Hand-eye calibration establishes the transformation relationship between the camera and robot reference frames. With this relationship, the object poses determined by the vision system can be transformed into those in the robot reference frame, which guides the robot to perform its tasks.

Intrinsic parameters

Intrinsic parameters are measures of the properties of a camera itself, including the focal length, the lens distortion, etc. These parameters are usually calibrated and stored in the camera before the camera leaves the factory.

Extrinsic parameters

Extrinsic parameters define how poses are transformed between the camera reference frame and the world reference frame.

Euler angles

Euler angles are used to describe the orientation of an object in the 3D space. The object’s rotation in the 3D space can be denoted by 3 angles, i.e., pitch, yaw, and roll.

TCP (Tool Center Point)

Tool center point is the pinpoint at the end of the robot tool. In order to complete tasks such as picking, we usually say that the robot should move to a specific point in space, which actually means its TCP should move to that point.

Vision Processing

Point cloud

A point cloud is a set of data points in space that represents a 3D shape or object.


The position and orientation information that are used to guide the robot.


Specified images, shapes, or objects are usually selected to mask the image (partial or all) to control the area to process or the processing. The particular image or object used for masking is called a mask.

ROI (Region of Interest)

The region of interest excludes surrounding parts unnecessary for vision data processing in the scene. Such parts may be background objects, pallets, bin edges, etc.

Deep Learning

Model Package

After a model has been trained in Mech-DLK, it can be exported as a model package, which contains one or more models. In Mech-Vision, the model package can be used for the inference of the image data.

Super Model Package

A universal model provided by Mech-Mind used to recognize cartons or sacks. If the recognition performance is unsatisfactory, Mech-DLK can be used to fine-tune the model.

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.