Single Camera Correction

## Single Camera Correction

In a single-plane single-camera scenario, calculate the offset pose to correct the start position to the arrival position (teach position).

## Module Principle

Single camera correction is where all node data is acquired through one camera, so only one calibration is needed to convert image data into mechanical displacement.
Before connecting ports, the start position and arrival position need to be defined. It is the alignment of the start position to the arrival position; the start position is the position that needs to be moved.

![](/media/202603/2026-03-13_113536_8065670.05997920472080809.png)

Mechanical models are divided into XYR, XR, YR (with angle) and XY, X, Y (without angle) types. The calculation methods for the two types of correction are different. Correction with an angle requires the input calibration data to also be of the XYR, XR, YR type with an angle. Correction without an angle has no requirement for calibration.
There are three alignment methods: point pair, point plus angle, and point plus line. Among them, the point pair uses the SVD decomposition algorithm. Point plus angle and point plus line use the same algorithm; the line input will extract the line's angle and substitute it into the point plus angle algorithm to calculate the result.

### Multiple Alignment Shooting
Shooting Pose: The fixed position when the machine picks up the workpiece for shooting. When the machine type has an angle R, the shooting pose has a significant impact on the result.
**Alignment Completion Accuracy** is the mechanical accuracy. When the correction output is less than the alignment accuracy, the correction is successful. Otherwise, if the number of corrections is less than the set number, error code 1 will be output, and correction will continue.
Accumulated Offset is the result of accumulating multiple corrections when the maximum number of corrections is reached. It is the sum of the mechanical correction displacements (compensation will be added).

![](/media/202603/2026-03-13_113557_1986030.8067677640392769.png)

The mechanical range is the movable range of the mechanism. When the output actual coordinate exceeds the range, error code 5 will be output.

![](/media/202603/2026-03-13_113614_7299150.7964383528691137.png)

### Compensation Amount
For the compensation amount in a mechanical model with angle R, the compensated R will affect the XY values. (That is, if only R is compensated, the XY position where the robot arm picks the workpiece will not change, but the actual mechanical XY coordinates will change slightly to compensate for the rotation.) The compensation amount will be added to the result after the last correction ends. If the correction has not ended and needs to continue, the result output will not add compensation.
The compensation amount will not affect the judgment of the alignment completion accuracy of the correction.

## Usage Scenarios
Correction refers to the process of using the deviation of the real-time detected object relative to the preset target position (or reference line, reference point) captured by the camera, converting this image point information into mechanical point data, and driving the robot arm to perform real-time, dynamic adjustments to the object or its carrier, so that it accurately restores to the target position or runs along the predetermined trajectory. Simply put, the eyes (camera) find that something is crooked or deviated, and then tell the hand (actuator) to straighten it or pull it back.
Different from alignment, correction is correction on a single plane. Correction corrects the data acquired on the plane to the correct position on that plane. Alignment involves two planes and requires converting points on two planes to one plane (usually through mapping conversion) before correction calculation. Alignment corresponds point data on one plane to points on another plane. In the model, alignment will have twice as many cameras as correction because alignment involves two planes.

![](/media/202601/2026-01-16_095322_6984470.6527623670014461.png)
## Usage Method

### Pre/Post-Sequence Modules
Camera image acquisition, feature matching, circle extraction are used to obtain points or angles for correction. (Optimized feature matching is used to provide **position correction** for circle extraction.) Learning a reference target is used to record a standard position, generally used as the point of the arrival position for single camera correction. Subsequent points acquired will be corrected to the reference position learned by the learn reference target via single camera correction.

## Parameter Configuration Description
【Mechanical Model】 Select whether to rotate and whether X/Y are separated based on the application scenario.
【Alignment Method】 Select multi-point, point + angle, and point + line according to different feature extraction methods.
【Number of Point Pairs】 If point pair alignment method is selected, input the number of point pairs.

#### Advanced Parameters
【Shooting Pose】 The pose corresponding to the mechanical end when the camera can capture the material during the teaching process. Calibration Center Pose: The mechanical coordinate of the calibration center in the referenced calibration data. When the camera shoots, the robot arm end is at the calibration center position, this option can be selected; External Introduction: Shooting pose can be introduced via port; Manual Input: Shooting pose can be manually input.
【Max Alignment Times】 The maximum number of times alignment is allowed. If the alignment result does not reach the alignment completion accuracy and is still within the mechanical travel range, alignment continues until the maximum number of alignment times.
【Alignment Completion Accuracy】 Mechanical coordinates, the accuracy range that alignment needs to reach.
【Mechanical Travel】 Allowed travel range of the robot arm.
【Compensation Amount】 Mechanical coordinates, compensated in the mechanical coordinate system. When clicking subscribe, the compensation amount can be introduced via the port.
【Reference Image】 The image used as a reference during processing.

## Output Description

![](/media/202603/2026-03-13_113649_9277070.6720162486251506.png)

Accumulated Offset is the result of accumulating multiple corrections when the maximum number of corrections is reached. It is the sum of the mechanical correction displacements (compensation will be added).
The output has two sets: Pick Pose and Offset Pose. Pick Pose is the actual picking pose of the robot arm, which is also the judgment range for [Mechanical Travel]. Offset Pose is the offset of the robot arm relative to the teaching position and does not judge mechanical travel.
| Feature | Pick Pose | Offset Pose |
|---|---|---|
| Coordinate Type | Absolute Coordinate (GPS style) | Relative Coordinate (Reference object style) |
| Safety Check | Full check of mechanical travel | No range check |
| Main Function | Final execution position | Position fine-tuning |
| Analogy | Detailed delivery address | "Front left of you" |
| Dependency | Absolute Coordinate (GPS style) | Contains teach coordinates + offset based only on teach coordinates |

## Precautions
1. The calibration plane needs to be at the same height as the correction plane.
2. The calibration type needs to be the same as the type selected for correction.
3. Before connecting ports, the start position and arrival position need to be defined. It is the alignment of the start position to the arrival position; the start position is the position that needs to be moved.
   
## Error Troubleshooting
1. When correction is inaccurate, prioritize relearning the arrival position and testing again. (If the arrival position is the first workpiece, it is necessary to strengthen the supplemental correction to the correct position.)
2. Pay attention to whether the feature matching module acquires an accurate image.
3. If still unable to stabilize correction, test the accuracy of the calibration (the calibration module introduces testing).
4. If there is a large offset angle leading to inaccurate XY, it may be caused by an error in the calculation of the calibration rotation center. Try to recalibrate, modify the calibration method, and improve the calculation of the rotation center (add calibration verification or use the long radius calibration module).
5. If the correction is accurate in the center of the field of view but there is XY deviation around the periphery, consider image distortion (use the Image Distortion Correction module), or calibration scale calculation error (use the Calibration Correction module).

---

Click here to jump to the corresponding Chinese manual page: [Single Camera Correction](/doc/145)