Quality report Help - PIX4Dcloud

PIX4Dcloud generates a quality report that can be used to get an overview of the project and assess its accuracy and quality.

Access: Once the project is processed, the quality report can be accessed from:

Go to Files & Reports > Results to display the list of downloadable items.
Click Download on the quality report.

Input Summary

Project

Name of the project.

Camera Model Name(s)

The name of the camera model(s) used to capture the images.

Image input

Total images in the dataset.

Image Coordinate System

Coordinate the system of the image geolocation.

Project Coordinate System Name

Output horizontal and vertical coordinate reference system.

Project Coordinate System Type

The type of coordinate reference system in which all results will be exported.

Project Coordinate System Axes

The name and the unit of measurement of the coordinate reference system's axes.

Geoid Model

Geoid model used for processing.

Platform versions

The version of the software used to process the project.

Quality Check

Dataset

Number of images that have been calibrated, i.e., the number of images that have been used for the reconstruction of the model.

Text highlighted in green: More than 95% of images are calibrated.
Text highlighted in orange: Between 65% and 95% of images are calibrated.
Text highlighted in red: Less than 65% of images are calibrated.

Camera Optimization

Perspective lens: The percentage of difference between the initial and optimized focal length.

Text highlighted in green:
- Perspective lens: The percentage of the difference between initial and optimized focal length is less than 1%.
Text highlighted in orange:
- Perspective lens: The percentage of the difference between initial and optimized focal length is between 1% and 5%.
Text highlighted in red:
- Perspective lens: The percentage of the difference between initial and optimized focal length is equal/or more than 5%.Failed Processing Report: always displayed as the information is not available.

Median number of Matches per camera

The median of matches per calibrated image.

Text highlighted in green:
- More than 1,000 matches have been computed per calibrated image.
Text highlighted in orange:
- Between 100 and 1,000 matches have been computed per calibrated image.
Text highlighted in red:
- Less than 100 matches have been computed per calibrated image.

Median Number of Keypoints per camera

The median of keypoints per image. Keypoints are characteristic points that can be detected in the images.

Text highlighted in green:
- More than 10,000 keypoints have been extracted per image.
Text highlighted in orange:
- Between 500 and 10,000 keypoints have been extracted per image.
Text highlighted in red:
- Less than 500 keypoints have been extracted per image.

Average Ground Sampling Distance (GSD)

The average GSD of the images. For more information, Ground sampling distance (GSD).

Cameras calibrated

The number of images that have been calibrated, i.e., the number of images that have been used for the reconstruction.

Cameras geolocated

The number of images that are geotagged.

Number of Ray Cloud Points

The number of automatic tie points used for calibration.

Ground control points (GCPs)

Label

The name of the GCP.

Position error - X

The difference between the computed and the initial position of the ground control point in the X-axis, i.e., initial position - computed position.

Position error - Y

The difference between the computed and the initial position of the ground control point in the Y-axis, i.e., initial position - computed position.

Position error - Z

The difference between the computed and the initial position of the ground control point in the Z-axis, i.e., initial position - computed position.

Reprojection
error [px]

The average distance in the images where the GCP has been marked and where it has been re-projected is measured in pixels.

Marked

The images on which the GCP has been marked.

Mean

The mean/average position error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

Sigma

The standard deviation of the error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

RMS

The root mean square error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

3D Checkpoints (CPs)

Label

The name of the checkpoint.

Position error - X

The difference between the computed checkpoint and the original position in X direction (original position - computed position).

Position error - Y

The difference between the computed checkpoint and the original position in Y direction (original position - computed position).

Position error - Z

The difference between the computed checkpoint and the original position in Z direction (original position - computed position).

Reprojection
error [px]

The average distance in the images where the checkpoint has been marked and where it has been re-projected is measured in pixels.

Marked

The images on which the checkpoint has been marked.

Mean

The mean/average position error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

Sigma

The standard deviation of the error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

RMS

The root mean square error in each direction (X,Y,Z). For more information: How are the GCP Errors defined in the Quality Report?.

Internal Camera Parameters

Initial Values

The initial values of the camera model.

Optimized Values

The optimized values are computed from the camera calibration and are used to generate reconstructions.

Focal Length

The focal length of the camera's lens is in pixels and in millimeters.

Principal Point x

The x image coordinate of the principal point in pixels and in millimeters. The principal point is located around the center of the image. The coordinate system has its origin as displayed here:

Principal Point y

The y image coordinate of the principal point in pixels and in millimeters. The principal point is located around the center of the image. The coordinate system has its origin as displayed here:

Radial distortion of the lens R1.

Radial distortion of the lens R2.

Radial distortion of the lens R3.

Tangential distortion of the lens T1.

Tangential distortion of the lens T2.

Initial and Optimized Camera Positions with Capture Paths

Initial and computed camera positions.

Status

Blue - Indicates the initial position of a camera as extracted from the image EXIF.

Green - Indicates a computed position of a camera after the calibration step has been completed.

Red - Uncalibrated camera position (failed to calibrate).

Camera path

The line represents the shortest path traveled by the camera between each consecutive image.

Initial and Optimized Camera Positions with Links

Initial and computed camera, GCPs, and checkpoint positions.

Status

Blue - Indicates the initial position of a camera as extracted from the image EXIF.

Green - Indicates a computed position of a camera after the calibration step has been completed.

Red - Uncalibrated camera position (failed to calibrate).

Purple - GCPs' optimized positions.

Brown - 3D checkpoints' optimized positions.

Initial and optimized camera link

The line represents the relationship between each image's initial and optimized position.

2D Keypoint matches

Computed camera positions with links between matched cameras.

Number of matches

The weight of the links indicates the number of matched 2D keypoints between each pair of images. Lighter links indicate fewer matches, and darker links correspond with more matches.

3D Points from 2D Keypoint Matches

Number of 3D Points Observed in N Images

Each 3D point is derived from keypoints that have been observed in at least two images. Each row of this table displays the number of 3D points that have been observed in N images. The higher the image number in which a 3D point is visible, the higher its accuracy is.

Absolute Geolocation Variance

Min Error and Max Error represent geolocation error intervals between -1000 and 1000 on the project unit of measurement.

Geolocation Error X, Y, Z show the percentage of images with geolocation errors within the predefined error intervals. The geolocation error is the difference between the initial and optimized image positions. Note that the image geolocation errors do not correspond to the accuracy of the reconstructions.

Min Error [project units] / Max Error [project units]

The minimum and maximum errors represent the geolocation error intervals between -1000 and 1000 on the project unit of measurement.

Geolocation Error X [%]

The percentage of images with geolocation errors in the X direction within the predefined error intervals. The geolocation error is the difference between the camera's initial geolocations and their computed positions.

Geolocation error Y [%]

The percentage of images with geolocation errors in the Y direction within the predefined error intervals. The geolocation error is the difference between the camera's initial geolocations and their computed positions.

Geolocation error Z [%]

The percentage of images with geolocation errors in the Z direction within the predefined error intervals. The geolocation error is the difference between the camera's initial geolocations and their computed positions.

Mean

The mean/average error in each direction (X,Y,Z).

Sigma

The standard deviation of the error in each direction (X,Y,Z).

RMS error

The root mean square error in each direction (X,Y,Z).

Absolute Orientation Variances

Root mean square error of the image orientation. It is the difference between the initial image orientation and the optimized orientation. Note that the image orientation errors do not correspond to the accuracy of the reconstructions.

Min Error [degrees] / Max Error [degrees]

The minimum and maximum errors represent the orientation error intervals between 0 and 360 degrees.

Orientation Error Omega / Phi / Kappa [%]

The proportion of images in the dataset with an orientation error that is within the defined range of degrees.

Mean

The mean/average error in each rotation.

Sigma

The standard deviation of the error in each rotation.

RMS error

The root mean square error in each rotation.

Information: The sections Calibration & Reoptimization Settings, Densification Settings, Mesh Geometry & Texture Settings, and DSM and DTM Settings refer to the processing options used to calibrate the cameras and generate reconstructions.