diff options
Diffstat (limited to 'docs')
-rw-r--r-- | docs/user_guide/aruco_markers/camera_calibration.md | 91 | ||||
-rw-r--r-- | docs/user_guide/augmented_reality_pipeline/optic_parameters_calibration.md | 133 |
2 files changed, 133 insertions, 91 deletions
diff --git a/docs/user_guide/aruco_markers/camera_calibration.md b/docs/user_guide/aruco_markers/camera_calibration.md deleted file mode 100644 index ad28200..0000000 --- a/docs/user_guide/aruco_markers/camera_calibration.md +++ /dev/null @@ -1,91 +0,0 @@ -Camera calibration -================== - -Any camera device have to be calibrated to compensate its optical distorsion. - -![Camera calibration](../../img/camera_calibration.png) - -The first step to calibrate a camera is to create an [ArUcoBoard](../../argaze.md/#argaze.ArUcoMarkers.ArUcoBoard) like in the code below: - -``` python -from argaze.ArUcoMarkers import ArUcoMarkersDictionary, ArUcoBoard - -# Create ArUco dictionary -aruco_dictionary = ArUcoMarkersDictionary.ArUcoMarkersDictionary('DICT_APRILTAG_16h5') - -# Create an ArUco board of 7 columns and 5 rows with 5 cm squares with 3cm ArUco markers inside -aruco_board = ArUcoBoard.ArUcoBoard(7, 5, 5, 3, aruco_dictionary) - -# Export ArUco board with 300 dpi resolution -aruco_board.save('./calibration_board.png', 300) -``` - -Then, the calibration process needs to make many different captures of an [ArUcoBoard](../../argaze.md/#argaze.ArUcoMarkers.ArUcoBoard) through the camera and then, pass them to an [ArUcoDetector](../../argaze.md/#argaze.ArUcoMarkers.ArUcoDetector.ArUcoDetector) instance to detect board corners and store them as calibration data to an [ArUcoOpticCalibrator](../../argaze.md/#argaze.ArUcoMarkers.ArUcoOpticCalibrator) for final calibration process. - -![Calibration step](../../img/camera_calibration_step.png) - -The sample of code below shows how to detect board corners into camera images, store detected corners then process them to build calibration data and, finally, save it into a JSON file: - -``` python -from argaze.ArUcoMarkers import ArUcoMarkersDictionary, ArUcoOpticCalibrator, ArUcoBoard, ArUcoDetector - -# Create ArUco dictionary -aruco_dictionary = ArUcoMarkersDictionary.ArUcoMarkersDictionary('DICT_APRILTAG_16h5') - -# Create ArUco optic calibrator -aruco_optic_calibrator = ArUcoOpticCalibrator.ArUcoOpticCalibrator() - -# Create ArUco board of 7 columns and 5 rows with 5 cm squares with 3cm aruco markers inside -# Note: This board is the one expected during further board tracking -expected_aruco_board = ArUcoBoard.ArUcoBoard(7, 5, 5, 3, aruco_dictionary) - -# Create ArUco detector -aruco_detector = ArUcoDetector.ArUcoDetector(dictionary=aruco_dictionary, marker_size=3) - -# Capture images from a live Full HD video stream (1920x1080) -while video_stream.is_alive(): - - image = video_stream.read() - - # Detect all board corners in image - aruco_detector.detect_board(image, expected_aruco_board, expected_aruco_board.markers_number) - - # If board corners are detected - if aruco_detector.board_corners_number > 0: - - # Draw board corners to show that board tracking succeeded - aruco_detector.draw_board(image) - - # Append tracked board data for further calibration processing - aruco_optic_calibrator.store_calibration_data(aruco_detector.board_corners, aruco_detector.board_corners_identifier) - -# Start camera calibration processing for Full HD image resolution -print('Calibrating camera...') -optic_parameters = aruco_optic_calibrator.calibrate(aruco_board, dimensions=(1920, 1080)) - -if optic_parameters: - - print('\nCalibration succeeded!') - - print(f'\nRMS:\n{optic_parameters.rms}') - print(f'\nDimensions:\n{optic_parameters.dimensions[0]}x{optic_parameters.dimensions[1]}') - print(f'\nCamera matrix:\n{optic_parameters.K}') - print(f'\nDistortion coefficients:\n{optic_parameters.D}') - - optic_parameters.to_json(f'{args.output}/calibration.json') - - print(f'\ncalibration.json file exported into {args.output} folder') - -else: - - print('\nCalibration error.') -``` - -Then, the camera calibration data are loaded to compensate optical distorsion during [ArUcoMarkers](../../argaze.md/#argaze.ArUcoMarkers.ArUcoMarker) detection: - -``` python -from argaze.ArUcoMarkers import ArUcoOpticCalibrator - -# Load camera optic parameters -optic_parameters = ArUcoOpticCalibrator.OpticParameters.from_json('./calibration.json') -``` diff --git a/docs/user_guide/augmented_reality_pipeline/optic_parameters_calibration.md b/docs/user_guide/augmented_reality_pipeline/optic_parameters_calibration.md new file mode 100644 index 0000000..0561112 --- /dev/null +++ b/docs/user_guide/augmented_reality_pipeline/optic_parameters_calibration.md @@ -0,0 +1,133 @@ +Calibrate optic parameters +========================== + +A camera device have to be calibrated to compensate its optical distorsion. + +![Optic parameters calibration](../../img/optic_calibration.png) + +## Print calibration board + +The first step to calibrate a camera is to create an [ArUcoBoard](../../argaze.md/#argaze.ArUcoMarkers.ArUcoBoard) like in the code below: + +``` python +from argaze.ArUcoMarkers import ArUcoMarkersDictionary, ArUcoBoard + +# Create ArUco dictionary +aruco_dictionary = ArUcoMarkersDictionary.ArUcoMarkersDictionary('DICT_APRILTAG_16h5') + +# Create an ArUco board of 7 columns and 5 rows with 5 cm squares with 3cm ArUco markers inside +aruco_board = ArUcoBoard.ArUcoBoard(7, 5, 5, 3, aruco_dictionary) + +# Export ArUco board with 300 dpi resolution +aruco_board.save('./calibration_board.png', 300) +``` + +!!! note + There is **A3_DICT_APRILTAG_16h5_3cm_35cmx25cm.pdf** file located in *./src/argaze/ArUcoMarkers/utils/* folder ready to be printed on A3 paper sheet. + +Let's print the calibration board before to go further. + +## Capture board pictures + +Then, the calibration process needs to make many different captures of an [ArUcoBoard](../../argaze.md/#argaze.ArUcoMarkers.ArUcoBoard) through the camera and then, pass them to an [ArUcoDetector](../../argaze.md/#argaze.ArUcoMarkers.ArUcoDetector.ArUcoDetector) instance to detect board corners and store them as calibration data into an [ArUcoOpticCalibrator](../../argaze.md/#argaze.ArUcoMarkers.ArUcoOpticCalibrator) for final calibration process. + +![Calibration step](../../img/optic_calibration_step.png) + +The sample of code below illustrates how to: + +* load all required ArGaze objects, +* detect board corners into a Full HD camera video stream, +* store detected corners as calibration data then, +* once enough captures are made, process them to find optic parameters and, +* finally, save optic parameters into a JSON file. + +``` python +from argaze.ArUcoMarkers import ArUcoMarkersDictionary, ArUcoOpticCalibrator, ArUcoBoard, ArUcoDetector + +# Create ArUco dictionary +aruco_dictionary = ArUcoMarkersDictionary.ArUcoMarkersDictionary('DICT_APRILTAG_16h5') + +# Create ArUco optic calibrator +aruco_optic_calibrator = ArUcoOpticCalibrator.ArUcoOpticCalibrator() + +# Create ArUco board of 7 columns and 5 rows with 5 cm squares with 3cm aruco markers inside +# Note: This board is the one expected during further board tracking +expected_aruco_board = ArUcoBoard.ArUcoBoard(7, 5, 5, 3, aruco_dictionary) + +# Create ArUco detector +aruco_detector = ArUcoDetector.ArUcoDetector(dictionary=aruco_dictionary, marker_size=3) + +# Assuming that live Full HD (1920x1080) video stream is enabled +... + +# Assuming there is a way to escape the while loop +... + + # Capture images from video stream + while video_stream.is_alive(): + + image = video_stream.read() + + # Detect all board corners in image + aruco_detector.detect_board(image, expected_aruco_board, expected_aruco_board.markers_number) + + # If all board corners are detected + if aruco_detector.board_corners_number == expected_aruco_board.corners_number: + + # Draw board corners to show that board tracking succeeded + aruco_detector.draw_board(image) + + # Append tracked board data for further calibration processing + aruco_optic_calibrator.store_calibration_data(aruco_detector.board_corners, aruco_detector.board_corners_identifier) + +# Start optic calibration processing for Full HD image resolution +print('Calibrating optic...') +optic_parameters = aruco_optic_calibrator.calibrate(aruco_board, dimensions=(1920, 1080)) + +if optic_parameters: + + # Export optic parameters + optic_parameters.to_json('./optic_parameters.json') + + print('Calibration succeeded: optic_parameters.json file exported.') + +else: + + print('Calibration failed.') +``` + +Below, an optic_parameters JSON file example: + +```json +{ + "rms": 0.6688921504088245, + "dimensions": [ + 1920, + 1080 + ], + "K": [ + [ + 1135.6524381415752, + 0.0, + 956.0685325355497 + ], + [ + 0.0, + 1135.9272506869524, + 560.059099810324 + ], + [ + 0.0, + 0.0, + 1.0 + ] + ], + "D": [ + 0.01655492265003404, + 0.1985524264972037, + 0.002129965902489484, + -0.0019528582922179365, + -0.5792910353639452 + ] +} +``` |