diff options
author | Théo de la Hogue | 2024-04-10 15:13:12 +0200 |
---|---|---|
committer | Théo de la Hogue | 2024-04-10 15:13:12 +0200 |
commit | 03013286100d4a3cc49439afc6f432f7be0c494b (patch) | |
tree | 3615506f50381208bd4d327d61a49440143d6ffe /docs/user_guide/aruco_marker_pipeline/advanced_topics | |
parent | bcfb82055c1736262ce974dc5dd10b365dda8d5c (diff) | |
download | argaze-03013286100d4a3cc49439afc6f432f7be0c494b.zip argaze-03013286100d4a3cc49439afc6f432f7be0c494b.tar.gz argaze-03013286100d4a3cc49439afc6f432f7be0c494b.tar.bz2 argaze-03013286100d4a3cc49439afc6f432f7be0c494b.tar.xz |
orthographic corrections
Diffstat (limited to 'docs/user_guide/aruco_marker_pipeline/advanced_topics')
3 files changed, 359 insertions, 0 deletions
diff --git a/docs/user_guide/aruco_marker_pipeline/advanced_topics/aruco_detector_configuration.md b/docs/user_guide/aruco_marker_pipeline/advanced_topics/aruco_detector_configuration.md new file mode 100644 index 0000000..410e2d7 --- /dev/null +++ b/docs/user_guide/aruco_marker_pipeline/advanced_topics/aruco_detector_configuration.md @@ -0,0 +1,37 @@ +Improve ArUco markers detection +=============================== + +As explain in [OpenCV ArUco documentation](https://docs.opencv.org/4.x/d1/dcd/structcv_1_1aruco_1_1DetectorParameters.html), ArUco markers detection is highly configurable. + +## Load ArUcoDetector parameters + +[ArUcoCamera.detector.parameters](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoDetector.Parameters) can be loaded thanks to a dedicated JSON entry. + +Here is an extract from the JSON [ArUcoCamera](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoCamera) configuration file with ArUco detector parameters: + +```json +{ + "name": "My FullHD camera", + "size": [1920, 1080], + "aruco_detector": { + "dictionary": "DICT_APRILTAG_16h5", + "parameters": { + "adaptiveThreshConstant": 10, + "useAruco3Detection": 1 + } + }, + ... +``` + +## Print ArUcoDetector parameters + +```python +# Assuming ArUcoCamera is loaded +... + +# Print all ArUcoDetector parameters +print(aruco_camera.aruco_detector.parameters) + +# Print only modified ArUcoDetector parameters +print(f'{aruco_camera.aruco_detector.parameters:modified}') +``` diff --git a/docs/user_guide/aruco_marker_pipeline/advanced_topics/optic_parameters_calibration.md b/docs/user_guide/aruco_marker_pipeline/advanced_topics/optic_parameters_calibration.md new file mode 100644 index 0000000..54d0c94 --- /dev/null +++ b/docs/user_guide/aruco_marker_pipeline/advanced_topics/optic_parameters_calibration.md @@ -0,0 +1,190 @@ +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) + +# Assuming that live Full HD (1920x1080) video stream is enabled +... + +# Assuming there is a way to escape the while loop +... + + while video_stream.is_alive(): + + # Capture image from video stream + 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(expected_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 + ] +} +``` + +## Load and display optic parameters + +[ArUcoCamera.detector.optic_parameters](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoOpticCalibrator.OpticParameters) can be enabled thanks to a dedicated JSON entry. + +Here is an extract from the JSON [ArUcoCamera](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoCamera) configuration file where optic parameters are loaded and displayed: + +```json +{ + "name": "My FullHD Camera", + "size": [1920, 1080], + "aruco_detector": { + "dictionary": "DICT_APRILTAG_16h5", + "optic_parameters": { + "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 + ] + } + }, + ... + "image_parameters": { + ... + "draw_optic_parameters_grid": { + "width": 192, + "height": 108, + "z": 100, + "point_size": 1, + "point_color": [0, 0, 255] + } + } +```
\ No newline at end of file diff --git a/docs/user_guide/aruco_marker_pipeline/advanced_topics/scripting.md b/docs/user_guide/aruco_marker_pipeline/advanced_topics/scripting.md new file mode 100644 index 0000000..2eb64f8 --- /dev/null +++ b/docs/user_guide/aruco_marker_pipeline/advanced_topics/scripting.md @@ -0,0 +1,132 @@ +Script the pipeline +=================== + +All aruco markers pipeline objects are accessible from Python script. +This could be particularly useful for realtime AR interaction applications. + +## Load ArUcoCamera configuration from dictionary + +First of all, [ArUcoCamera](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoCamera) configuration can be loaded from a python dictionary. + +```python +from argaze.ArUcoMarkers import ArUcoCamera + +# Edit a dict with ArUcoCamera configuration +configuration = { + "name": "My FullHD camera", + "size": (1920, 1080), + ... + "aruco_detector": { + ... + }, + "scenes": { + "MyScene" : { + "aruco_markers_group": { + ... + }, + "layers": { + "MyLayer": { + "aoi_scene": { + ... + } + }, + ... + } + }, + ... + } + "layers": { + "MyLayer": { + ... + }, + ... + }, + "image_parameters": { + ... + } +} + +# Load ArUcoCamera +aruco_camera = ArUcoCamera.ArUcoCamera.from_dict(configuration) + +# Do something with ArUcoCamera +... +``` + +## Access to ArUcoCamera and ArScenes attributes + +Then, once the configuration is loaded, it is possible to access to its attributes: [read ArUcoCamera code reference](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoCamera) to get a complete list of what is available. + +Thus, the [ArUcoCamera.scenes](../../../argaze.md/#argaze.ArFeatures.ArCamera) attribute allows to access each loaded aruco scene and so, access to their attributes: [read ArUcoScene code reference](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) to get a complete list of what is available. + +```python +from argaze import ArFeatures + +# Assuming the ArUcoCamera is loaded +... + +# Iterate over each ArUcoCamera scene +for name, aruco_scene in aruco_camera.scenes.items(): + ... +``` + +## Pipeline execution outputs + +[ArUcoCamera.watch](../../../argaze.md/#argaze.ArFeatures.ArCamera.watch) method returns data about pipeline execution. + +```python +# Assuming that timestamped images are available +...: + + try: + + # Watch image with ArUco camera + aruco_camera.watch(image, timestamp=timestamp) + + # Do something with pipeline exception + except Exception as e: + + ... + + # Do something with detected_markers + ... aruco_camera.aruco_detector.detected_markers() + +``` + +Let's understand the meaning of each returned data. + +### *aruco_camera.aruco_detector.detected_markers()* + +A dictionary containing all detected markers provided by [ArUcoDetector](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoDetector) class. + +## Setup ArUcoCamera image parameters + +Specific [ArUcoCamera.image](../../../argaze.md/#argaze.ArFeatures.ArFrame.image) method parameters can be configured thanks to a Python dictionary. + +```python +# Assuming ArUcoCamera is loaded +... + +# Edit a dict with ArUcoCamera image parameters +image_parameters = { + "draw_detected_markers": { + ... + }, + "draw_scenes": { + ... + }, + "draw_optic_parameters_grid": { + ... + }, + ... +} + +# Pass image parameters to ArUcoCamera +aruco_camera_image = aruco_camera.image(**image_parameters) + +# Do something with ArUcoCamera image +... +``` + +!!! note + [ArUcoCamera](../../../argaze.md/#argaze.ArUcoMarkers.ArUcoCamera) inherits from [ArFrame](../../../argaze.md/#argaze.ArFeatures.ArFrame) and so, benefits from all image parameters described in [gaze analysis pipeline visualisation section](../../gaze_analysis_pipeline/visualisation.md).
\ No newline at end of file |