sports2d 0.8.19__py3-none-any.whl → 0.8.20__py3-none-any.whl

Sports2D/Demo/Config_demo.toml

@@ -60,8 +60,8 @@ pose_model = 'Body_with_feet'  #With RTMLib:
                          # - Hand (HAND_21, only lightweight mode. Potentially better results with Whole_body), 
                          # - Face (FACE_106), 
                          # - Animal (ANIMAL2D_17)
-                         # /!\ Only RTMPose is natively embeded in Pose2Sim. For all other pose estimation methods, you will have to run them yourself, and then refer to the documentation to convert the output files if needed
-                         # /!\ For Face and Animal, use mode="""{dictionary}""", and find the corresponding .onnx model there https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
+                         # ⚠ Only RTMPose is natively embeded in Pose2Sim. For all other pose estimation methods, you will have to run them yourself, and then refer to the documentation to convert the output files if needed
+                         # ⚠ For Face and Animal, use mode="""{dictionary}""", and find the corresponding .onnx model there https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
 mode = 'balanced' # 'lightweight', 'balanced', 'performance', or """{dictionary}""" (see below)
 
 # A dictionary (WITHIN THREE DOUBLE QUOTES) allows you to manually select the person detection (if top_down approach) and/or pose estimation models (see https://github.com/Tau-J/rtmlib). 
@@ -139,6 +139,7 @@ reject_outliers = true      # Hampel filter for outlier rejection before other f
 
 filter = true
 show_graphs = true         # Show plots of raw and processed results
+save_graphs = false        # Save position and angle plots of raw and processed results
 filter_type = 'butterworth'     # butterworth, kalman, gcv_spline, gaussian, loess, median, butterworth_on_speed
    
    # Most intuitive and standard filter in biomechanics

Sports2D/Sports2D.py

@@ -28,7 +28,7 @@
     - Run on webcam with default parameters: 
         sports2d --video_input webcam
     - Run with custom parameters (all non specified are set to default): 
-        sports2d --show_plots False --time_range 0 2.1 --result_dir path_to_result_dir
+        sports2d --show_graphs False --time_range 0 2.1 --result_dir path_to_result_dir
         sports2d --person_detection_method highest_likelihood --mode lightweight --det_frequency 50
     - Run with a toml configuration file: 
         sports2d --config path_to_config.toml
@@ -44,7 +44,7 @@
     pip install .
     
     -----
-    /!\ Warning /!\
+    ⚠ Warning ⚠
     -----
     - The angle estimation is only as good as the pose estimation algorithm, i.e., it is not perfect.
     - It will only lead to acceptable results if the persons move in the 2D plane (sagittal plane).
@@ -236,6 +236,7 @@ DEFAULT_CONFIG =   {'base': {'video_input': ['demo.mp4'],
                                         'reject_outliers': True,
                                         'filter': True,
                                         'show_graphs': True,
+                                        'save_graphs': False,
                                         'filter_type': 'butterworth',
                                         'butterworth': {'order': 4, 'cut_off_frequency': 6.0},
                                         'kalman': {'trust_ratio': 500.0, 'smooth':True},
@@ -279,6 +280,7 @@ CONFIG_HELP =   {'config': ["C", "path to a toml configuration file"],
                 'show_realtime_results': ["R", "show results in real-time. true if not specified"],
                 'display_angle_values_on': ["a", '"body", "list", "body" "list", or "none". body list if not specified'],
                 'show_graphs': ["G", "show plots of raw and processed results. true if not specified"],
+                'save_graphs': ["", "save position and angle plots of raw and processed results. false if not specified"],
                 'joint_angles': ["j", '"Right ankle" "Left ankle" "Right knee" "Left knee" "Right hip" "Left hip" "Right shoulder" "Left shoulder" "Right elbow" "Left elbow" if not specified'],
                 'segment_angles': ["s", '"Right foot" "Left foot" "Right shank" "Left shank" "Right thigh" "Left thigh" "Pelvis" "Trunk" "Shoulders" "Head" "Right arm" "Left arm" "Right forearm" "Left forearm" if not specified'],
                 'save_vid': ["V", "save processed video. true if not specified"],
@@ -546,7 +548,7 @@ def main():
     - Run on webcam with default parameters: 
         sports2d --video_input webcam
     - Run with custom parameters (all non specified are set to default): 
-        sports2d --show_plots False --time_range 0 2.1 --result_dir path_to_result_dir
+        sports2d --show_graphs False --time_range 0 2.1 --result_dir path_to_result_dir
         sports2d --mode lightweight --det_frequency 50
     - Run with a toml configuration file: 
         sports2d --config path_to_config.toml

Sports2D/process.py

@@ -29,7 +29,7 @@
     - optionally plots pose and angle data before and after processing for comparison
     - optionally saves poses for each person as a trc file, and angles as a mot file
         
-    /!\ Warning /!\
+    ⚠ Warning ⚠ 
     - The pose detection is only as good as the pose estimation algorithm, i.e., it is not perfect.
     - It will lead to reliable results only if the persons move in the 2D plane (sagittal or frontal plane).
     - The persons need to be filmed as perpendicularly as possible from their side.
@@ -77,6 +77,7 @@ from matplotlib.widgets import Slider, Button
 from matplotlib import patheffects
 
 from rtmlib import PoseTracker, BodyWithFeet, Wholebody, Body, Hand, Custom
+from rtmlib.tools.object_detection.post_processings import nms
 from deep_sort_realtime.deepsort_tracker import DeepSort
 
 from Sports2D.Utilities.common import *
@@ -789,10 +790,10 @@ def make_mot_with_angles(angles, time, mot_path):
     return angles
 
 
-def pose_plots(trc_data_unfiltered, trc_data, person_id):
+def pose_plots(trc_data_unfiltered, trc_data, person_id, show=True):
     '''
     Displays trc filtered and unfiltered data for comparison
-    /!\ Often crashes on the third window...
+    ⚠ Often crashes on the third window...
 
     INPUTS:
     - trc_data_unfiltered: pd.DataFrame. The unfiltered trc data
@@ -835,13 +836,16 @@ def pose_plots(trc_data_unfiltered, trc_data, person_id):
 
         pw.addPlot(keypoint, f)
     
-    pw.show()
+    if show:
+        pw.show()
 
+    return pw
 
-def angle_plots(angle_data_unfiltered, angle_data, person_id):
+
+def angle_plots(angle_data_unfiltered, angle_data, person_id, show=True):
     '''
     Displays angle filtered and unfiltered data for comparison
-    /!\ Often crashes on the third window...
+    ⚠ Often crashes on the third window...
 
     INPUTS:
     - angle_data_unfiltered: pd.DataFrame. The unfiltered angle data
@@ -878,7 +882,10 @@ def angle_plots(angle_data_unfiltered, angle_data, person_id):
 
         pw.addPlot(angle, f)
 
-    pw.show()
+    if show:
+        pw.show()
+
+    return pw
 
 
 def get_personIDs_with_highest_scores(all_frames_scores, nb_persons_to_detect):
@@ -1374,7 +1381,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     - optionally plots pose and angle data before and after processing for comparison
     - optionally saves poses for each person as a trc file, and angles as a mot file
         
-    /!\ Warning /!\d
+    ⚠ Warning ⚠ 
     - The pose detection is only as good as the pose estimation algorithm, i.e., it is not perfect.
     - It will lead to reliable results only if the persons move in the 2D plane (sagittal or frontal plane).
     - The persons need to be filmed as perpendicularly as possible from their side.
@@ -1490,6 +1497,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     handle_LR_swap = config_dict.get('post-processing').get('handle_LR_swap', False)
     reject_outliers = config_dict.get('post-processing').get('reject_outliers', False)
     show_plots = config_dict.get('post-processing').get('show_graphs')
+    save_plots = config_dict.get('post-processing').get('save_graphs')
     filter_type = config_dict.get('post-processing').get('filter_type')
     butterworth_filter_order = config_dict.get('post-processing').get('butterworth', {}).get('order')
     butterworth_filter_cutoff = config_dict.get('post-processing').get('butterworth', {}).get('cut_off_frequency')
@@ -1513,6 +1521,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
         output_dir_name = f'{video_file_stem}_Sports2D'    
         video_file_path = video_dir / video_file
     output_dir = result_dir / output_dir_name
+    plots_output_dir = output_dir / f'{output_dir_name}_graphs'
     img_output_dir = output_dir / f'{output_dir_name}_img'
     vid_output_path = output_dir / f'{output_dir_name}.mp4'
     pose_output_path = output_dir / f'{output_dir_name}_px.trc'
@@ -1521,6 +1530,8 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     output_dir.mkdir(parents=True, exist_ok=True)
     if save_img:
         img_output_dir.mkdir(parents=True, exist_ok=True)
+    if save_plots:
+        plots_output_dir.mkdir(parents=True, exist_ok=True)
 
     # Inverse kinematics settings
     do_ik = config_dict.get('kinematics').get('do_ik')
@@ -1721,6 +1732,13 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 # Detect poses
                 keypoints, scores = pose_tracker(frame)
 
+                # Non maximum suppression (at pose level, not detection)
+                frame_shape = frame.shape
+                bboxes = bbox_xyxy_compute(frame_shape, keypoints, padding=0)
+                score_bboxes = np.array([np.mean(s) for s in scores])
+                keep = nms(bboxes, score_bboxes, nms_thr=0.45)
+                keypoints, scores = keypoints[keep], scores[keep]
+                
                 # Track poses across frames
                 if tracking_mode == 'deepsort':
                     keypoints, scores = sort_people_deepsort(keypoints, scores, deepsort_tracker, frame, frame_count)
@@ -1999,9 +2017,17 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                     columns_to_concat.extend([all_frames_X_person.iloc[:,kpt], all_frames_Y_person.iloc[:,kpt], all_frames_Z_homog.iloc[:,kpt]])
                 trc_data_unfiltered_i = pd.concat([all_frames_time] + columns_to_concat, axis=1)
                 trc_data_unfiltered.append(trc_data_unfiltered_i)
-                if show_plots and not to_meters:
-                    pose_plots(trc_data_unfiltered_i, trc_data_i, i)
-                
+                if not to_meters and (show_plots or save_plots):
+                    pw = pose_plots(trc_data_unfiltered_i, trc_data_i, i, show=show_plots)
+                    if save_plots:
+                        for n, f in enumerate(pw.figure_handles):
+                            dpi = pw.canvases[i].figure.dpi
+                            f.set_size_inches(1280/dpi, 720/dpi)
+                            title = pw.tabs.tabText(n)
+                            plot_path = plots_output_dir / (pose_output_path.stem + f'_person{i:02d}_px_{title.replace(" ","_").replace("/","_")}.png')
+                            f.savefig(plot_path, dpi=dpi, bbox_inches='tight')
+                        logging.info(f'Pose plots (px) saved in {plots_output_dir}.')
+                        
                 all_frames_X_processed[:,idx_person,:], all_frames_Y_processed[:,idx_person,:] = all_frames_X_person_filt, all_frames_Y_person_filt
                 if calculate_angles or save_angles:
                     all_frames_X_flipped_processed[:,idx_person,:] = all_frames_X_flipped_person
@@ -2087,9 +2113,17 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                     px_to_m_unfiltered_i = [convert_px_to_meters(trc_data_unfiltered[i][kpt_name], first_person_height, height_px, cx, cy, -floor_angle_estim) for kpt_name in new_keypoints_names]
                     trc_data_unfiltered_m_i = pd.concat([all_frames_time.rename('time')]+px_to_m_unfiltered_i, axis=1)
 
-                    if to_meters and show_plots:
-                        pose_plots(trc_data_unfiltered_m_i, trc_data_m_i, i)
-                    
+                    if to_meters and (show_plots or save_plots):
+                        pw = pose_plots(trc_data_unfiltered_m_i, trc_data_m_i, i, show=show_plots)
+                        if save_plots:
+                            for n, f in enumerate(pw.figure_handles):
+                                dpi = pw.canvases[i].figure.dpi
+                                f.set_size_inches(1280/dpi, 720/dpi)
+                                title = pw.tabs.tabText(n)
+                                plot_path = plots_output_dir / (pose_output_path_m.stem + f'_person{i:02d}_m_{title.replace(" ","_").replace("/","_")}.png')
+                                f.savefig(plot_path, dpi=dpi, bbox_inches='tight')
+                            logging.info(f'Pose plots (m) saved in {plots_output_dir}.')
+
                     # Write to trc file
                     trc_data_m.append(trc_data_m_i)
                     pose_path_person_m_i = (pose_output_path.parent / (pose_output_path_m.stem + f'_person{i:02d}.trc'))
@@ -2248,9 +2282,16 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 logging.info(f'Angles saved to {angles_path_person.resolve()}.')
 
                 # Plotting angles before and after interpolation and filtering
-                if show_plots:
-                    all_frames_angles_person.insert(0, 'time', all_frames_time)
-                    angle_plots(all_frames_angles_person, angle_data, i) # i = current person
+                all_frames_angles_person.insert(0, 'time', all_frames_time)
+                if save_plots and (show_plots or save_plots):
+                    pw = angle_plots(all_frames_angles_person, angle_data, i, show=show_plots) # i = current person
+                    for n, f in enumerate(pw.figure_handles):
+                        dpi = pw.canvases[i].figure.dpi
+                        f.set_size_inches(1280/dpi, 720/dpi)
+                        title = pw.tabs.tabText(n)
+                        plot_path = plots_output_dir / (pose_output_path_m.stem + f'_person{i:02d}_ang_{title.replace(" ","_").replace("/","_")}.png')
+                        f.savefig(plot_path, dpi=dpi, bbox_inches='tight')
+                    logging.info(f'Pose plots (m) saved in {plots_output_dir}.')
 
 
     #%% ==================================================

{sports2d-0.8.19.dist-info → sports2d-0.8.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sports2d
-Version: 0.8.19
+Version: 0.8.20
 Summary: Compute 2D human pose and angles from a video or a webcam.
 Author-email: David Pagnon <contact@david-pagnon.com>
 Maintainer-email: David Pagnon <contact@david-pagnon.com>
@@ -38,7 +38,7 @@ Requires-Dist: openvino
 Requires-Dist: opencv-python<4.12
 Requires-Dist: imageio_ffmpeg
 Requires-Dist: deep-sort-realtime
-Requires-Dist: Pose2Sim>=0.10.33
+Requires-Dist: Pose2Sim>=0.10.36
 Dynamic: license-file
 
 

{sports2d-0.8.19.dist-info → sports2d-0.8.20.dist-info}/RECORD

@@ -9,17 +9,17 @@ Content/paper.md,sha256=8rWSOLrKTysloZv0Fz2lr3nayxtHi7GlFMqwdgDVggY,11333
 Content/sports2d_blender.gif,sha256=wgMuPRxhja3XtQn76_okGXsNnUT9Thp0pnD36GdW5_E,448786
 Content/sports2d_opensim.gif,sha256=XP1AcjqhbGcJknXUoNJjPWAwaM9ahZafbDgLWvzKJs4,376656
 Sports2D/Sports2D.ipynb,sha256=VnOVjIl6ndnCJTT13L4W5qTw4T-TQDF3jt3-wxnXDqM,2427047
-Sports2D/Sports2D.py,sha256=3Mcc_jFaD5Zv4ArB-jKYhgpMlFT0XBifTlSe70volzk,35385
+Sports2D/Sports2D.py,sha256=aCx3Hy1XltgBS7kuQ52b653hQtL_9sjvpQ0xGoPuoOw,35572
 Sports2D/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
-Sports2D/process.py,sha256=hw9En4j6ROPmow0YmPK8Ohuc8Li8CoEEUXdtUTN_5zg,122898
-Sports2D/Demo/Config_demo.toml,sha256=YescEgeQq3ojGqEAFWgXN142HL-YaVcRty9LbJgScoM,15577
+Sports2D/process.py,sha256=VrN8ZQimznjPAk_-1r9NpZnBCzDz9z0lV-E4wNJMCq0,125549
+Sports2D/Demo/Config_demo.toml,sha256=GXlj4tuGvnEpzQm0FFOS2BWVHcGSHGxuudAAHhzsTQc,15665
 Sports2D/Demo/demo.mp4,sha256=2aZkFxhWR7ESMEtXCT8MGA83p2jmoU2sp1ylQfO3gDk,3968304
 Sports2D/Utilities/__init__.py,sha256=BuUkPEdItxlkeqz4dmoiPwZLkgAfABJK3KWQ1ujTGwE,153
 Sports2D/Utilities/common.py,sha256=idMRmesFv5BPX-5g3z5dOVa7SpS_8tNgijvGrOZlR-k,11185
 Sports2D/Utilities/tests.py,sha256=bUcPoaIwa6ur13Njup5MjGY3N060Ropl_MCdAbCAbTc,4792
-sports2d-0.8.19.dist-info/licenses/LICENSE,sha256=f4qe3nE0Y7ltJho5w-xAR0jI5PUox5Xl-MsYiY7ZRM8,1521
-sports2d-0.8.19.dist-info/METADATA,sha256=F5rmn0eQhNwzk_6IYmY8nrtPZv7NHFCqgcnGeAdYHhI,41277
-sports2d-0.8.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sports2d-0.8.19.dist-info/entry_points.txt,sha256=V8dFDIXatz9VvoGgoHzb2wE71C9-f85K6_OjnEQlxww,108
-sports2d-0.8.19.dist-info/top_level.txt,sha256=cWWBiDD2WbQXMoIoN6-9et9U2t2c_ZKo2JtBqO5uN-k,17
-sports2d-0.8.19.dist-info/RECORD,,
+sports2d-0.8.20.dist-info/licenses/LICENSE,sha256=f4qe3nE0Y7ltJho5w-xAR0jI5PUox5Xl-MsYiY7ZRM8,1521
+sports2d-0.8.20.dist-info/METADATA,sha256=PX4DMmISr1ZnSSKNHFqGF6F97_SuZBAPV5OOe8tgTPU,41277
+sports2d-0.8.20.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sports2d-0.8.20.dist-info/entry_points.txt,sha256=V8dFDIXatz9VvoGgoHzb2wE71C9-f85K6_OjnEQlxww,108
+sports2d-0.8.20.dist-info/top_level.txt,sha256=cWWBiDD2WbQXMoIoN6-9et9U2t2c_ZKo2JtBqO5uN-k,17
+sports2d-0.8.20.dist-info/RECORD,,