sports2d 0.7.0__tar.gz → 0.7.3__tar.gz

{sports2d-0.7.0 → sports2d-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: sports2d
-Version: 0.7.0
+Version: 0.7.3
 Summary: Detect pose and compute 2D joint angles from a video.
 Home-page: https://github.com/davidpagnon/Sports2D
 Author: David Pagnon
@@ -40,6 +40,7 @@ Requires-Dist: tqdm
 Requires-Dist: imageio_ffmpeg
 Requires-Dist: deep-sort-realtime
 Requires-Dist: Pose2Sim
+Dynamic: license-file
 
 
 [![Continuous integration](https://github.com/davidpagnon/sports2d/actions/workflows/continuous-integration.yml/badge.svg?branch=main)](https://github.com/davidpagnon/sports2d/actions/workflows/continuous-integration.yml)
@@ -81,7 +82,10 @@ Works on any smartphone!**\
 
 </br>
 
-https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e
+
+https://github.com/user-attachments/assets/6a444474-4df1-4134-af0c-e9746fa433ad
+
+<!-- https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e -->
 
 `Warning:` Angle estimation is only as good as the pose estimation algorithm, i.e., it is not perfect.\
 `Warning:` Results are acceptable only if the persons move in the 2D plane (sagittal or frontal plane). The persons need to be filmed as parallel as possible to the motion plane.\
@@ -465,7 +469,7 @@ sports2d --help
 'participant_mass': ["", "mass of the participant in kg or none. Defaults to 70 if not provided. No influence on kinematics (motion), only on kinetics (forces)"],
 'close_to_zero_speed_m': ["","Sum for all keypoints: about 50 px/frame or 0.2 m/frame"], 
 'multiperson': ["", "multiperson involves tracking: will be faster if set to false. true if not specified"],
-'tracking_mode': ["", "sports2d or rtmlib. sports2d is generally much more accurate and comparable in speed. sports2d if not specified"],
+'tracking_mode': ["", "'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned"],
 'deepsort_params': ["", 'Deepsort tracking parameters: """{dictionary between 3 double quotes}""". \n\
                     Default: max_age:30, n_init:3, nms_max_overlap:0.8, max_cosine_distance:0.3, nn_budget:200, max_iou_distance:0.8, embedder_gpu: True\n\
                     More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51'],

{sports2d-0.7.0 → sports2d-0.7.3}/README.md

@@ -38,7 +38,10 @@ Works on any smartphone!**\
 
 </br>
 
-https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e
+
+https://github.com/user-attachments/assets/6a444474-4df1-4134-af0c-e9746fa433ad
+
+<!-- https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e -->
 
 `Warning:` Angle estimation is only as good as the pose estimation algorithm, i.e., it is not perfect.\
 `Warning:` Results are acceptable only if the persons move in the 2D plane (sagittal or frontal plane). The persons need to be filmed as parallel as possible to the motion plane.\
@@ -422,7 +425,7 @@ sports2d --help
 'participant_mass': ["", "mass of the participant in kg or none. Defaults to 70 if not provided. No influence on kinematics (motion), only on kinetics (forces)"],
 'close_to_zero_speed_m': ["","Sum for all keypoints: about 50 px/frame or 0.2 m/frame"], 
 'multiperson': ["", "multiperson involves tracking: will be faster if set to false. true if not specified"],
-'tracking_mode': ["", "sports2d or rtmlib. sports2d is generally much more accurate and comparable in speed. sports2d if not specified"],
+'tracking_mode': ["", "'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned"],
 'deepsort_params': ["", 'Deepsort tracking parameters: """{dictionary between 3 double quotes}""". \n\
                     Default: max_age:30, n_init:3, nms_max_overlap:0.8, max_cosine_distance:0.3, nn_budget:200, max_iou_distance:0.8, embedder_gpu: True\n\
                     More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51'],

{sports2d-0.7.0 → sports2d-0.7.3}/Sports2D/Demo/Config_demo.toml

@@ -89,7 +89,7 @@ det_frequency = 4       # Run person detection only every N frames, and inbetwee
                         # Equal to or greater than 1, can be as high as you want in simple uncrowded cases. Much faster, but might be less accurate. 
 device = 'auto' # 'auto', 'CPU', 'CUDA', 'MPS', 'ROCM'
 backend = 'auto' # 'auto', 'openvino', 'onnxruntime', 'opencv'
-tracking_mode = 'sports2d' # 'sports2d' or 'deepsort'. 'deepsort' is slower but more robust in difficult configurations
+tracking_mode = 'sports2d' # 'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned
 # deepsort_params = """{'max_age':30, 'n_init':3, 'max_cosine_distance':0.3, 'max_iou_distance':0.8, 'embedder_gpu': True, embedder':'torchreid'}""" # """{dictionary between 3 double quotes}"""
                   # More robust in crowded scenes but tricky to parametrize. More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51
                   # Requires `pip install torch torchvision torchreid gdown tensorboard`
@@ -151,8 +151,8 @@ filter_type = 'butterworth'   # butterworth, gaussian, LOESS, median
 
 
 [kinematics]
-do_ik = true # Do scaling and inverse kinematics?
-use_augmentation = true  # true or false (lowercase) # Set to true if you want to use the model with augmented markers
+do_ik = false # Do scaling and inverse kinematics?
+use_augmentation = false  # true or false (lowercase) # Set to true if you want to use the model with augmented markers
 use_contacts_muscles = true # true or false (lowercase) # If true, contact spheres and muscles are added to the model
 participant_mass = [67.0, 55.0] # kg # defaults to 70 if not provided. No influence on kinematics (motion), only on kinetics (forces)
 right_left_symmetry = true # true or false (lowercase) # Set to false only if you have good reasons to think the participant is not symmetrical (e.g. prosthetic limb)

{sports2d-0.7.0 → sports2d-0.7.3}/Sports2D/Sports2D.py

@@ -109,6 +109,7 @@
 
 
 ## INIT
+from importlib.metadata import version
 import argparse
 import toml
 from datetime import datetime
@@ -261,7 +262,7 @@ CONFIG_HELP =   {'config': ["C", "path to a toml configuration file"],
                 'participant_mass': ["", "mass of the participant in kg or none. Defaults to 70 if not provided. No influence on kinematics (motion), only on kinetics (forces)"],
                 'close_to_zero_speed_m': ["","Sum for all keypoints: about 50 px/frame or 0.2 m/frame"], 
                 'multiperson': ["", "multiperson involves tracking: will be faster if set to false. true if not specified"],
-                'tracking_mode': ["", "sports2d or rtmlib. sports2d is generally much more accurate and comparable in speed. sports2d if not specified"],
+                'tracking_mode': ["", "'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned"],
                 'deepsort_params': ["", 'Deepsort tracking parameters: """{dictionary between 3 double quotes}""". \n\
                                     Default: max_age:30, n_init:3, nms_max_overlap:0.8, max_cosine_distance:0.3, nn_budget:200, max_iou_distance:0.8, embedder_gpu: True\n\
                                     More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51'],
@@ -301,7 +302,7 @@ __author__ = "David Pagnon"
 __copyright__ = "Copyright 2023, Sports2D"
 __credits__ = ["David Pagnon"]
 __license__ = "BSD 3-Clause License"
-__version__ = "0.4.0"
+__version__ = version("sports2d")
 __maintainer__ = "David Pagnon"
 __email__ = "contact@david-pagnon.com"
 __status__ = "Development"

sports2d-0.7.3/Sports2D/Utilities/__init__.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+from importlib.metadata import version
+
+__version__ = version("sports2d")
+VERSION = __version__

sports2d-0.7.3/Sports2D/Utilities/common.py

@@ -0,0 +1,226 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+
+'''
+    ##################################################
+    ## Common classes and functions                 ##
+    ##################################################
+    
+    - A class for displaying several matplotlib figures in tabs.
+    - A function for interpolating sequences with missing data. 
+    It does not interpolate sequences of more than N contiguous missing data.
+
+'''
+
+
+## INIT
+import sys
+from importlib.metadata import version
+import subprocess
+from pathlib import Path
+import logging
+from collections import defaultdict
+import numpy as np
+import imageio_ffmpeg as ffmpeg
+
+
+## AUTHORSHIP INFORMATION
+__author__ = "David Pagnon"
+__copyright__ = "Copyright 2023, Sports2D"
+__credits__ = ["David Pagnon"]
+__license__ = "BSD 3-Clause License"
+__version__ = version("sports2d")
+__maintainer__ = "David Pagnon"
+__email__ = "contact@david-pagnon.com"
+__status__ = "Development"
+
+
+## CONSTANTS
+angle_dict = { # lowercase!
+    # joint angles
+    'right ankle': [['RKnee', 'RAnkle', 'RBigToe', 'RHeel'], 'dorsiflexion', 90, 1],
+    'left ankle': [['LKnee', 'LAnkle', 'LBigToe', 'LHeel'], 'dorsiflexion', 90, 1],
+    'right knee': [['RAnkle', 'RKnee', 'RHip'], 'flexion', -180, 1],
+    'left knee': [['LAnkle', 'LKnee', 'LHip'], 'flexion', -180, 1],
+    'right hip': [['RKnee', 'RHip', 'Hip', 'Neck'], 'flexion', 0, -1],
+    'left hip': [['LKnee', 'LHip', 'Hip', 'Neck'], 'flexion', 0, -1],
+    # 'lumbar': [['Neck', 'Hip', 'RHip', 'LHip'], 'flexion', -180, -1],
+    # 'neck': [['Head', 'Neck', 'RShoulder', 'LShoulder'], 'flexion', -180, -1],
+    'right shoulder': [['RElbow', 'RShoulder', 'Hip', 'Neck'], 'flexion', 0, -1],
+    'left shoulder': [['LElbow', 'LShoulder', 'Hip', 'Neck'], 'flexion', 0, -1],
+    'right elbow': [['RWrist', 'RElbow', 'RShoulder'], 'flexion', 180, -1],
+    'left elbow': [['LWrist', 'LElbow', 'LShoulder'], 'flexion', 180, -1],
+    'right wrist': [['RElbow', 'RWrist', 'RIndex'], 'flexion', -180, 1],
+    'left wrist': [['LElbow', 'LWrist', 'LIndex'], 'flexion', -180, 1],
+
+    # segment angles
+    'right foot': [['RBigToe', 'RHeel'], 'horizontal', 0, -1],
+    'left foot': [['LBigToe', 'LHeel'], 'horizontal', 0, -1],
+    'right shank': [['RAnkle', 'RKnee'], 'horizontal', 0, -1],
+    'left shank': [['LAnkle', 'LKnee'], 'horizontal', 0, -1],
+    'right thigh': [['RKnee', 'RHip'], 'horizontal', 0, -1],
+    'left thigh': [['LKnee', 'LHip'], 'horizontal', 0, -1],
+    'pelvis': [['LHip', 'RHip'], 'horizontal', 0, -1],
+    'trunk': [['Neck', 'Hip'], 'horizontal', 0, -1],
+    'shoulders': [['LShoulder', 'RShoulder'], 'horizontal', 0, -1],
+    'head': [['Head', 'Neck'], 'horizontal', 0, -1],
+    'right arm': [['RElbow', 'RShoulder'], 'horizontal', 0, -1],
+    'left arm': [['LElbow', 'LShoulder'], 'horizontal', 0, -1],
+    'right forearm': [['RWrist', 'RElbow'], 'horizontal', 0, -1],
+    'left forearm': [['LWrist', 'LElbow'], 'horizontal', 0, -1],
+    'right hand': [['RIndex', 'RWrist'], 'horizontal', 0, -1],
+    'left hand': [['LIndex', 'LWrist'], 'horizontal', 0, -1]
+    }
+
+marker_Z_positions = {'right':
+                        {"RHip": 0.105, "RKnee": 0.0886, "RAnkle": 0.0972, "RBigToe":0.0766, "RHeel":0.0883, "RSmallToe": 0.1200, 
+                        "RShoulder": 0.2016, "RElbow": 0.1613, "RWrist": 0.120, "RThumb": 0.1625, "RIndex": 0.1735, "RPinky": 0.1740, "REye": 0.0311, 
+                        "LHip": -0.105, "LKnee": -0.0886, "LAnkle": -0.0972, "LBigToe": -0.0766, "LHeel": -0.0883, "LSmallToe": -0.1200, 
+                        "LShoulder": -0.2016, "LElbow": -0.1613, "LWrist": -0.120, "LThumb": -0.1625, "LIndex": -0.1735, "LPinky": -0.1740, "LEye": -0.0311, 
+                        "Hip": 0.0, "Neck": 0.0, "Head":0.0, "Nose": 0.0},
+                    'left':
+                        {"RHip": -0.105, "RKnee": -0.0886, "RAnkle": -0.0972, "RBigToe": -0.0766, "RHeel": -0.0883, "RSmallToe": -0.1200, 
+                        "RShoulder": -0.2016, "RElbow": -0.1613, "RWrist": -0.120, "RThumb": -0.1625, "RIndex": -0.1735, "RPinky": -0.1740, "REye": -0.0311, 
+                        "LHip": 0.105, "LKnee": 0.0886, "LAnkle": 0.0972, "LBigToe":0.0766, "LHeel":0.0883, "LSmallToe": 0.1200, 
+                        "LShoulder": 0.2016, "LElbow": 0.1613, "LWrist": 0.120, "LThumb": 0.1625, "LIndex": 0.1735, "LPinky": 0.1740, "LEye": 0.0311, 
+                        "Hip": 0.0, "Neck": 0.0, "Head":0.0, "Nose": 0.0},
+                    'front': # original knee:0.0179
+                        {"RHip": 0.0301, "RKnee": 0.129, "RAnkle": 0.0230, "RBigToe": 0.2179, "RHeel": -0.0119, "RSmallToe": 0.1804, 
+                        "RShoulder": -0.01275, "RElbow": 0.0702, "RWrist": 0.1076, "RThumb": 0.0106, "RIndex": -0.0004, "RPinky": -0.0009, "REye": 0.0702, 
+                        "LHip": 0.0301, "LKnee": 0.129, "LAnkle": 0.0230, "LBigToe": 0.2179, "LHeel": -0.0119, "LSmallToe": 0.1804, 
+                        "LShoulder": -0.01275, "LElbow": 0.0702, "LWrist": 0.1076, "LThumb": 0.0106, "LIndex": -0.0004, "LPinky": -0.0009, "LEye": 0.0702, 
+                        "Hip": 0.0301, "Neck": 0.0008, "Head": 0.0655, "Nose": 0.1076},
+                    'back':
+                        {"RHip": -0.0301, "RKnee": -0.129, "RAnkle": -0.0230, "RBigToe": -0.2179, "RHeel": 0.0119, "RSmallToe": -0.1804, 
+                        "RShoulder": 0.01275, "RElbow": 0.0702, "RWrist": -1076.0002, "RThumb": -0.0106, "RIndex": 0.0004, "RPinky": 0.0009, "REye": -0.0702, 
+                        "LHip": -0.0301, "LKnee": -0.129, "LAnkle": -0.0230, "LBigToe": -0.2179, "LHeel": 0.0119, "LSmallToe": -0.1804, 
+                        "LShoulder": 0.01275, "LElbow": 0.0702, "LWrist": -0.1076, "LThumb": -0.0106, "LIndex": 0.0004, "LPinky": 0.0009, "LEye": -0.0702, 
+                        "Hip": -0.0301, "Neck": -0.0008, "Head": -0.0655, "Nose": -0.1076},
+            }
+
+colors = [(255, 0, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), (0, 255, 255), (0, 0, 0), (255, 255, 255),
+            (125, 0, 0), (0, 125, 0), (0, 0, 125), (125, 125, 0), (125, 0, 125), (0, 125, 125), 
+            (255, 125, 125), (125, 255, 125), (125, 125, 255), (255, 255, 125), (255, 125, 255), (125, 255, 255), (125, 125, 125),
+            (255, 0, 125), (255, 125, 0), (0, 125, 255), (0, 255, 125), (125, 0, 255), (125, 255, 0), (0, 255, 0)]
+thickness = 1
+
+## FUNCTIONS
+def to_dict(d):
+    '''
+    Convert a defaultdict to a dict.
+    '''
+    if isinstance(d, defaultdict):
+        return {k: to_dict(v) for k, v in d.items()}
+    return d
+
+
+def make_homogeneous(list_of_arrays):
+    '''
+    Make a list of arrays (or a list of lists) homogeneous by padding with nans
+
+    Example: foo = [[array([nan, 656.02643776]), array([nan, nan])],
+                    [array([1, 2, 3]), array([1, 2])]]
+    becomes foo_updated = array([[[nan, 656.02643776, nan], [nan, nan, nan]],
+                                [[1., 2., 3.], [1., 2., nan]]])
+    Or foo = [[1, 2, 3], [1, 2], [3, 4, 5]]
+    becomes foo_updated = array([[1., 2., 3.], [1., 2., nan], [3., 4., 5.]])
+
+    INPUTS:
+    - list_of_arrays: list of arrays or list of lists
+
+    OUTPUT:
+    - np.array(list_of_arrays): numpy array of padded arrays
+    '''
+    
+    def get_max_shape(list_of_arrays):
+        '''
+        Recursively determine the maximum shape of a list of arrays.
+        '''
+        if isinstance(list_of_arrays[0], list):
+            # Maximum length at the current level plus the max shape at the next level
+            return [max(len(arr) for arr in list_of_arrays)] + get_max_shape(
+                [item for sublist in list_of_arrays for item in sublist])
+        else:
+            # Determine the maximum shape across all list_of_arrays at this level
+            return [len(list_of_arrays)] + [max(arr.shape[i] for arr in list_of_arrays if arr.size > 0) for i in range(list_of_arrays[0].ndim)]
+
+    def pad_with_nans(list_of_arrays, target_shape):
+        '''
+        Recursively pad list_of_arrays with nans to match the target shape.
+        '''
+        if isinstance(list_of_arrays, np.ndarray):        
+            # Pad the current array to the target shape        
+            pad_width = []        
+            for dim_index in range(0, len(target_shape)):
+                if dim_index == len(list_of_arrays.shape) or dim_index > len(list_of_arrays.shape):
+                    list_of_arrays = np.expand_dims(list_of_arrays, 0)
+            for dim_index in range(0, len(target_shape)):
+                max_dim = target_shape[dim_index]
+                curr_dim = list_of_arrays.shape[dim_index]
+                pad_width.append((0, max_dim - curr_dim))
+            return np.pad(list_of_arrays.astype(float), pad_width, constant_values=np.nan)
+        # Recursively pad each array in the list
+        return [pad_with_nans(array, target_shape[1:]) for array in list_of_arrays]
+
+    # Pad all missing dimensions of arrays with nans
+    list_of_arrays = [np.array(arr, dtype=float) if not isinstance(arr, np.ndarray) else arr for arr in list_of_arrays]
+    max_shape = get_max_shape(list_of_arrays)
+    list_of_arrays = pad_with_nans(list_of_arrays, max_shape)
+
+    return np.array(list_of_arrays)
+
+
+def get_start_time_ffmpeg(video_path):
+    '''
+    Get the start time of a video using FFmpeg.
+    '''
+
+    try:
+        ffmpeg_path = ffmpeg.get_ffmpeg_exe()
+    except Exception as e:
+        logging.warning(f"No ffmpeg exe could be found. Starting time set to 0.0. Error: {e}")
+        return 0.0
+    
+    cmd = [ffmpeg_path, "-i", video_path]
+    result = subprocess.run(cmd, stderr=subprocess.PIPE, stdout=subprocess.DEVNULL, text=True)
+    for line in result.stderr.splitlines():
+        if "start:" in line:
+            parts = line.split("start:")
+            if len(parts) > 1:
+                start_time = parts[1].split(",")[0].strip()
+                return float(start_time)
+    return 0.0  # Default to 0 if not found
+
+
+def resample_video(vid_output_path, fps, desired_framerate):
+    '''
+    Resample video to the desired fps using ffmpeg.
+    '''
+   
+    ffmpeg_path = ffmpeg.get_ffmpeg_exe()
+    new_vid_path = vid_output_path.parent / Path(vid_output_path.stem+'_2'+vid_output_path.suffix)
+    subprocess.run([ffmpeg_path, '-i', vid_output_path, '-filter:v', f'setpts={fps/desired_framerate}*PTS', '-r', str(desired_framerate), new_vid_path])
+    vid_output_path.unlink()
+    new_vid_path.rename(vid_output_path)
+
+
+def write_calibration(calib_params, toml_path):
+    '''
+    Write calibration file from calibration parameters
+    '''
+    
+    S, D, N, K, R, T, P = calib_params
+    with open(toml_path, 'w+') as cal_f:
+        for c in range(len(S)):
+            cam_str = f'[{N[c]}]\n'
+            name_str = f'name = "{N[c]}"\n'
+            size_str = f'size = {S[c]} \n'
+            mat_str = f'matrix = {K[c]} \n'
+            dist_str = f'distortions = {D[c]} \n' 
+            rot_str = f'rotation = {R[c]} \n'
+            tran_str = f'translation = {T[c]} \n'
+            fish_str = f'fisheye = false\n\n'
+            cal_f.write(cam_str + name_str + size_str + mat_str + dist_str + rot_str + tran_str + fish_str)
+        meta = '[metadata]\nadjusted = false\nerror = 0.0\n'
+        cal_f.write(meta)

{sports2d-0.7.0 → sports2d-0.7.3}/Sports2D/Utilities/filter.py

@@ -19,6 +19,7 @@
 
 
 ## INIT
+from importlib.metadata import version
 import numpy as np
 from scipy import signal
 from scipy.ndimage import gaussian_filter1d
@@ -30,7 +31,7 @@ __author__ = "David Pagnon"
 __copyright__ = "Copyright 2021, Pose2Sim"
 __credits__ = ["David Pagnon"]
 __license__ = "BSD 3-Clause License"
-__version__ = "0.4.0"
+__version__ = version("sports2d")
 __maintainer__ = "David Pagnon"
 __email__ = "contact@david-pagnon.com"
 __status__ = "Development"

{sports2d-0.7.0 → sports2d-0.7.3}/Sports2D/Utilities/tests.py

@@ -13,6 +13,7 @@
 
 
 ## INIT
+from importlib.metadata import version
 import toml
 import subprocess
 from pathlib import Path
@@ -23,7 +24,7 @@ __author__ = "David Pagnon"
 __copyright__ = "Copyright 2023, Sports2D"
 __credits__ = ["David Pagnon"]
 __license__ = "BSD 3-Clause License"
-__version__ = "0.4.0"
+__version__ = version("sports2d")
 __maintainer__ = "David Pagnon"
 __email__ = "contact@david-pagnon.com"
 __status__ = "Development"
@@ -58,12 +59,14 @@ def test_workflow():
     demo_cmd = ["sports2d", "--show_realtime_results", "False", "--show_graphs", "False"]
     subprocess.run(demo_cmd, check=True, capture_output=True, text=True, encoding='utf-8')
 
-    # With no pixels to meters conversion, no multiperson, lightweight mode, detection frequency, time range and slowmo factor
+    # With no pixels to meters conversion, no multiperson, lightweight mode, detection frequency, slowmo factor, gaussian filter, RTMO body pose model
     demo_cmd2 = ["sports2d", "--show_realtime_results", "False", "--show_graphs", "False", 
                  "--to_meters", "False", 
                  "--multiperson", "False", 
                  "--mode", "lightweight", "--det_frequency", "50", 
-                 "--time_range", "1.2", "2.7",  "--slowmo_factor", "4"]
+                 "--slowmo_factor", "4",
+                 "--filter_type", "gaussian",
+                 "--pose_model", "body", "--mode", """{'pose_class':'RTMO', 'pose_model':'https://download.openmmlab.com/mmpose/v1/projects/rtmo/onnx_sdk/rtmo-m_16xb16-600e_body7-640x640-39e78cc4_20231211.zip', 'pose_input_size':[640, 640]}"""]
     subprocess.run(demo_cmd2, check=True, capture_output=True, text=True, encoding='utf-8')
     
     # With a time range, inverse kinematics, marker augmentation, body pose_model and custom RTMO mode
@@ -71,9 +74,8 @@ def test_workflow():
                  "--time_range", "1.2", "2.7",
                  "--do_ik", "True", "--use_augmentation", "True", 
                  "--px_to_m_from_person_id", "1", "--px_to_m_person_height", "1.65",
-                 "--visible_side", "left", "front", "--participant_mass", "55.0", "67.0",
-                 "--pose_model", "body", "--mode", """{'pose_class':'RTMO', 'pose_model':'https://download.openmmlab.com/mmpose/v1/projects/rtmo/onnx_sdk/rtmo-m_16xb16-600e_body7-640x640-39e78cc4_20231211.zip', 'pose_input_size':[640, 640]}"""]
-    subprocess.run(demo_cmd3, check=True, capture_output=True, text=True)
+                 "--visible_side", "front", "auto", "--participant_mass", "55.0", "67.0"]
+    subprocess.run(demo_cmd3, check=True, capture_output=True, text=True, encoding='utf-8')
     
     # From config file
     cli_config_path = Path(__file__).resolve().parent.parent / 'Demo' / 'Config_demo.toml'

sports2d-0.7.3/Sports2D/__init__.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+from importlib.metadata import version
+
+__version__ = version("sports2d")
+VERSION = __version__

{sports2d-0.7.0 → sports2d-0.7.3}/Sports2D/process.py

@@ -58,6 +58,7 @@ import json
 import ast
 import shutil
 import os
+from importlib.metadata import version
 from functools import partial
 from datetime import datetime
 import itertools as it
@@ -72,11 +73,11 @@ import matplotlib as mpl
 import matplotlib.pyplot as plt
 from rtmlib import PoseTracker, BodyWithFeet, Wholebody, Body, Custom
 from deep_sort_realtime.deepsort_tracker import DeepSort
-import opensim as osim
 
 from Sports2D.Utilities import filter
 from Sports2D.Utilities.common import *
 from Sports2D.Utilities.skeletons import *
+from Pose2Sim.common import *
 
 DEFAULT_MASS = 70
 DEFAULT_HEIGHT = 1.7
@@ -86,7 +87,7 @@ __author__ = "David Pagnon, HunMin Kim"
 __copyright__ = "Copyright 2023, Sports2D"
 __credits__ = ["David Pagnon"]
 __license__ = "BSD 3-Clause License"
-__version__ = "0.4.0"
+__version__ = version("sports2d")
 __maintainer__ = "David Pagnon"
 __email__ = "contact@david-pagnon.com"
 __status__ = "Development"
@@ -625,7 +626,7 @@ def trc_data_from_XYZtime(X, Y, Z, time):
     '''
 
     trc_data = pd.concat([pd.concat([X.iloc[:,kpt], Y.iloc[:,kpt], Z.iloc[:,kpt]], axis=1) for kpt in range(len(X.columns))], axis=1)
-    trc_data.insert(0, 't', time)
+    trc_data.insert(0, 'time', time)
 
     return trc_data
 
@@ -928,6 +929,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     px_to_m_from_person_id = int(config_dict.get('project').get('px_to_m_from_person_id'))
     px_to_m_person_height_m = config_dict.get('project').get('px_to_m_person_height')
     visible_side = config_dict.get('project').get('visible_side')
+    if isinstance(visible_side, str): visible_side = [visible_side]
     # Pose from file
     load_trc_px = config_dict.get('project').get('load_trc_px')
     if load_trc_px == '': load_trc_px = None
@@ -1040,7 +1042,8 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     close_to_zero_speed_px = config_dict.get('kinematics').get('close_to_zero_speed_px')
     close_to_zero_speed_m = config_dict.get('kinematics').get('close_to_zero_speed_m')
     if do_ik:
-        from Pose2Sim.markerAugmentation import augment_markers_all
+        if use_augmentation:
+            from Pose2Sim.markerAugmentation import augment_markers_all
         from Pose2Sim.kinematics import kinematics_all
         # Create a Pose2Sim dictionary and fill in missing keys
         recursivedict = lambda: defaultdict(recursivedict)
@@ -1127,12 +1130,18 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
             logging.error(f'\n{load_trc_px} file needs to be in px, not in meters.')
         logging.info(f'\nUsing a pose file instead of running pose estimation and tracking: {load_trc_px}.')
         # Load pose file in px
-        Q_coords, _, _, keypoints_names, _ = read_trc(load_trc_px)
+        Q_coords, _, time_col, keypoints_names, _ = read_trc(load_trc_px)
+
         keypoints_ids = [i for i in range(len(keypoints_names))]
         keypoints_all, scores_all = load_pose_file(Q_coords)
         for pre, _, node in RenderTree(pose_model):
             if node.name in keypoints_names:
                 node.id = keypoints_names.index(node.name)
+        if time_range:
+            frame_range = [abs(time_col - time_range[0]).idxmin(), abs(time_col - time_range[1]).idxmin()+1]
+        else:
+            frame_range = [0, len(Q_coords)]
+        frame_iterator = tqdm(range(*frame_range))
     
     else:
         # Retrieve keypoint names from model
@@ -1336,7 +1345,10 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
     all_frames_scores = make_homogeneous(all_frames_scores)
 
     frame_range = [0,frame_count] if video_file == 'webcam' else frame_range
-    all_frames_time = pd.Series(np.linspace(frame_range[0]/fps, frame_range[1]/fps, frame_count+1), name='time')
+    if not load_trc_px:
+        all_frames_time = pd.Series(np.linspace(frame_range[0]/fps, frame_range[1]/fps, frame_count-frame_range[0]+1), name='time')
+    else:
+        all_frames_time = time_col
     if not multiperson:
         px_to_m_from_person_id = get_personID_with_highest_scores(all_frames_scores)
         detected_persons = [px_to_m_from_person_id]
@@ -1475,7 +1487,6 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                 if not np.array(trc_data[i].iloc[:,1:] ==0).all():
                     # Automatically determine visible side
                     visible_side_i = visible_side[i] if len(visible_side)>i else 'auto' # set to 'auto' if list too short
-                    
                     # Set to 'front' if slope of X values between [-5,5]
                     if visible_side_i == 'auto':
                         try:
@@ -1512,7 +1523,7 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
                     pose_path_person_m_i = (pose_output_path.parent / (pose_output_path_m.stem + f'_person{idx_path:02d}.trc'))
                     make_trc_with_trc_data(trc_data_m_i, pose_path_person_m_i, fps=fps)
                     if make_c3d:
-                        c3d_path = convert_to_c3d(pose_path_person_m_i)
+                        c3d_path = convert_to_c3d(str(pose_path_person_m_i))
                     logging.info(f'Pose in meters saved to {pose_path_person_m_i.resolve()}. {"Also saved in c3d format." if make_c3d else ""}')
                     
                 
@@ -1643,12 +1654,17 @@ def process_fun(config_dict, video_file, time_range, frame_rate, result_dir):
 
     # OpenSim inverse kinematics (and optional marker augmentation)
     if do_ik or use_augmentation:
+        import opensim as osim
         logging.info('\nPost-processing angles (with inverse kinematics):')
         if not to_meters:
             logging.warning('Skipping marker augmentation and inverse kinematics as to_meters was set to False.')
         else:
             # move all trc files containing _m_ string to pose3d_dir
-            for trc_file in output_dir.glob('*_m_*.trc'):
+            if not load_trc_px: 
+                trc_list = output_dir.glob('*_m_*.trc')
+            else:
+                trc_list = [pose_path_person_m_i]
+            for trc_file in trc_list:
                 if (pose3d_dir/trc_file.name).exists():
                     os.remove(pose3d_dir/trc_file.name)
                 shutil.move(trc_file, pose3d_dir)

{sports2d-0.7.0 → sports2d-0.7.3}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = sports2d
-version = 0.7.0
+version = 0.7.3
 author = David Pagnon
 author_email = contact@david-pagnon.com
 description = Detect pose and compute 2D joint angles from a video.

{sports2d-0.7.0 → sports2d-0.7.3}/sports2d.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: sports2d
-Version: 0.7.0
+Version: 0.7.3
 Summary: Detect pose and compute 2D joint angles from a video.
 Home-page: https://github.com/davidpagnon/Sports2D
 Author: David Pagnon
@@ -40,6 +40,7 @@ Requires-Dist: tqdm
 Requires-Dist: imageio_ffmpeg
 Requires-Dist: deep-sort-realtime
 Requires-Dist: Pose2Sim
+Dynamic: license-file
 
 
 [![Continuous integration](https://github.com/davidpagnon/sports2d/actions/workflows/continuous-integration.yml/badge.svg?branch=main)](https://github.com/davidpagnon/sports2d/actions/workflows/continuous-integration.yml)
@@ -81,7 +82,10 @@ Works on any smartphone!**\
 
 </br>
 
-https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e
+
+https://github.com/user-attachments/assets/6a444474-4df1-4134-af0c-e9746fa433ad
+
+<!-- https://github.com/user-attachments/assets/1c6e2d6b-d0cf-4165-864e-d9f01c0b8a0e -->
 
 `Warning:` Angle estimation is only as good as the pose estimation algorithm, i.e., it is not perfect.\
 `Warning:` Results are acceptable only if the persons move in the 2D plane (sagittal or frontal plane). The persons need to be filmed as parallel as possible to the motion plane.\
@@ -465,7 +469,7 @@ sports2d --help
 'participant_mass': ["", "mass of the participant in kg or none. Defaults to 70 if not provided. No influence on kinematics (motion), only on kinetics (forces)"],
 'close_to_zero_speed_m': ["","Sum for all keypoints: about 50 px/frame or 0.2 m/frame"], 
 'multiperson': ["", "multiperson involves tracking: will be faster if set to false. true if not specified"],
-'tracking_mode': ["", "sports2d or rtmlib. sports2d is generally much more accurate and comparable in speed. sports2d if not specified"],
+'tracking_mode': ["", "'sports2d' or 'deepsort'. 'deepsort' is slower, harder to parametrize but can be more robust if correctly tuned"],
 'deepsort_params': ["", 'Deepsort tracking parameters: """{dictionary between 3 double quotes}""". \n\
                     Default: max_age:30, n_init:3, nms_max_overlap:0.8, max_cosine_distance:0.3, nn_budget:200, max_iou_distance:0.8, embedder_gpu: True\n\
                     More information there: https://github.com/levan92/deep_sort_realtime/blob/master/deep_sort_realtime/deepsort_tracker.py#L51'],

sports2d-0.7.0/Sports2D/Utilities/__init__.py

@@ -1,7 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-import sys
-
-__version__ = "0.4.0"
-VERSION = __version__