bottom_up_pose_tracking_demo.py

# Copyright (c) OpenMMLab. All rights reserved.
import os
import warnings
from argparse import ArgumentParser

import cv2
import mmcv

from mmpose.apis import (get_track_id, inference_bottom_up_pose_model,
                         init_pose_model, vis_pose_tracking_result)
from mmpose.core import Smoother
from mmpose.datasets import DatasetInfo


def main():
    """Visualize the demo images."""
    parser = ArgumentParser()
    parser.add_argument('pose_config', help='Config file for pose')
    parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
    parser.add_argument('--video-path', type=str, help='Video path')
    parser.add_argument(
        '--show',
        action='store_true',
        default=False,
        help='whether to show visualizations.')
    parser.add_argument(
        '--out-video-root',
        default='',
        help='Root of the output video file. '
        'Default not saving the visualization video.')
    parser.add_argument(
        '--device', default='cuda:0', help='Device used for inference')
    parser.add_argument(
        '--kpt-thr', type=float, default=0.5, help='Keypoint score threshold')
    parser.add_argument(
        '--pose-nms-thr',
        type=float,
        default=0.9,
        help='OKS threshold for pose NMS')
    parser.add_argument(
        '--use-oks-tracking', action='store_true', help='Using OKS tracking')
    parser.add_argument(
        '--tracking-thr', type=float, default=0.3, help='Tracking threshold')
    parser.add_argument(
        '--euro',
        action='store_true',
        help='(Deprecated, please use --smooth and --smooth-filter-cfg) '
        'Using One_Euro_Filter for smoothing.')
    parser.add_argument(
        '--smooth',
        action='store_true',
        help='Apply a temporal filter to smooth the pose estimation results. '
        'See also --smooth-filter-cfg.')
    parser.add_argument(
        '--smooth-filter-cfg',
        type=str,
        default='configs/_base_/filters/one_euro.py',
        help='Config file of the filter to smooth the pose estimation '
        'results. See also --smooth.')
    parser.add_argument(
        '--radius',
        type=int,
        default=4,
        help='Keypoint radius for visualization')
    parser.add_argument(
        '--thickness',
        type=int,
        default=1,
        help='Link thickness for visualization')

    args = parser.parse_args()

    assert args.show or (args.out_video_root != '')

    # build the pose model from a config file and a checkpoint file
    pose_model = init_pose_model(
        args.pose_config, args.pose_checkpoint, device=args.device.lower())

    dataset = pose_model.cfg.data['test']['type']
    dataset_info = pose_model.cfg.data['test'].get('dataset_info', None)
    if dataset_info is None:
        warnings.warn(
            'Please set `dataset_info` in the config.'
            'Check https://github.com/open-mmlab/mmpose/pull/663 for details.',
            DeprecationWarning)
        assert (dataset == 'BottomUpCocoDataset')
    else:
        dataset_info = DatasetInfo(dataset_info)

    video = mmcv.VideoReader(args.video_path)
    assert video.opened, f'Faild to load video file {args.video_path}'

    if args.out_video_root == '':
        save_out_video = False
    else:
        os.makedirs(args.out_video_root, exist_ok=True)
        save_out_video = True

    if save_out_video:
        fps = video.fps
        size = (video.width, video.height)
        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
        videoWriter = cv2.VideoWriter(
            os.path.join(args.out_video_root,
                         f'vis_{os.path.basename(args.video_path)}'), fourcc,
            fps, size)

    # optional
    return_heatmap = False

    # build pose smoother for temporal refinement
    if args.euro:
        warnings.warn(
            'Argument --euro will be deprecated in the future. '
            'Please use --smooth to enable temporal smoothing, and '
            '--smooth-filter-cfg to set the filter config.',
            DeprecationWarning)
        smoother = Smoother(
            filter_cfg='configs/_base_/filters/one_euro.py', keypoint_dim=2)
    elif args.smooth:
        smoother = Smoother(filter_cfg=args.smooth_filter_cfg, keypoint_dim=2)
    else:
        smoother = None

    # e.g. use ('backbone', ) to return backbone feature
    output_layer_names = None
    next_id = 0
    pose_results = []
    for cur_frame in mmcv.track_iter_progress(video):
        pose_results_last = pose_results

        pose_results, _ = inference_bottom_up_pose_model(
            pose_model,
            cur_frame,
            dataset=dataset,
            dataset_info=dataset_info,
            pose_nms_thr=args.pose_nms_thr,
            return_heatmap=return_heatmap,
            outputs=output_layer_names)

        # get track id for each person instance
        pose_results, next_id = get_track_id(
            pose_results,
            pose_results_last,
            next_id,
            use_oks=args.use_oks_tracking,
            tracking_thr=args.tracking_thr,
            use_one_euro=args.euro,
            fps=fps)

        # post-process the pose results with smoother
        if smoother:
            pose_results = smoother.smooth(pose_results)

        # show the results
        vis_frame = vis_pose_tracking_result(
            pose_model,
            cur_frame,
            pose_results,
            radius=args.radius,
            thickness=args.thickness,
            dataset=dataset,
            dataset_info=dataset_info,
            kpt_score_thr=args.kpt_thr,
            show=False)

        if args.show:
            cv2.imshow('Image', vis_frame)

        if save_out_video:
            videoWriter.write(vis_frame)

        if args.show and cv2.waitKey(1) & 0xFF == ord('q'):
            break

    if save_out_video:
        videoWriter.release()
    if args.show:
        cv2.destroyAllWindows()


if __name__ == '__main__':
    main()