module: myeasymocap.stages.basestage.MultiStage
args:
  output: output/detect_match_triangulate
  keys_keep: [cameras, imgnames]
  at_step:
    detect:
      module: myeasymocap.backbone.yolo.yolo.MultiPerson # Use YOLO to detect multi-person
      key_from_data: [images, imgnames]
      args:
        model: yolov5m
        name: person
        min_length: 150 # this two threshold control the wanted bboxes
        max_length: 1000
    # keypoints2d:
    #   module: myeasymocap.backbone.hrnet.myhrnet.MyHRNet
    #   key_from_data: [images, imgnames]
    #   key_from_previous: [bbox]
    #   key_keep: []
    #   args:
    #     ckpt: data/models/pose_hrnet_w48_384x288.pth
    #     single_person: False # This flag controls the function to detect all keypoints
    keypoints2d:
      module: myeasymocap.backbone.vitpose.vit_moe.MyViT
      key_from_data: [images, imgnames]
      key_from_previous: [bbox]
      key_keep: []
      args:
        ckpt: data/models/vitpose+_base.pth
        single_person: False # This flag controls the function to detect all keypoints
    vis_2d:
      module: myeasymocap.io.vis.Vis2D
      skip: False
      key_from_data: [images]
      key_from_previous: [keypoints, bbox]
      args:
        name: vis_keypoints2d
        scale: 0.5
    match:
      module: myeasymocap.operations.match_base.MatchAndTrack
      key_from_data: [cameras, meta]
      key_from_previous: [keypoints]
      args:
        cfg_match:
          min_conf: 0.3
          min_joints: 9
          distance:
            mode: epipolar
            threshold: 0.05 # 用于控制匹配的内点阈值
            threshold_track: 0.05 # track的匹配的内点阈值
            min_common_joints: 9
            cfg_svt:
              debug: 0
              maxIter: 10
              w_sparse: 0.1
              w_rank: 50
              tol: 0.0001
              aff_min: 0.3
          triangulate:
            min_view: 3 # min view when triangulate each points
            min_view_body: 3 # min visible view of the body
            min_conf_3d: 0.1
            dist_max: 50 # pixel
            dist_track: 100 # mm
        cfg_track:
          max_person: 100
          max_missing: 3 # 最多丢失3帧就要删除
          final_ranges: [[-10000, -10000, -10000], [10000, 10000, 10000]] # 最终的输出的range，仅用于输出的时候的筛选
          final_max_person: 100
          kintree: [[2, 3], [5, 6], [3, 4], [6, 7], [11, 22], [22, 23], [11, 24], [14, 19], [19, 20], [14, 21]]
    vis_kpts3d:
      module: myeasymocap.io.vis.Vis3D
      key_from_data: [images, cameras]
      key_from_previous: [results] # 用于最后的一起优化
      args:
        scale: 0.5
        lw_factor: 10
  at_final:
    write_raw: # write the raw 3d keypoints
      module: myeasymocap.io.write.WriteAll
      key_from_data: [results, meta]
      args:
        name: keypoints3d_raw
    make_video:
      module: myeasymocap.io.video.MakeVideo
      args:
        fps: 60
        keep_image: False