Skip to content

Reconstruction: Landmark Triangulation from Motion Capture

The reconstruction pipeline transforms synchronized videos into 3D motion trajectories through two stages:

  1. 2D landmark detection: a tracker processes each camera's video to identify anatomical landmarks (e.g., joint positions) in every frame
  2. 3D triangulation: using the calibrated camera system, corresponding 2D observations from multiple cameras are triangulated into 3D world coordinates

The pipeline uses the camera intrinsics and extrinsics established during calibration to locate landmarks in physical space.

Available Trackers

Custom ONNX Trackers

Caliscope can load custom pose estimation models in ONNX format. This is the primary extensibility mechanism: you can use models trained on your specific subjects (particular species, body regions, behavioral features) without modifying Caliscope's source code. Models exported from SLEAP, DeepLabCut, RTMPose, or other frameworks are supported.

After installation, ONNX models appear alongside the built-in trackers in the reconstruction tab's dropdown menu. See Custom ONNX Trackers for setup instructions.

Built-in MediaPipe Trackers

Four MediaPipe-based trackers are included for convenience:

Tracker Description Landmarks
Pose Full body skeletal tracking 33 keypoints
Hand Detailed hand tracking 21 keypoints per hand
Simple Holistic Body + hands + face (filtered) Reduced set for gross movement
Holistic Body + hands + face (full) Several hundred keypoints

The Holistic tracker combines body, hand, and face tracking into a single output. The large number of face landmarks (several hundred) can become unwieldy for users primarily interested in skeletal movement. The Simple Holistic tracker filters these down to a smaller set focused on gross motor patterns.

Workflow

  1. Navigate to the Reconstruction tab
  2. Select the recording you want to process from the list
  3. Recordings are detected automatically from subfolders within recordings/ that contain synchronized videos
  4. You may need to reload the workspace if recordings were added while the application was running
  5. Choose a tracker from the dropdown menu
  6. Click Process to begin landmark tracking and triangulation
  7. Results appear in the 3D viewer when processing completes
  8. Open the recording's output subfolder to access trajectory files

Output Files

After processing, output is saved to a subfolder named after the tracker within the recording directory (e.g., recordings/walking/POSE/).

File Format Description
xy_{TRACKER}.csv Long CSV 2D tracked points per camera (sync_index, cam_id, point_id, img_loc_x, img_loc_y, frame_time)
xyz_{TRACKER}.csv Long CSV Triangulated 3D points (sync_index, point_id, x_coord, y_coord, z_coord, frame_time)
xyz_{TRACKER}_labelled.csv Wide CSV Named columns (e.g., nose_x, nose_y, nose_z, left_shoulder_x, ...)
xyz_{TRACKER}.trc TRC OpenSim-compatible format for biomechanical modeling
camera_array.toml TOML Snapshot of the camera calibration used for this reconstruction

Coordinate Units

All 3D coordinates are in meters. The physical scale is determined by the calibration target dimensions you entered during extrinsic calibration. See Calibration Targets for details on how the scale chain propagates from board geometry to world coordinates.

Per-Recording Camera Snapshot

Each reconstruction saves a copy of camera_array.toml alongside its output files. This ensures that recalibrating your camera system does not invalidate previous reconstruction results. Each recording retains the exact calibration parameters used to produce it.

In longitudinal studies where camera positions may shift between sessions, this prevents the need to reprocess archived recordings.

Practical Recording Guidelines

Minimize Motion Blur

Motion blur substantially compromises landmark recognition. To reduce blur:

  • Use higher frame rates (e.g., 60 fps or above for dynamic movements)
  • Increase lighting to maintain exposure at faster shutter speeds
  • Avoid slow shutter speeds that allow excessive motion during exposure

Lighting

  • Ensure adequate, even lighting across the capture volume
  • Avoid harsh shadows or high-contrast regions that can confuse trackers
  • Diffuse lighting generally produces more consistent tracking than point sources