iTrace vs Pupil Player

iTrace is a free, MIT-licensed toolkit for analyzing webcam eye-tracking data, with a scientific core built on NumPy and SciPy. It computes gaze in degrees of visual angle and detects fixations, saccades, and microsaccades using I-VT, I-DT, and Engbert–Kliegl methods. Pupil tools include blink detection and interpolation, preprocessing, and eye-crop segmentation measured in pixels or relative to iris size. Affine screen-space calibration reports calibration error and gaze-quality measures. The command-line tool analyzes gaze CSV files and exports JSON reports. Optional webcam capture uses OpenCV and MediaPipe, and optional interfaces include a local HTML app using FastAPI and WebSockets and a Streamlit dashboard. Live workflows can export derived gaze, pupil, and capture CSVs. By default, the workflow does not save raw eye video or persisted eye-crop images, though live viewing may send a temporary JPEG crop to a browser over a local WebSocket. The project says its checks use synthetic ground truth rather than real eye-tracking data or a reference device. Webcam pupil size is a relative proxy, not a measurement in millimetres.

Pupil Player is free, open-source software for viewing, analyzing, and exporting Pupil Capture recordings. It runs on Windows, macOS, and Linux and uses hardware recordings as input. Playback includes frame stepping, timeline trimming, and five speeds from 0.25x through 4x. A plugin framework adds gaze displays, marker and surface tracking, and data export. Analysis plugins cover post-hoc fixation and blink detection, pupil detection, gaze calibration, mapping, validation, and head-pose tracking. Visualizations can show circles, crosses, polylines, light points, heatmaps, or fixation overlays. Raw Data Exporter writes pupil and gaze data as CSV, while World Video Exporter saves visualized video. An iMotions exporter creates undistorted world video and gaze.tlv data. Exports go into an exports subfolder without removing or overwriting raw captures. Available plugins depend on the recording source, and eye-video overlays require eye video enabled during capture. Runtime-loaded Python plugins can extend the software.