Skip to content
WI ZUT CVLab

Event-Based Data

This page provides access to segmented video clips and detailed CSV files for our Driver Fatigue Detection dataset. These resources are specifically structured to facilitate the study of distinct fatigue-related events across different subjects.

Video Clips by Event and Subject

File Description: This ZIP archive contains 44 folders, one for each participant. Each participant’s folder is further divided into five subfolders, corresponding to different classes of fatigue-related events. These clips are extracted from processed video data, showing specific behaviors such as yawning, eye rubbing, etc.

Contents

  • Number of Participant Folders: 44
  • Subfolders per Participant: 5 (one for each class of event)
  • Format: Videos (.mp4)
  • Total File Size: 227MB

Classes

  1. Yawning without Covering Mouth: Videos capturing subjects yawning openly, which is a common sign of tiredness.
  2. Frequent Blinking: Recordings of subjects blinking more frequently than usual, which can indicate the early stages of fatigue.
  3. Yawning with Mouth Covered: This class includes videos where subjects cover their mouths while yawning, often considered a social behavior to mask tiredness.
  4. Head Dropping: This category features subjects whose heads drop in a nodding motion, indicating severe drowsiness or loss of alertness.
  5. Eye Rubbing: Subjects are shown rubbing their eyes, a behavior typically associated with fatigue and eye strain.

Naming Convention for Files

The naming convention for the annotated video files is structured to ensure easy identification and sorting of data:

  • Format: <modality>_<participant_id>_<class_id>_<event_id>
    • Modality: Indicates the mode of the recording (depth, normal, normal2, termo).
    • Participant ID: A number ranging from 1 to 44 representing each participant.
    • Class ID: A number from 1 to 5 that identifies the class of the event.
    • Event ID: Corresponds to the row number in the respective CSV file, acting as a unique identifier for each event. It may not necessarily appear in sequential order.
  • Separator: An underscore _ is used to separate different elements of the file name.

Examples of file names:

  • normal_3_2_15.mp4: This file name indicates it is from the normal modality, belongs to participant 3, is of class 2, and is the 15th event recorded for this participant.
  • depth_22_4_07.mp4: This file name indicates it is from the depth modality, belongs to participant 22, is of class 4, and is the 7th event recorded for this participant.

Event Annotations in CSV Format

File Description: This ZIP file contains CSV files for each participant. These manually recorded annotations detail the events observed in the RGB1 (normal) video clips. Each event is described by three parameters: class of the event, start frame, and end frame. This provides a precise temporal annotation of each occurrence. The annotations were initially made on the RGB1 mode and subsequently mapped onto the other modes (depth, thermal). Each event is represented as a separate row in the CSV, described by three columns: event class number, start frame number, and end frame number where the event occurred.

Contents

  • Number of CSV Files: 44 (one for each participant)
  • Description of Parameters: Event class, Start Frame, End Frame
  • Format: CSV
  • Total File Size: 10KB