Products

 

Respondus Monitor: Automated Video Analysis

 

Respondus Monitor uses Automated Video Analysis to provide additional information about exam sessions. This information is available to instructors from the LockDown Browser Dashboard. This feature does not determine whether a student has cheated or not, but instead, points to unusual events or anomalies that occurred during the exam session.

  • Facial Detection % – The percent of time the student's face was detected for analysis
  • Flags – The number of suspicious activities or problematic events that occurred
  • Total Flagged Time – The total time for events that were flagged

Expand the details for a student to view more information.

The bar charts at the top right provide the following information:

  • Duration of Exam – The length of the exam, in minutes
  • Facial Detection Successful – The number of minutes that facial detection was successful
  • Student Facing Their Webcam – The number of minutes the student faced their screen
  • Total Time of Flagged Events – The total time for events that were flagged

The "Flagged Segments & Warnings" section, which appears below the large playback window, is where an instructor can view a list of flagged events, including the time/duration of each one. Three types of events are currently flagged:

  • MISSING – Indicates that the student could not be detected in the video frame for a period of time
  • DIFFERENT – Indicates a different person from whom started the exam appears in the video for a period of time
  • MULTIPLE – Indicates that multiple faces are detected in the video for a period of time

Other automated events will appear in this section too, such as notifications of video interruptions. Each flagged event is a clickable link that will start the video playback from that timestamp.

 

Things to Remember

Automated Video Analysis is a constantly-evolving technology. It does not determine whether a student has cheated or not, but instead, points to suspicious activities or anomalies that occurred during the exam session.

As an instructor, there are several things to keep in mind about the Automated Video Analysis.

1) Facial detection is important. Facial detection is the foundation of flagging. If you cannot detect the face, you cannot determine if it's missing, different, or looking away from the screen. If a student's face is turned away from the webcam or heavily cropped in the video (e.g. you can only see the student's nose and above), facial detection rates will drop. Other things that affect facial detection rates are baseball caps, backlighting, very low lighting, hands on the face, and certain eye glasses.

2) There are more "false positives" than "true positives." A "false positive" is a behavior that's mistakenly flagged as being suspicious. An example would be a student flagged as "missing" but is still visible in the frame. A "true positive" is a suspicious behavior that is correctly identified by the flagging system. Our goal is to provide "meaningful results," which means presenting as few flags as possible, without allowing true positives to be missed. However, this inevitably results in a higher rate of false positives than true positives.

3) Automated Video Analysis continuously improves. We often develop new algorithms or tweak settings in order to improve the Automated Video Analysis. Older videos don't get reprocessed, but you'll see ongoing improvement to the flagging system as time progresses.

4) Garbage in, garbage out. You can achieve immediate improvement with automated flagging by having students produce better videos. Provide these simple guidelines to students to help them create higher quality videos so that Automated Video Analysis works better .

  • Avoid wearing baseball caps or hats that extend beyond the forehead
  • If using a notebook computer, place it on a firm surface like a desk or table, not your lap.
  • If the webcam is built into the screen, avoid making screen adjustments after the exam starts. A common mistake is to push the screen back, resulting in only the top portion of the face being recorded.
  • Don't lie down on a couch or bed while taking an exam. There is a greater chance you'll move out of the video frame or change your relative position to the webcam.
  • Don't take an exam in a dark room. If the details of your face don't show clearly during the webcam check, the automated video analysis is more likely to flag you as missing.
  • Avoid backlighting situations, such as sitting with your back to a window. The general rule is to have light in front of your face, not behind your head.
  • Select a distraction-free environment for the exam. Televisions and other people in the room can draw your attention away from the screen. Other people that come into view of the webcam may also trigger flags by the automated system.

 

See the Respondus Monitor Instructor Resources page for user guides, sample wording for the syllabus, information on preparing an exam for use with Respondus Monitor, and the importance of using a practice quiz.