This protocol captures a representative daily routine of individuals with upper limb impairments using wearable cameras or egocentric videos. Its purpose is to evaluate and use at home for rehabilitation applications. The imaged hand use can help to evaluate the impact of new therapies in the home environments.
The protocol is designed to efficiently capture data representative of the user's daily life. The information obtained using this protocol can be used to evaluate the impact of rehabilitation, track progress over time or guide remote care. Good communications with participant is essential.
Ensure that they understand the importance of not changing their usual routine or the manner in which they perform tasks. Begin by asking the participant whether their affected hands impact their ability to carry out activities of daily living, or ADLs. Ask the participant to give some examples of tasks that they can and cannot perform independently with their affected hands.
Ask participants to recall their daily routines over the past two weeks. Document which daily tasks are performed, for how long, and at approximately what time. In collaboration with the participant, select three time slots of 90 minutes each, during which to record videos.
Select time slots that are spread over different days of the week and take place when ADLs involving the hands are typically carried out in sequence. Obtain agreement of the participant on the recording schedules after discussing any concerns that they may have. Set a goal of three hours of videos over two weeks and inform the participant that insufficient videos may lead to extending their recording periods.
Instruct the participant to focus on capturing realistic routines. Ensure that the participant understands that all recordings should take place inside their homes, not in public places. Give some examples that may raise privacy concerns, such as bathing, dressing and checking confidential information.
Remind the participant to be aware of mirrors, which may show their face in the recordings. Suggest that the participant avoids the presence of other people, such as family members or caregivers, as much as possible in the videos. Demonstrate how to use an egocentric camera.
Specifically, show the participant how to turn the camera on and off and how to control recordings. Ask the participant to practice turning the camera on and off, then to try to record from the camera. If applicable, demonstrate how to use a tablet with the pre-installed camera app.
Demonstrate how to turn the tablet on and off, how to connect the tablet to the camera through the camera app, and how to control the recordings. Ask the participant to practice the demonstrated steps. Then, show them how to review the recorded videos and how to trim or delete them.
Have the participant practice reviewing, trimming and deleting a recording from the tablet. Next, demonstrate how to don or doff the camera using an elastic headband adjustable to the participant's head. Place the camera on the participant's forehead and adjust the headband to wear the camera comfortably and steadily.
Ensure an optimal angle of the camera with respect to the forehead. Ask the participant to record a short segment of video while moving their hands in front of them and manipulating an object. Review the recorded video and ensure that the two hands are clearly visible in the central region of the scene while conducting manipulation tasks.
Practice the use of the camera and tablet with the participant and their caregivers until they demonstrate proficiency. Give the participant the kit with the equipment to record their ADLs at home. In addition to the camera and tablet, the kit should include extra camera batteries, battery chargers for both camera and tablet, charging cables, headband for the camera and a printed set of guidelines for using the camera.
A sample of 23 participants was recruited, including nine stroke survivors and 14 individuals with spinal cord injury. The proposed protocol was successful for 95.7%of the participants. Recorded activities included meal preparation, eating, dishwashing, physical activity and knitting.
The daily average video recording length per participant was 60 minutes, with an average of three hours of video obtained per participant. Some participants reported feeling tired and uncomfortable wearing the camera for over one hour, due to its weight and heat against the forehead. 27%of participants required assistance from the research team during the recording periods at home.
On average, each help call took five to 10 minutes. In addition, 15 caregivers of participants were involved in helping to record videos at home. Selecting the activities needs to be collaborative process between the researcher and participants to ensure that realistic, representative and meaningful routines are captured.
The data obtained from these videos can be used for automatic analysis, through computer vision and machine learning techniques to create new tools for tracking rehabilitation progress and outcomes.
