Passive Observer of Activities for Aging in Place Using a Network of RGB-D Sensors
Bibliographic record
Abstract
Aging in place is a notion which supports the independent living of older adults at their own place of residence for as long as possible. To support this alternative living which can be in contrast to various other types of assisted living options, modes of monitoring technology need to be explored and studied in order to determine a balance between the preservation of privacy and adequacy of sensed information for better estimation and visualization of movements and activities. In this paper, we explore such monitoring paradigm on how a network of RGB-D sensors can be utilized for this purpose. This type of sensor offers both visual and depth sensing modalities from the scene where the information can be fused and coded for better protection of privacy. For this purpose, we introduce the novel notion of passive observer. This observer is only triggered by detecting the absence of movements of older adults in the scene. This is accomplished by classifying and localizing objects in the monitoring scene from both before and after the detection of movements. A deep learning tool is utilized for visual classification of known objects in the physical scene followed by virtual reality reconstructing of the scene where the shape and location of objects are recreated. Such reconstruction can be used as a visual summary in order to identify objects which were handled by an older adult in-between observation. The simplified virtual scene can be used, for example, by caregivers or monitoring personnel in order to assist in detecting any anomalies. This virtual visualization can offer a high level of privacy protection without having any direct visual access to the monitoring scene. In addition, using the scene graph representation, an automatic decision-making tool is proposed where spatial relationships between the objects can be used to estimate the expected activities. The results of this paper are demonstrated through two case studies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".