SocialNet: Detecting Social Distancing Violations in Crowd Scene on IoT devices
Bibliographic record
Abstract
Recently, the COVID-19 pandemic has affected the world and spread in the majority of the countries. To decrease the number of infections, experts suggested people practice social distancing by maintaining a distance of six feet apart. It is hard to monitor this restriction by only a traditional surveillance system. Existing methods used deep learning to tackle this problem by designing a Deep Convolutional Neural Network (DCNN). However, these methods do not accommodate for low-power systems such as Internet-of-Things-based devices. In this paper, we propose SocialNet, a novel network design that can detect violations of social distancing in public crowd scene. SocialNet is composed of two components, (1) The detector backbone and (2) The Autoencoder. In the detector backbone, the network generates the bounding boxes of the human/person category. In the Autoencoder, the network learns to predict a score which represents the violation between each bounding box and the others. The input image is divided into nine patches and each patch goes through the Autoencoder to predict the violation score. The Autoencoder consists of the encoder which produces the latent vector for the decoder network. The decoder network outputs a real-valued vector of length fifteen as scores for each patch in the image. Furthermore, SocialNet uses mixed precision which makes it suitable for low-power devices.
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 | 0.001 |
| 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".