GICEDCam: A Geospatial Internet of Things Framework for Complex Event Detection in Camera Streams
Bibliographic record
Abstract
Complex event detection (CED) adds value to camera stream data in various applications such as workplace safety, task monitoring, security, and health. Recent CED frameworks have addressed the issues of limited spatiotemporal labels and costly training by decomposing the CED into low-level features, as well as spatial and temporal relationship extraction. However, these frameworks suffer from high resource costs, low scalability, and an increased number of false positives and false negatives. This paper proposes GICEDCAM, which distributes CED across edge, stateless, and stateful layers to improve scalability and reduce computation cost. Additionally, we introduce a Spatial Event Corrector component that leverages geospatial data analysis to minimize false negatives and false positives in spatial event detection. We evaluate GICEDCAM on 16 camera streams covering four complex events. Relative to a strong open-source baseline configured for our setting, GICEDCAM reduces end-to-end latency by 36% and total computational cost by 45%, with the advantage widening as objects per frame increase. Among corrector variants, Bayesian Network (BN) yields the lowest latency, Long Short-Term Memory (LSTM) achieves the highest accuracy, and trajectory analysis offers the best accuracy-latency trade-off for this architecture.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".