Closed-Loop Region of Interest Enabling High Spatial and Temporal Resolutions in Object Detection and Tracking via Wireless Camera
Bibliographic record
Abstract
The trade-off between spatial and temporal resolution remains a fundamental challenge in machine vision. A captured image often contains a significant amount of redundant information, and only a small region of interest (ROI) is necessary for object detection and tracking. In this paper, we first systematically characterize the effects of ROI on camera capturing, data transmission, and image processing. We then present the closed-loop ROI algorithm capable of high spatial and temporal resolution as well as wide scanning field of view (FOV) in single and multi-object detection and tracking via real-time wireless video streaming. With the feedback from real-time object tracking, the wireless camera is able to capture and transmit only the ROI which in turn enhances both the spatial and temporal resolution in object tracking. In addition, the proposed approach can still maintain a large FOV by processing regions outside of the ROI at lower spatial and temporal resolutions. When applied to a high spatial resolution wireless stream (5 MegaPixels), the closed-loop ROI algorithm improves the temporal resolution by up to 10× (from 2.4FPS to 22.5FPS). Specifically, camera processing is improved by up to 4.7×, data transmission is improved by up to 160×, and PC processing is improved by up to 2.5×. In a person tracking experiment, the closed-loop ROI algorithm enables a wide-angle camera to outperform both a normal wide-angle camera-which suffers from poor temporal resolution and motion blur-and a pan & tilt camera-which cannot automatically refresh tracking after the tracking is lost.
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 | 0.001 | 0.002 |
| 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".