Augmenting Face Detection in Extremely Low-Light CCTV Footage Using the EDCE Enhancement Model
Bibliographic record
Abstract
Face detection constitutes a pivotal task in computer vision, with its utility extending across security and surveillance, biometrics, human-computer interaction, and entertainment.This technology facilitates the automated recognition and location of human faces within images or videos, a feature instrumental for identification, authentication, and tracking.However, the efficacy of face detection algorithms is compromised under low-light conditions prevalent in CCTV videos, due to variations in illumination levels.To address this challenge, this study introduces a video enhancement method, the Enhanced Deep Curve Estimation (EDCE), designed to augment the quality of low-light CCTV footage, thereby improving face detection accuracy.To circumvent the redundancy of frames during face detection from the input video, a key frame extraction method was employed.Subsequently, the Retina Face was utilized to detect faces from the enhanced CCTV video keyframes.The CCTV videos evaluated in this study were sourced from public cameras, and the performance of the EDCE model was assessed against other existing enhancement models.The findings reveal that the EDCE model exhibits superior performance with a Peak Signalto-Noise Ratio (PSNR) of 21.37 and a Structural Similarity Index Measure (SSIM) of 0.83.Further, the face detection evaluation yielded an Average Precision of 0.847, signifying the effectiveness of our enhancement methodology.This study, thus, underscores the potential of the EDCE model in enhancing the performance of face detection systems under challenging low-light conditions.
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".