Improving Object Detection in Low Light Surveillance Using Hybrid Image Fusion Techniques Over Traditional Filtering Methods
Bibliographic record
Abstract
The modern surveillance systems face a critical issue to enhance the accuracy of object detection in low-light environments. The classic filtering methods for enhancement fail to maintain crucial detection features like edge points and details with textures as well as illumination differences. A new innovative image fusion framework gets presented within this research because it unites multi-exposure image fusion with guided filtering alongside deep learning-based denoising features to advance object detection accuracy during low-light situations. The system uses wavelet transforms to merge visible and infrared images by CNN-based fusion approaches which enhances spatial definition while preserving semantic fidelity. The proposed system demonstrates superior outcomes against traditional filtering approaches when it comes to detection precision and recall as well as processing efficiency. The proposed method proves its ability to boost feature visibility across different surveillance datasets through multiple experimental evaluations. Experiments on the ExDark (10 117 images) and FLIR-ADAS (13 192 frames) datasets show a mean-Average-Precision (mAP@0.5) of 79.3 %, a+17.9 pp gain over Gaussian filtering and +9.6 pp over CLARE baselines while sustaining 59 ms inference latency on an NVIDIA RTX 4080. These results confirm the framework's suitability for real-time urban surveillance.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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 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".