High Precision Underwater Object Recognition Using AI Driven Sonar Imaging and Ensemble Learning
Bibliographic record
Abstract
Marine ecosystems are compromised by lost fishing gear dumping and overfishing that destroy biodiversity and ecological balance. This paper suggests a highly sophisticated Automatic Target Recognition (ATR) system based on modern sonar imagery and artificial intelligence (AI) to enable better detection and identification of marine wildlife and underwater waste. It consists of several AI-based models made up of architectures like YOLOv11, Faster Region-Based Convolutional Neural Network (R-CNN), a specialist Convolutional Neural Network (CNN), and a hybrid ResNet-VGG ensemble to increase both accuracy and efficiency during real-time tracking. This paper focuses on inclusive data preprocessing, model enhancement, and ensemble learning in order to overcome sonar noise, reduced visibility, and occluding objects. Performance evaluation shows that the proposed ResNet-VGG ensemble achieved the highest detection accuracy of 68%, representing an 11.48% improvement over the best-performing single model (YOLOv11 at 61% accuracy). Experimental findings confirm the significant enhancement of the precision and accuracy of detections and present a scalable and efficient method for ensuring marine preservation and sustainable fishing. Subsequent research will cover the enhancement of computational efficiency, expanded training data sets, and adaptive hybrid models in order to further enhance environmental monitoring and resource management.
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 | 0.001 |
| 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 | 0.001 | 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".