Deep Learning-driven Blind Spot Detection for Forklifts in Industrial Environments
Bibliographic record
Abstract
Abstract In modern industrial settings, ensuring the safety of human workers coexisting with heavy machinery like forklifts is paramount. Traditional safety measures often fall short in addressing dynamic hazards, especially in blind spot areas where visibility is limited. This research introduces an advanced blind spot detection system utilizing deep learning techniques specifically designed for industrial environments. The system leverages the YOLOv8 architecture, enhanced through transfer learning, and optimized with model pruning and quantization techniques to achieve high accuracy and low latency, operating at 45 FPS on edge devices with a mean Average Precision (mAP) of 97.3%. The detection models are integrated with a real-time video processing pipeline using the RTSP protocol and OpenCV for spatial awareness. The system incorporates a novel attention mechanism to improve detection accuracy in challenging conditions, such as occlusions and varying lighting. Real-time alerts are provided via an integrated hardware system using ESP8266 microcontrollers and Node-RED for orchestration, ensuring immediate hazard notifications to operators. Extensive experiments in an automotive wheel manufacturing facility validate the system’s effectiveness, demonstrating an improvement of up to 5% in mAP compared to traditional methods. This work contributes to a scalable, efficient, and highly accurate solution for enhancing safety in high-risk industrial environments by addressing critical blind spot hazards in real time.
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 | 0.000 |
| 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".