An Intelligent Detection Method for Conveyor Belt Deviation State Based on Machine Vision
Bibliographic record
Abstract
To address the shortcomings of existing conveyor belt deviation detection methods, such as poor fault location accuracy, a low automation level and low reliability, a method that utilizes machine vision technology to detect belt deviations in belt conveyors is proposed.This method involves preprocessing operations on captured video images, including Region of Interest (ROI) extraction, grayscale processing, and noise reduction, thereby eliminating image noise and interference.To address the edge blurring due to Gaussian filtering and threshold setting issues in Canny detection, an enhanced edge detection technique using a guided filter and the Otsu method modifies the traditional Canny operator is introduced.Subsequent application of Hough Transform and least squares fitting processes delineate the edges of the conveyor belt and its rollers during operation.Utilizing the detected edges of the conveyor belt and rollers as references, a dual-baseline positioning method is for the first time proposed to quantify the deviation degree, facilitating the identification of deviation faults.After detection with the improved Canny algorithm, clearer contour binary images with fewer noise and impurities were obtained.Experiments conducted on images from various deviation scenarios yielded an average detection accuracy of 95.4% and a detection speed of 26 frames per second (FPS).This approach not only enhances the detection speed and accuracy but also reduces the frequency of conveyor belt failures and improves the operational efficiency of belt conveyors.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".