Research on non‐contact infrared imaging technique for multilayer storage identification of oil tanks based on an improved edge‐detection algorithm
Bibliographic record
Abstract
Abstract Detection of internal storage objects in tanks is crucial for production in the petrochemical industry and chemical raw material storage. Compared to traditional methods, infrared detection provides benefits like non‐contact operation, safety, and efficiency. In image processing, utilizing edge detection to obtain edge information is an advanced approach. By analyzing the thermal texture in infrared tank images and extracting boundaries between different regions, it is possible to predict the volume of internal storage. To address the issues of noise, lack of clarity, and discontinuity in existing image edge detection methods, a novel edge detection algorithm called wavelet transform and mathematical morphological fusion to improve edge detection (WMF‐IED) is proposed. Compared to the Roberts, Prewitt, Sobel, and Laplacian of Gaussian (LOG) methods, the WMF‐IED algorithm offers several advantages. It not only provides clear and continuous edges but also exhibits minimal mean squared error (MSE). Additionally, it achieves maximum signal‐to‐noise ratio (SNR) and peak signal‐to‐noise ratio (PSNR). These factors show the proposed algorithm's superior performance. Moreover, an experimental platform for storage tanks was designed and constructed to analyze the detection of internal storage contents using the proposed WMF‐IED algorithm. The results demonstrate that the WMF‐IED algorithm has strong universality and can detect the edges of various internal storage. The volume prediction errors using the WMF‐IED algorithm are less than 4% and 6% for liquid level detection and sludge detection, respectively. Based on the analysis and experimental results, a recommended sampling value is proposed, which can be selected to obtain the minimum error.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 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 | 0.001 |
| 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".