Acoustic-Based Vehicle Detection and Classification on Malaysian Roads
Bibliographic record
Abstract
Vehicle detection and classification (VDC) plays a significant role in modern transportation. It contributes to various applications such as traffic monitoring, military surveillance, toll collection, and bridge engineering. The steadily increasing number of vehicles on Malaysian roads highlights the pressing need for robust VDC systems. In this context, this study investigates acoustic-based VDC for Malaysian roadways. Accordingly, we collected pass-by vehicle audio (PVA) recordings in accordance with ISO 11819-1 to emulate real-world vehicle classification scenarios. Short-Time Energy thresholding was employed for accurate vehicle detection, while the IDMT-Traffic benchmark dataset was used to train a vehicle classification model. Log Mel-spectrogram features were extracted, and a Convolutional Neural Network (CNN) classifier was applied for model training. The classification accuracy was examined at different down sampling rates, including <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$22.05 \text{kHz}, 24 \text{kHz}$</tex> and 32 kHz. The proposed system achieved 96.19% vehicle detection accuracy and superior classification performance was observed at a down sampling rate of 22.05 kHz with an accuracy of 73%. However, 24 kHz and 32 kHz yielded lower accuracies of 61% and 66%, respectively. Overall, the results demonstrate the feasibility of using an open-source dataset for model training and applying it to real-world data, specifically vehicle sound recordings collected in Malaysia. This highlights the potential for developing practical and scalable VDC systems without the need for extensive locally labeled data.
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 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 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".