An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers

• URL: http://arxiv.org/abs/2606.05149v1
• Date: Wed, 03 Jun 2026 17:53:33 GMT
• Title: An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers
• Abstract summary: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles do not exist in the open literature.<n>This paper presents an open-source two-stage computer vision pipeline combining a pre-trained RT-DETR detector for coarse vehicle localization with a fine-tuned Vision Transformer.<n>A confidence-based abstention mechanism withholds Stage 2 predictions when softmax output falls below 0.60, producing unknown labels rather than silent misclassifications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature. Standard object detection benchmarks provide only coarse vehicle labels (car, truck, bus, motorcycle), while existing fine-grained recognition systems are trained on controlled imagery and lack evaluation for deployment robustness across recording sites. This paper presents an open-source two-stage computer vision pipeline combining a pre-trained RT-DETR detector for coarse vehicle localization with a fine-tuned Vision Transformer (ViT-Base/16) for six-category body-type classification: passenger car, SUV, pickup truck, minivan, large van, and commercial truck. A confidence-based abstention mechanism withholds Stage 2 predictions when softmax output falls below 0.60, producing unknown labels rather than silent misclassifications. Evaluated on 3,805 annotated overtaking events from a bicycle-lane corridor in Ann Arbor, Michigan (in-distribution), the pipeline achieved 0.94 accuracy with per-class F1 scores from 0.91 (minivan) to 0.97 (SUV). On an independent out-of-distribution evaluation of 311 events from an open cycling dataset without retraining, accuracy was 0.89. Three of four well-represented categories maintained F1 at or above 0.90 under domain shift. The largest degradation was observed for minivan (F1 = 0.72), driven by abstention rate rising from 2.4% to 25.0% rather than active misclassification, consistent with the mechanism propagating genuine model uncertainty. The full pipeline, including inference scripts, training code, evaluation utilities, and model weights, is released as open-source software to support reproducibility and reuse across roadside video archives and cycling safety research.

Related papers

• Sensitivity Analysis of GRU, LSTM and Transformer Encoder in Classification of Automated Driving Systems [0.5156484100374058]
  Monitoring systems to independently verify which automated driving system is active are important for safety monitoring, regulatory compliance, insurance assessment, and anomaly detection.<n>We first evaluate the effectiveness of three sequence-based classification models: Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) networks, and a Transformer encoder model.<n>All three models achieve strong clean-data performance with macro F1-scores of 0.92 (GRU), 0.90 (LSTM), and 0.93 (Transformer encoder model) when trained on clean data.
  arXiv  Detail & Related papers  (2026-07-25T01:31:37Z)
• Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective [76.02772556944073]
  Environmental illusions are naturally existing yet overlooked phenomena in real-world driving environments.<n>They can disturb visual perception, leading to misinterpretation of the scene and posing serious safety risks to autonomous driving systems.<n>We introduce the first benchmark, LanEvil++, for evaluating the robustness of lane perception under environmental illusions.
  arXiv  Detail & Related papers  (2026-07-07T03:15:00Z)
• NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity [1.889930012459364]
  NOVA is an autonomous symbolic regression framework for car-following and lane-change structures.<n>It is applied to 4,765,788 active driving observations from the NGSIM I-80 and US-101 datasets.<n>NOVA achieves 67.4% balanced accuracy under strict vehicle-ID holdout on 502 unseen drivers.
  arXiv  Detail & Related papers  (2026-06-09T08:47:39Z)
• A Geometry-Informed Computer Vision Method for Detecting and Examining Overtaking Vehicles From A Bicycle [0.0]
  We present a geometry-informed computer vision pipeline that automates overtaking event detection from a single bicycle-mounted camera.<n>The pipeline achieved 97.8% recall with zero false positives and identified overtaking intentions a mean of 2.44 seconds before vehicle passage.
  arXiv  Detail & Related papers  (2026-06-03T17:41:00Z)
• Instance-level Visual Active Tracking with Occlusion-Aware Planning [61.982298426203165]
  Visual Active Tracking (VAT) aims to control cameras to follow a target in 3D space.<n>VAT faces two key bottlenecks in real-world deployment: confusion from visually similar distractors and severe failure under occlusions.<n>We propose OA-VAT, a unified pipeline with three complementary modules.
  arXiv  Detail & Related papers  (2026-04-23T09:11:50Z)
• AI-Driven Predictive Maintenance with Real-Time Contextual Data Fusion for Connected Vehicles: A Multi-Dataset Evaluation [0.0]
  This paper presents a simulation-validated proof-of-concept framework for V2X-augmented predictive maintenance.<n>It integrates on-board sensor streams with external contextual signals.<n>Edge inference is estimated to reduce latency from 3.5s to under 1.0s versus cloud-only processing.
  arXiv  Detail & Related papers  (2026-03-07T06:08:45Z)
• Real-time Secondary Crash Likelihood Prediction Excluding Post Primary Crash Features [6.477496237661746]
  We propose a hybrid crash likelihood prediction framework that does not depend on postcrash features.<n>A dynamic post-temporal window is designed to extract real-time traffic flow and environmental features from primary crash locations and their upstream segments.<n>Experiments on Florida freeways demonstrate that proposed the hybrid framework correctly identifies 91% of secondary crashes with a low false alarm rate of 0.20.
  arXiv  Detail & Related papers  (2026-02-17T22:49:33Z)
• Commercial Vehicle Braking Optimization: A Robust SIFT-Trajectory Approach [6.751326589596112]
  A vision-based trajectory analysis solution is proposed to address the "zero-speed braking" issue caused by inaccurate Controller Area Network (CAN) signals.<n>The algorithm utilizes the NVIDIA Jetson AGX Xavier platform to process sequential video frames from a blind spot camera.<n>The deployment on-site shows an 89% reduction in false braking events, a 100% success rate in emergency braking, and a fault rate below 5%.
  arXiv  Detail & Related papers  (2025-12-21T05:06:16Z)
• Overtake Detection in Trucks Using CAN Bus Signals: A Comparative Study of Machine Learning Methods [51.28632782308621]
  We focus on overtake detection using Controller Area Network (CAN) bus data collected from five in-service trucks provided by the Volvo Group.<n>We evaluate three common classifiers for vehicle manoeuvre detection, Artificial Neural Networks (ANN), Random Forest (RF), and Support Vector Machines (SVM)<n>Our pertruck analysis also reveals that classification accuracy, especially for overtakes, depends on the amount of training data per vehicle.
  arXiv  Detail & Related papers  (2025-07-01T09:20:41Z)
• Predicting Overtakes in Trucks Using CAN Data [51.28632782308621]
  We investigate the detection of truck overtakes from CAN data. Our analysis covers up to 10 seconds before the overtaking event. We observe that the prediction scores of the overtake class tend to increase as we approach the overtake trigger.
  arXiv  Detail & Related papers  (2024-04-08T17:58:22Z)
• DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving [76.29141888408265]
  We propose a large-scale dataset containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset.
  arXiv  Detail & Related papers  (2023-04-03T17:37:00Z)
• Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation [0.3441021278275805]
  There is no difference between accident and near-miss at the time before the accident happened. Our contribution is to redefine the accident definition and re-annotate the accident inconsistency on DADA-2000 dataset together with near-miss. The proposed method integrates two different components: conditional style translation (CST) and separable 3-dimensional convolutional neural network (S3D)
  arXiv  Detail & Related papers  (2023-01-06T22:04:47Z)
• Fine-Grained Vehicle Classification in Urban Traffic Scenes using Deep Learning [0.0]
  Fine-grained vehicle classification appears to be a challenging task as compared to vehicle coarse classification. Existing Vehicle Make and Model Recognition (VMMR) systems have been developed on synchronized and controlled traffic conditions. Need for robust VMMR in complex, urban, heterogeneous, and unsynchronized traffic conditions still remain an open research area.
  arXiv  Detail & Related papers  (2021-11-17T21:19:03Z)
• Driver Intention Anticipation Based on In-Cabin and Driving Scene Monitoring [52.557003792696484]
  We present a framework for the detection of the drivers' intention based on both in-cabin and traffic scene videos. Our framework achieves a prediction with the accuracy of 83.98% and F1-score of 84.3%.
  arXiv  Detail & Related papers  (2020-06-20T11:56:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.