# BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance

arXiv: https://arxiv.org/abs/1703.00686 · HTML: https://mlsanity.com/paper/1703.00686/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2017.

## Built on by (most cited first, 23 of 23)

- [Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task](https://mlsanity.com/paper/2203.13608/) (2022)
- [RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception](https://mlsanity.com/paper/2403.10145/) (2024)
- [I-24 MOTION: An instrument for freeway traffic science](https://mlsanity.com/paper/2301.11198/) (2023)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [Trends in Vehicle Re-identification Past, Present, and Future: A Comprehensive Review](https://mlsanity.com/paper/2102.09744/) (2021)
- [Network-level Safety Metrics for Overall Traffic Safety Assessment: A Case Study](https://mlsanity.com/paper/2201.13229/) (2022)
- [Traffic Camera Calibration via Vehicle Vanishing Point Detection](https://mlsanity.com/paper/2103.11438/) (2021)
- [Leverage Weakly Annotation to Pixel-wise Annotation via Zero-shot Segment Anything Model for Molecular-empowered Learning](https://mlsanity.com/paper/2308.05785/) (2023)
- [Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey](https://mlsanity.com/paper/2412.00348/) (2024)
- [The Interstate-24 3D Dataset: a new benchmark for 3D multi-camera vehicle tracking](https://mlsanity.com/paper/2308.14833/) (2023)
- [Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection](https://mlsanity.com/paper/2408.15637/) (2024)
- [MC-BEVRO: Multi-Camera Bird Eye View Road Occupancy Detection for Traffic Monitoring](https://mlsanity.com/paper/2502.11287/) (2025)
- [A Fine-Grained Vehicle Detection (FGVD) Dataset for Unconstrained Roads](https://mlsanity.com/paper/2212.14569/) (2022)
- [SKoPe3D: A Synthetic Dataset for Vehicle Keypoint Perception in 3D from Traffic Monitoring Cameras](https://mlsanity.com/paper/2309.01324/) (2023)
- [VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification](https://mlsanity.com/paper/2311.16278/) (2023)
- [Automated Object Behavioral Feature Extraction for Potential Risk Analysis based on Video Sensor](https://mlsanity.com/paper/2107.03554/) (2021)
- [Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning](https://mlsanity.com/paper/2205.10011/) (2022)
- [ATEAM: Knowledge Integration from Federated Datasets for Vehicle Feature Extraction using Annotation Team of Experts](https://mlsanity.com/paper/2211.09098/) (2022)
- [Efficient Vision-based Vehicle Speed Estimation](https://mlsanity.com/paper/2505.01203/) (2025)
- [Explainable Part-Based Vehicle Classifier with Spatial Awareness](https://mlsanity.com/paper/2605.07831/) (2026)
- [Calibration-Free Vehicle Speed Estimation: A Monocular Keypoint-Template Approach](https://mlsanity.com/paper/2608.16785/) (2026)
- [Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition](https://mlsanity.com/paper/2608.29929/) (2026)
- [Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validation](https://mlsanity.com/paper/2609.05523/) (2026)

## Abstract (arXiv)

In this paper, we focus on fine-grained recognition of vehicles mainly in traffic surveillance applications. We propose an approach that is orthogonal to recent advancements in fine-grained recognition (automatic part discovery and bilinear pooling). In addition, in contrast to other methods focused on fine-grained recognition of vehicles, we do not limit ourselves to a frontal/rear viewpoint, but allow the vehicles to be seen from any viewpoint. Our approach is based on 3-D bounding boxes built around the vehicles. The bounding box can be automatically constructed from traffic surveillance data. For scenarios where it is not possible to use precise construction, we propose a method for an estimation of the 3-D bounding box. The 3-D bounding box is used to normalize the image viewpoint by "unpacking" the image into a plane. We also propose to randomly alter the color of the image and add a rectangle with random noise to a random position in the image during the training of convolutional neural networks (CNNs). We have collected a large fine-grained vehicle data set BoxCars116k, with 116k images of vehicles from various viewpoints taken by numerous surveillance cameras. We performed a number of experiments, which show that our proposed method significantly improves CNN classification accuracy (the accuracy is increased by up to 12% points and the error is reduced by up to 50% compared with CNNs without the proposed modifications). We also show that our method outperforms the state-of-the-art methods for fine-grained recognition.