# Infrastructure-based Monocular 3D Vehicle Localization Framework with Experimental Validation

arXiv: https://arxiv.org/abs/2609.05523 · HTML: https://mlsanity.com/paper/2609.05523/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation](https://mlsanity.com/paper/2002.10111/) (2020)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://mlsanity.com/paper/2106.01178/) (2021)
- [MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships](https://mlsanity.com/paper/2003.00504/) (2020)
- [Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving](https://mlsanity.com/paper/1903.11444/) (2019)
- [Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction](https://mlsanity.com/paper/1904.01690/) (2019)
- [Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image](https://mlsanity.com/paper/1703.07570/) (2017)
- [Joint Monocular 3D Vehicle Detection and Tracking](https://mlsanity.com/paper/1811.10742/) (2018)
- [Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline](https://mlsanity.com/paper/2301.12511/) (2023)
- [Learning Occupancy for Monocular 3D Object Detection](https://mlsanity.com/paper/2305.15694/) (2023)
- [Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving](https://mlsanity.com/paper/2205.14882/) (2022)
- [InfraDet3D: Multi-Modal 3D Object Detection based on Roadside Infrastructure Camera and LiDAR Sensors](https://mlsanity.com/paper/2305.00314/) (2023)
- [BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance](https://mlsanity.com/paper/1703.00686/) (2017)
- [MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings](https://mlsanity.com/paper/2310.00400/) (2023)
- [Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography](https://mlsanity.com/paper/2103.15293/) (2021)
- [Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition](https://mlsanity.com/paper/2510.09653/) (2025)
- [Intelligent Transportation Systems Using External Infrastructure: A Literature Survey](https://mlsanity.com/paper/2112.05615/) (2021)
- [Roadside Lidar Vehicle Detection and Tracking Using Range And Intensity Background Subtraction](https://mlsanity.com/paper/2201.04756/) (2022)
- [AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training](https://mlsanity.com/paper/2309.01106/) (2023)

## Abstract (arXiv)

This paper presents a one-stage learning framework that maps monocular roadside-camera images directly to vehicle states in a ground-fixed coordinate frame. Unlike conventional approaches that first detect vehicles in the image plane and subsequently apply geometric post-processing, the proposed method leverages features from a pretrained object detector to jointly estimate each vehicle's ground-plane position, dimensions, and yaw angle. The framework therefore uses visual features not only for vehicle detection but also for direct spatial and orientation estimation. To support model training and evaluation, we develop a data-collection and label-generation pipeline based on synchronized video from a roadside camera and an unmanned aerial vehicle (UAV). Acting as a temporary top-view sensing platform, the UAV provides vehicle trajectories, dimensions, and orientations, which are transformed into the ground-fixed coordinate frame and temporally aligned with the roadside-camera images to generate ground-truth labels. The framework is evaluated using data collected during multiple experiments at the Mcity Test Facility. Results show that the proposed method can recover vehicle trajectories and orientations from monocular roadside imagery without a separate geometric post-processing stage, demonstrating its potential as a scalable approach to infrastructure-based perception at urban intersections.