# Understanding Traffic Density from Large-Scale Web Camera Data

arXiv: https://arxiv.org/abs/1703.05868 · HTML: https://mlsanity.com/paper/1703.05868/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2017.

## Built on by (most cited first, 18 of 18)

- [Context Understanding in Computer Vision: A Survey](https://mlsanity.com/paper/2302.05011/) (2023)
- [Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography](https://mlsanity.com/paper/2103.15293/) (2021)
- [Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling](https://mlsanity.com/paper/2206.01319/) (2022)
- [Multi-Camera Vehicle Counting Using Edge-AI](https://mlsanity.com/paper/2106.02842/) (2021)
- [TrafficCAM: A Versatile Dataset for Traffic Flow Segmentation](https://mlsanity.com/paper/2211.09620/) (2022)
- [Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification](https://mlsanity.com/paper/2304.04042/) (2023)
- [Applications of Deep Learning in Fish Habitat Monitoring: A Tutorial and Survey](https://mlsanity.com/paper/2206.05394/) (2022)
- [Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation](https://mlsanity.com/paper/2111.00941/) (2021)
- [Identifying High Accuracy Regions in Traffic Camera Images to Enhance the Estimation of Road Traffic Metrics: A Quadtree-Based Method](https://mlsanity.com/paper/2106.14049/) (2021)
- [Scalable and Real-time Multi-Camera Vehicle Detection, Re-Identification, and Tracking](https://mlsanity.com/paper/2204.07442/) (2022)
- [Deep Learning Techniques for Visual Counting](https://mlsanity.com/paper/2206.03033/) (2022)
- [Context Enhanced Transformer for Single Image Object Detection](https://mlsanity.com/paper/2312.14492/) (2023)
- [Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm](https://mlsanity.com/paper/2102.09191/) (2021)
- [Peng Cheng Object Detection Benchmark for Smart City](https://mlsanity.com/paper/2203.05949/) (2022)
- [MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting](https://mlsanity.com/paper/2208.06761/) (2022)
- [A Unified Object Counting Network with Object Occupation Prior](https://mlsanity.com/paper/2212.14193/) (2022)
- [STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction](https://mlsanity.com/paper/2306.14476/) (2023)
- [BMD-45: A Large-Scale CCTV Vehicle Detection Dataset for Urban Traffic in Developing Cities](https://mlsanity.com/paper/2604.24419/) (2026)

## Abstract (arXiv)

Understanding traffic density from large-scale web camera (webcam) videos is a challenging problem because such videos have low spatial and temporal resolution, high occlusion and large perspective. To deeply understand traffic density, we explore both deep learning based and optimization based methods. To avoid individual vehicle detection and tracking, both methods map the image into vehicle density map, one based on rank constrained regression and the other one based on fully convolution networks (FCN). The regression based method learns different weights for different blocks in the image to increase freedom degrees of weights and embed perspective information. The FCN based method jointly estimates vehicle density map and vehicle count with a residual learning framework to perform end-to-end dense prediction, allowing arbitrary image resolution, and adapting to different vehicle scales and perspectives. We analyze and compare both methods, and get insights from optimization based method to improve deep model. Since existing datasets do not cover all the challenges in our work, we collected and labelled a large-scale traffic video dataset, containing 60 million frames from 212 webcams. Both methods are extensively evaluated and compared on different counting tasks and datasets. FCN based method significantly reduces the mean absolute error from 10.99 to 5.31 on the public dataset TRANCOS compared with the state-of-the-art baseline.