Understanding Traffic Density from Large-Scale Web Camera Data

By Shanghang Zhang, Guanhang Wu, João Paulo Costeira, José M. F. Moura. 2017

145 citations recorded by the source corpus.

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 optimization based and deep learning based methods. To avoid individual vehicle detection or tracking, both methods map the dense image feature into vehicle density, one based on rank constrained regression and the other based on fully convolutional networks (FCN). The regression based method learns different weights for different blocks of the image to embed road geometry and significantly reduce the error induced by camera perspective. The FCN based method jointly estimates vehicle density 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 (MAE) from 10.99 to 5.31 on the public dataset TRANCOS compared with the state-of-the-art baseline.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Domain Adaptation for Traffic Density Estimation (2021, methodology): “…Domain Shift - TRANCOS Dataset (Guerrero-Gómez-Olmedo et al., 2015) Hydra-CNN (Oñoro-Rubio and López-Sastre, 2016) 10.99 68.70 0.71 FCN-MT (Zhang et al., 2017a) 5.31 - 0.85 LC-ResFCN (Laradji et al., 2018) 3.32 - - Baseline - CSRNet (Li et al., 2018) 3.56 30.64 0.10 Our Approach 3.30…”
Designing a Moral Compass for the Future of Computer Vision Using Speculative Analysis (2017, unknown): “Without a doubt, combining advanced machine learning with troves of image data is likely to aid human causes such as health monitoring [37] and accelerate efficiency in areas such as archiving [17] and traffic analysis [66].”
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (2018, background): “With the rapid increase of population of major cities, crowd scene analysis [11, 33] has already become an important security technique in video surveillance [16, 20, 36].”
STREETS: A Novel Camera Network Dataset for Traffic Flow (2019, methodology): “Existing work typically examines vehicle detection and counting or traffic congestion at individual cameras [12, 39, 40, 41, 42, 43].”
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs (2017, methodology): “Also, the methods developed for crowd counting can be extended to counting tasks in other ﬁelds such as cell microscopy [38, 36, 16, 6], vehicle counting [23, 49, 48, 11, 34], environmental survey [8, 43], etc.”
Unsupervised vehicle counting via multiple camera domain adaptation (2020, methodology): “We conduct preliminary experiments using the WebCamT dataset introduced in [13].”