Semantic Topic Analysis of Traffic Camera Images

TL;DR

This paper introduces a novel NLP-inspired method called BoLW for analyzing traffic camera images using textual labels, enabling semantic analysis of traffic patterns and weather events without manual image interpretation.

Contribution

The paper presents the BoLW model combined with LDA to analyze traffic camera labels, providing a new way to extract semantic insights from image data.

Findings

Identified weather event sensitivity in traffic cameras

Detected temporal traffic patterns

Analyzed impact of infrequent events like storms

Abstract

Traffic cameras are commonly deployed monitoring components in road infrastructure networks, providing operators visual information about conditions at critical points in the network. However, human observers are often limited in their ability to process simultaneous information sources. Recent advancements in computer vision, driven by deep learning methods, have enabled general object recognition, unlocking opportunities for camera-based sensing beyond the existing human observer paradigm. In this paper, we present a Natural Language Processing (NLP)-inspired approach, entitled Bag-of-Label-Words (BoLW), for analyzing image data sets using exclusively textual labels. The BoLW model represents the data in a conventional matrix form, enabling data compression and decomposition techniques, while preserving semantic interpretability. We apply the Latent Dirichlet Allocation (LDA) topic model to decompose the label data into a small number of semantic topics. To illustrate our approach, we use freeway camera images collected from the Boston area between December 2017-January 2018. We analyze the cameras' sensitivity to weather events; identify temporal traffic patterns; and analyze the impact of infrequent events, such as the winter holidays and the "bomb cyclone" winter storm. This study demonstrates the flexibility of our approach, which allows us to analyze weather events and freeway traffic using only traffic camera image labels.