{"ID":2849301,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24902","arxiv_id":"2510.24902","title":"Pixels to Signals: A Real-Time Framework for Traffic Demand Estimation","abstract":"Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic signal optimization. This paper presents the first component, vehicle detection. The methodology involves analyzing multiple sequential frames from a camera feed to compute the background, i.e. the underlying roadway, by averaging pixel values over time. The computed background is then utilized to extract the foreground, where the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is applied to detect vehicles. With its computational efficiency and minimal infrastructure modification requirements, the proposed methodology offers a practical and scalable solution for real-world deployment.","short_abstract":"Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primar...","url_abs":"https://arxiv.org/abs/2510.24902","url_pdf":"https://arxiv.org/pdf/2510.24902v1","authors":"[\"H Mhatre\",\"M Vyas\",\"A Mittal\"]","published":"2025-10-28T19:04:53Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}