Research Lead: Murat Arcak
UC Campus(es): UC Berkeley
Problem Statement: A transformation is taking place in urban curb management: its stationary use as parking space is waning while it is increasingly becoming a space for dynamic interactions between people and vehicles. This transformation is fueled in part by the increasing public reliance on transportation network companies (TNCs), like Uber and Lyft, and on delivery services for food and consumer products. The curb space is also becoming an important location for bikeways, bus lanes, street vendors (e.g., food trucks), and paratransit pickups and drop-offs. How cities manage this public resource for the benefit of local economies is a timely problem, whose solution relies on first understanding emerging curb usage patterns over time and space. Currently no systematic method exists for identifying these patterns though there is great untapped potential for doing so with emerging machine learning technologies and non-traditional data sources, such as dashboard cameras mounted on shuttle buses, parking enforcement, and other vehicles that routinely traverse curb spaces. When combined with stationary cameras, these provide an excellent data source covering broad spans of time and multiple locations.
Project Description: This project will identify spatial and temporal curb usage patterns from data collected by multiple stationary and mobile cameras operating near the UC Berkeley campus. Dashboard cameras installed on local shuttle buses together with existing stationary cameras will be used to identify hot spots and times of day when curb activity peaks, disrupting traffic flow, limiting access to shuttle and public bus stops, and creating safety hazards. The research will further identify the types of commercial delivery vehicles using curb spaces, and track their arrival and departure times. Using visual data collected by the cameras and object detection algorithms based on deep learning, the researcher will identify the types of curb activity and specific vehicles using curb space (Amazon, USPS, UPS, FedEx, etc.) across the campus periphery and their distribution over the day, week, and year. The advanced data analysis technologies pioneered in this study will provide information to enable dynamic allocation of curb space to different types of activity, including a potential reservation system for delivery vehicles, thus facilitating freight and goods movement. The results will serve to establish the feasibility of the proposed data collection and analysis methodology that can be adopted by cities and public institutions throughout the state.
Status: In Progress