2024 Project Descriptions
Social Science Curriculum
In the My Streetscape Summer Research Institute, students are trained as youth community researchers by learning about social sciences research methods, such as surveys, interviews, and ethnography. In teams, students use what they have learned about these methods to design a social science research project to get community input on the engineering projects and technologies they are working on.
Students design data gathering tools, go on field trips where they go into the streetscape to engage with community members and gather data through conversations and observations, and analyze the data they collected before writing their final Research Reports. In the Research Reports, students share what their projects were, how they collected their original data, what they learned from community members, and how the findings informed their engineering project and technologies.
Additionally, the students create Photovoice Exhibits, another method for community engagement and way of communicating visually and through narratives what they learned in the engineering sessions and social science sessions and how they think interdisciplinary about their projects technologies.
ENHANCING MICROMOBILITY SAFETY WITH OBJECT DETECTION
Faculty Advisor:
Zoran Kostic
Engineering Mentor:
Sanjeev Narasimhan
Social Science Mentor:
Nicole Lum
Our research explored Vision-Language models for Zero-Shot Image tagging in urban intersections, to identify uncommon traffic-related objects (construction equipment, fire trucks, barricades, etc). We study the efficiency of using large pre-trained models such as Segment Anything (SAM) and LLaVA on high-resolution images captured from our cameras for traffic anomaly detection.
Our recent work shows promising results; so we aim to apply this approach to detecting small transportation devices such as scooters, e-bikes, segways etc. (micromobility vehicles) which are not easily recognized by current detection systems. We want to compare zero-shot and few-shot approaches with the more traditional approach of training object detection models to identify micromobility devices.
Mentees
High School for Math, Science and Engineering at City College
Xavier High School
Stuyvesant High School
SCALEDDOWN TESTBED
Faculty Advisor:
Sharon Di
Engineering Mentor:
Qi Gao
Social Science Mentor:
Miguel Beltran
Testing and deploying new transportation technologies in urban areas pose significant challenges, including managing autonomous vehicles, adaptive traffic control systems, and traffic monitoring tools. These complexities stem from high vehicle volumes, diverse traffic participants—such as pedestrians, cyclists, and electric delivery bikes—and unpredictable elements like red-light violations and obstructions from legally and illegally parked vehicles or buildings. While simulations can address certain scenarios, relying solely on simulations is impractical and unsafe for unproven technologies. Additionally, real-world testing in controlled environments often incurs substantial financial and time costs.
To overcome these challenges, we are developing a scaled-down, real-world intersection network testbed. This testbed enables efficient and effective evaluation of technologies such as autonomous driving systems, adaptive traffic signals, and pedestrian warning systems.
Mentees
Xavier High School
Manhattan Center for Science and Math
Columbia Secondary School
CONNECTED ACCESSIBLE PEDESTRIAN SIGNALS
Faculty Advisors:
Sharon Di & Anthony Vanky
Engineering Mentors:
Yongjie Fu & Joan Akibode
Social Science Mentors:
Jenny Fondren, Ki-Sang Yi & Timothy Small
This project explores innovative applications for connected Accessible Pedestrian Signals (APS). High school students engage in hands-on research to design and prototype connected crosswalk buttons that enhance pedestrian safety—particularly for elderly and mobility-challenged individuals. Using ESP32 microcontrollers and Python programming, students build, test, and network IoT-enabled APS devices, then refine their designs based on collaborative brainstorming about added functionalities such as detecting slow or large pedestrian groups. The project integrates engineering practice, coding, and user-centered design while fostering reflection on how connected infrastructure can create safer, smarter city streets.
Mentees
Team 1
Fiorello H. LaGuardia High School
Manhattan Center for Science and Math
Saint Jean Baptiste High School
Urban Assembly Gateway School for Technology
Team 2
Manhattan Center for Science and Math
Manhattan Center for Science and Math
Park East High School
Park East High School
STREETSCAPE TECHNOLOGY
Faculty Advisor: Jason Hallstrom
Engineering Mentor:
Suvosree Chatterjee
This interdisciplinary project combines engineering and social science approaches to examine how data-driven streetscape technologies can improve urban safety while addressing public concerns about privacy and surveillance. Using data collected from cameras, sensors, and public records across Broward, Miami-Dade, and Palm Beach counties, students cleaned, analyzed, and modeled traffic accident data in Python to identify high-risk intersections and predict areas most prone to severe crashes.
Complementing this technical work, their social science research investigated residents’ perceptions of privacy, safety, and trust in the city’s use of surveillance-based technologies, with a particular focus on income as a factor influencing attitudes toward data collection. Through surveys conducted over four weeks, they explored how citizens balance the benefits of increased traffic safety with the ethical and social implications of being monitored in public spaces. Together, their findings aim to inform smarter, safer, and more socially responsible urban technology deployment.
Mentees
Team 1
Spanish River High School
Boca Raton Community High School
Palm Beach Gardens High School
Team 2
Suncoast Community High School
Alexander W. Dreyfoos School of the Arts
West Boca Raton Community High School