The Traffic Monitor project (TrafficMonitor.ai) is an open-source, community-driven initiative designed to democratize roadway data collection and transform how neighborhoods understand public streets. Built on the principle that actionable transportation data should be transparent and accessible to everyone, the project empowers citizen scientists, urban planners, and traffic advocates to monitor local roadways. By providing open hardware and software blueprints, Traffic Monitor lowers the barrier to entry for collecting accurate, holistic street metrics—helping communities collaborate to foster safer, more efficient, and sustainable transportation networks where every road user, from pedestrians to cyclists and drivers, is counted.

At the technical core of the system is a low-power, modular architecture built on commodity hardware, including Raspberry Pi processors, specialized AI TPU co-processors, high-definition camera lenses, and law-enforcement-certified Doppler radar sensors. Utilizing edge machine learning, the devices perform real-time object detection, speed measurement, and event recording locally on the device, upholding privacy while delivering immediate data feeds without needing cloud processing. Furthermore, the extensible ecosystem seamlessly pairs with environmental sensors, allowing users to concurrently monitor ambient conditions like air quality, noise levels, and particulate matter (PM 2.5) alongside vehicular and foot traffic trends.

This interactive web map serves as a visual portal for the real-time telemetry and historical data captured by Traffic Monitor deployments. By translating complex edge analytics into an intuitive, geographical interface, the map allows you to explore traffic volumes, speed patterns, foot-traffic density, and localized microclimate data across different locations. Whether evaluating intersection safety, advocating for improved bicycle and pedestrian infrastructure, or analyzing the environmental footprint of traffic flows, this interactive platform bridges raw sensor data and community-led action.

• photo_cameraTraffic Volume & Modality Data
  • Modality Split: Percentage share of total travel divided among bicycles, pedestrians, and cars.
    • Benchmarks active transportation adoption against motorized vehicle dominance over selected time ranges.
  • Average Daily Traffic (ADT): Normalized daily traffic volumes for cars, bikes, and total traffic calculated across selected filter periods. Most state departments of transportation (DOTs) and the Federal Highway Administration (FHWA) follow standard rounding tiers based on traffic volume magnitude:

    Below 100 vehicles/day	Round to nearest 10 or report exact
    100 – 999 vehicles/day	Round to nearest 10
    1,000 – 9,999 vehicles/day	Round to nearest 50 or 100
    10,000 – 99,999 vehicles/day	Round to nearest 100 or 500
    100,000+ vehicles/da	Round to nearest 1,000

    • Serves as the primary standardized metric for corridor traffic load comparison and roadway capacity design.
  • Bicycle, Pedestrian, & Car Counts: Hourly volume totals detected per mode.
    • Used to evaluate modal shift trends, peak-hour congestion, and active transportation demand across different locations or time windows.
  • Directional Counts: Categorizes directional movement relative to sensor orientation.
    • Highlights directional commuting asymmetry (e.g., morning inbound flow versus evening outbound traffic).
• radarSpeed & Safety Dynamics
  • Hourly Average Speed: Mean speed in miles per hour (mph) per mode.
    • Identifies modal speed differentials and monitors compliance with target roadway speeds.
  • Directional Average Speed: Speeds categorized by inbound and outbound travel directions.
    • Pinpoints direction-specific speeding issues or traffic bottlenecks caused by road geometry and curbside parking friction.
  • Speed Bins: Percentage breakdown of vehicles traveling within specific speed brackets (below 15 mph, 16–25 mph, 26–35 mph, and 35+ mph).
    • Evaluates speed distribution curves; essential for assessing traffic-calming effectiveness and safety risks (e.g., high percentages in 35+ mph bins in pedestrian zones).
• airAir Quality - Particulate Matter & Gases
  Ultrafine Particles: Particulate matter ≤ 1 µg/m³ in size, measured in µg/m³.
  • Generated directly by vehicle exhaust and fuel combustion. Extremely small size allows deep respiratory penetration; used to detect direct combustion proximity and fresh engine exhaust plumes.
  Fine Respirable Particles: Particulate matter ≤ 2.5 µg/m³ in size, measured in µg/m³.
  • Produced by engine combustion, secondary atmospheric reactions, and smoke. Serves as the primary public health benchmark to compare fine haze levels during peak traffic hours.
  Coarse Particles: Particulate matter ≤ 10 µg/m³ in size, measured in µg/m³.
  • Originates from mechanical abrasion, such as brake pad wear, tire wear, and re-suspended road dust. Comparing PM10 against PM2.5 isolates mechanical vehicle wear from fuel combustion emissions.
  Reducing Gases: Calibrated concentration of reducing agents (such as carbon monoxide CO and hydrocarbons), measured in ppm.
  • Emitted during incomplete fuel combustion. High concentration spikes indicate heavy traffic congestion, vehicle idling, or slow-moving traffic.
  Ammonia: Calibrated concentration of airborne ammonia (NH₃), measured in ppm.
  • Released by vehicle catalytic converters (selective catalytic reduction systems) and ambient organic sources. Measured to evaluate vehicular chemical emissions alongside surrounding urban waste or agricultural influences.
  Oxidizing Gases: Calibrated concentration of oxidizing agents (such as nitrogen dioxide NO₂ and ground-level ozone O₃), measured in ppm.
  • Key indicators of fuel combustion byproducts and photochemical smog. Measured to assess localized atmospheric pollution caused by heavy traffic exhaust.
• thermostatAtmospheric & Microclimate Metrics
  • Temperature & Dew Point: Air and condensation temperatures in °F.
    • Controls for seasonal/diurnal effects on travel mode shifts and helps calculate thermal comfort for cyclists and pedestrians.
  • Humidity & Barometric Pressure: Relative air moisture (%) and atmospheric pressure in hPa.
    • Essential baseline controls when comparing gas concentrations and particulate dynamics, as moisture impacts particle growth/settling and pressure influences pollutant trapping during inversions.
• area_chartCross-Dataset Overlay Comparisons
  • Dual-Axis Overlay: Plots traffic variables (such as car counts or speeds) against environmental metrics (such as PM2.5 or oxidizing gases) on a synchronized time scale.
    • Allows direct comparative analysis to prove or disprove causal relationships between traffic volume surges, congestion slowdowns, and localized air quality degradation over custom date ranges.