Join us to participate in the upcoming 2019 City:One Challenge. 

Numina, a Data Utility & API for Streets

Numina measures all modes of street-level activity, to inform the design of more equitable infrastructure and mobility programs.

Photo of Tara Pham
3 5

Written by


Numina delivers real-time mobility insights from streets to make cities more responsive — namely, by building a street-level data utility to support walkability, bikeability, interactivity, and efficiency in cities. Our standalone sensor platform uses computer vision to measure how people and objects move throughout streets and public spaces. Numina’s real-time intelligence helps planners and municipal governments understand, map, and improve how streets and public spaces are actually used. Numina provides counts of each type of traveler or object, as well as their speeds, paths, directionality, proximities to one another, dwell times in key locations, and more — all of which accessible through a custom data dashboard and a real-time API.


The public and private sectors invest billions of dollars in infrastructure every year, informed by old, static census data and by car counts. Meanwhile, cities lack data about how people move — whether on foot or bicycle or other modes. Cities therefore can easily justify infrastructure for cars but not necessarily for people or for multimodal trips. As transportation trends shift in ways we’ve never seen before, there’s a new opportunity for Pittsburgh to make targeted data-driven decisions regarding urban mobility and multimodal travel. Numina measures all modes in streets so that cities have such data, to inform more equitable and more sustainable infrastructure, which will support a more seamless and enjoyable transportation experience for everyone.


Numina is an end-to-end solution that delivers real-time street-level intelligence, with a focus on the things that don’t move in lanes and are missed by traditional traffic sensors. Numina generates the “desire lines” of pedestrians, cyclists, wheelchairs, scooters, trucks — all kinds of things that planners and mobility operators need to better understand in order to design safer and more enjoyable transportation experiences.

Our hardware—made in Long Island City, Queens, NY—very easily mounts to street infrastructure (such as light poles) and detects pedestrians, bicycles, different classes of vehicles (cars, buses, trucks), and other objects in streets, plazas, and public spaces. The insights that Numina produces off of this anonymous, aggregate data include counts of each type of traveler or object, as well as their speeds, paths, directionality, proximities to one another, dwell times in key locations, and such events as near misses.

It is our commitment to provide intelligence without surveillance. By design, the sensor processes all raw data onboard the device, only distilling it down to the smallest, critical, anonymous data necessary. To glean meaningful insights, the system does not store or transmit off-site any imagery or personally identifiable information.

In addition to providing our data via an intuitive web dashboard, Numina’s platform also publishes data via JSON API, which updates by the minute and which can be easily integrated into any number of applications, data analysis, or processing tools outside of our proprietary technology stack. As Pittsburgh has been such a leader in new mobility technology, it is an ideal testbed for Numina data to, for example, feed multimodal data into autonomous vehicle training simulations, so they can train on real-world behaviors rather than on idealized (i.e. unrealistic) assumptions about human behavior.


By building and providing this data utility for Pittsburgh, we will enable its planners, designers, and engineers to make targeted decisions around the design, programming, and infrastructure for mobility in the city or—in other words—smarter transportation choices. Simultaneously, because this data is anonymous, aggregated, and secure, it is an asset that local stakeholders can share in near-real time for all kinds of other mobility and community applications.

This solution will also make the City’s transportation system adaptable to commuter needs that may change throughout a day, week, or month — subsequently enabling the introduction of multimodal and flexible transportation options. Our continuous data streams enable our users to see how public spaces and streetscapes are actually used, inclusive of all kinds of travellers and accurate across modes. We enable planners and transportation engineers to adjust transit schedules according to traffic flow; designers can model the impact of various design interventions on safety and curb utilization; and rideshare, bikeshare, and electric vehicle companies can manage the distribution of fleets based on the City’s daily (or even minute-by-minute) needs— among many other flexible use cases. In the flexibility of our sensors and data, Numina’s solution will aid the City in its responsiveness to the residents’ changing transportation needs; in the accuracy of our data across modes, Numina will aid the City in increasing the viability of the existing transportation network for non-motorists.

The real-time nature of Numina data also makes it possible for the system to trigger city services where needed, when needed. Numina’s real-time data helps maintenance and public safety departments identify anomalies (e.g. obstructions like trash piles or potholes, or sudden behaviors like crowds running in one direction) and automatically deploy maintenance or emergency services, or automatically provision traffic enforcement services to address idling rideshare vehicles at the curbside or in loading zones and create new revenue for municipalities. 

Since Numina never collects any personally identifiable information, the data is not intended for enforcement against individuals. It is meant to help us shape cities to humans’ real-world behavior and desires — which can help us strengthen and amplify public- and private-sector efforts in economic development, social science, public health, and more. Such a data infrastructure promotes the awareness and coverage of mobility options across the city, empowering mobility providers to create stellar travel experiences and residents to utilize a broader menu of transportation modes beyond single-occupancy vehicles.

Describe who will use your solution (1,000 characters)

Numina is purpose-built to empower urban planners and municipal DoTs with better data to design better places. At scale, planners and designers can use Numina data to A/B test the built environment, to empirically evaluate the safety and effectiveness of public places or alternate street designs. City service departments are able to use Numina’s real-time data feeds to identify anomalies and automatically trigger responses or maintenance crews. Furthermore, with the ability to develop and remotely improve our algorithms per request, the hardware is relatively future-proof and can accommodate all kinds of new detections for use cases we’ve yet to imagine. Numina enables new innovations in the private sector, to promote new forms of public-private partnership. Companies that operate in mobility, real estate, insurance, or any other sector that works in the public right-of-way can deliver safer, more efficient, and novel services in the public right-of-way.

Describe your solution's stage of development

  • Ready to Scale - you have completed and expanded your pilot and are seeing adoption of your solution by your intended user

Tell us about your team or organization (500 characters) Numina began in St. Louis in 2014, founded by Tara Pham & former CTO Martin McGreal. Both founders were struck by vehicles while on their bikes, and teamed up to develop and deploy Numina’s first generation of sensors in St. Louis. Dr. Ilan Goodman, former chief technology leader at Park Assist, succeeded as CTO in October 2017. Numina’s projects have been supported by the John S. and James L. Knight Foundation, Robert Wood Johnson Foundation, Clinton Foundation,

Size of your team or organization

  • 11-50

Funding Request

  • $100,000

Describe how you would pilot your idea (1000 characters)

The allocated project budget can fund the initial deployment of ~25 sensors on street poles along key roadways and transit corridors across the city. One benefit of Numina’s architecture is that each sensor is standalone and simple to deploy — easily and inexpensively scalable as we go! After an initial corridor-focused pilot, Numina proposes an on-going municipal franchise agreement, wherein the City co-invests in the deployment of Numina’s data utility with aligned private partners. Numina and the City will then be able to leverage that infrastructure as part of a broader funding strategy, as an additional means to fill funding gaps, and as part of multiple potential P3s. Once deployed, Numina will collect valuable street-level data and manage the marketplace for this data, informing commercial applications such as autonomous navigation, real estate site selection / property valuation, insurance underwriting, and urban freight logistics.

Describe how you would measure the success of your pilot (1000 characters)

While Numina itself is not a direct intervention, the platform serves as an evaluation tool that can measure the impact of other interventions in the public right-of-way, and as an enabler of new urban applications that depend on real-time multimodal data. Today, little accurate data exists for understanding inter- and multimodality on urban mobility. Planners, designers, and transit engineers need baseline multimodal traffic data in order to equitably plan transit to serve users from a range of destinations and utilizing a range of last-mile modes. Our metrics for success include equitable distribution of transit, data integration across city agencies, public access to multimodal traffic data, as well as API and Dashboard subscriptions and integration into local retail, real estate, insurance, and mobility markets. With a successful pilot, Numina would scale to greater coverage of the of the city and help attract, vet, and support new innovations and service providers to Pittsburgh.


Join the conversation:

Photo of Diana Avart

Hi Tara,

Thanks so much for submitting this idea! I am curious, what changes were identified in St. Louis as a result of the technology? I can see data driven decisionmaking being extremely beneficial as new transportation technology becomes more prominent so I would love to hear more about the updates that resulted from the data collected in some of the original pilots.

- Diana, Facilitator

Photo of Tara Pham

Hi, Diana Avart !

Thanks for your great questions! We have deployed in 5 cities to date. In Jacksonville, FL, they used our data to:
1.  calculate crash _rates_ (crashes per pedestrian crossing — a statistic for which they had never had a denominator before). For Jacksonville, this rate was more valuable than absolute crash numbers because, according to their framework, a place with one crash per 10,000 pedestrian crossings is actually much safer than a place with one crash per 1,000 ped crossings, regardless of how many crashes are happening at each site.
2. then rank intersections by pedestrian danger level, so they could focus limited resources on the most dangerous places first and have the highest impact per dollar spent.
3.  identify an effective intervention to be painting mid-block crossings for pedestrians because most people crossing outside of a crosswalk would still cross at a few common bands across the road.
4. determine where to locate each mid-block crossing, based on the observed desire lines of pedestrians.

We have a light case study on this work published here:

Here is a scientific poster we presented at the International Cycling Safety Conference and at Transport Research Arena:

We work with our city partners to design experiments around traffic safety, to empirically measure the impact of different approaches to urban design and planning. Unlike other traditional traffic measurement practices, Numina shortens the evaluation time of infrastructure to second-by-second and week-by-week, rather than year-by-year or decade-by-decade, so we can A/B test different interventions before permanently implementing the most effective one.

Photo of Diana Avart

Thanks so much for this additional information, it is really helpful!