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

CloudParc Smart City Platform: the "missing link" between parking, transportation and infrastructure

CloudParc's disruptive platform uses advanced machine vision and artificial intelligence to automate the entire parking lifecycle.

Photo of Dana Klein
6 3

Written by

Currently, most municipalities only collect 20-30% of their potential revenue from parking which comes from metering and violations.  30% of all congestion is caused by people looking for parking spaces.  In most cases, it's not clear how much the municipality actually spends on parking and in some cases, it's equal to what they take in and dismissals are high due to human error.  Parking infrastructure and manpower is very expensive and has never been fully automated before.  Parking effects almost everything in a city and is a huge revenue generator.   Finally, there is no other hub for parking, transportation, and infrastructure which we will need for future applications and smart mobility.  CloudParc is a smart city platform with parking as its first use case.  

We help find people parking and capture 2-4x's more violations and automate metering so it's precise and transparent.  Our machine learning (artificial intelligence) with computer vision (cameras) increase revenues, lowers expenses, and is sustainable.  We can provide autonomous vehicles extra eyes and municipalities with smart infrastructure for those vehicles.  We can provide curbside management and control, security use cases, infrastructure maintenance, etc.  and all with the same equipment in the same place.  Finally, the system gets smarter the longer it's in play and learns the environment for customized programs.  

Features include:

 - Real time data capture-  All in one solution-  DSRC and drone technology - Provides personalized services to mesh with clients infrastructure and needs  - Tracks traffic flow -  Virtual permitting - Extended vision and other use cases for autonomous cars and ride shares for sustainability - Dynamic/variable/incentive pricing based on stakeholder needs, demand, progressive violation, dimension, emissions, and more - Offers features applicable to or as smart city hubs -  Use cases for autonomous vehicles, electric cars, and ride shares-  Valuable use cases for rural transportation - Other data use cases for developers, planners, data analytics, transportation consultants - Offers data gathering, security, land use planning information, infrastructure maintenance, transportation, communications, resiliency, and logistics opportunities   -Becomes more relevant as the municipalities and automobiles become smarter

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

Municipalities, Airports, Ports, Campuses, Facilities,Parking Lots, Security, Infrastructure Maintenance, Transportation and Transit, and Data subscribers. Open to joint ventures, subcontracting, any win-win scenario.

Describe your solution's stage of development

  • Prototype - you have built a prototype and tested it with potential users

Tell us about your team or organization (500 characters)

Leadership team: Steven Neyaroff, co-creator of Ethereum, the bitcoin platform, Jeff Pulver Founder of Vonage also known as Father of "VoIP" as he wrote the protocol and invented it, and Kam Ghaffarian builds space stations for the Federal Government. We have 23 patents, 42 international and 10 approved. We are software using cameras to capture real time data, digest, distribute and even act on it for multiple purposes and multiple users with the same equipment in the same location.

Size of your team or organization

  • 11-50

Funding Request

  • $75,000

Describe how you would pilot your idea (1000 characters)

Our pilot would demonstrate automatic occupancy detection, automatic metering, automatic dynamic and variable pricing, and automatic capture and enforcement of violations. Our technology is sustainable. The longer it's in play, the smarter it becomes,adapting to the environment. We are also outfitted for autonomous vehicles and can be used by multiple users for multiple purposes. We have drone and DSRC technology. Anyone else who wants to get in the space must first find a way around our 23 patents and put in the time for machine training- a process you can't "leap frog". We have three different business models, a public private partnership on the gain share on the lowered expenses and increased revenues, fee for service, and hybrid. We intend to sell licenses and data subscriptions. We can work with contractors as a sub contractor, resllers, licensees, etc. and are open to many conversations. With our extensive patent portfolio, we can work with an unlimited amount of stakeholders.

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

To prove that we can increase capture 2-4x's and lower expenses and dismissals in parking by at least half. To prove to the public in that area that the technology works To prove the viability of other use cases outside of parking To gain interest in the local area to install To roll out into an area and eventually layer on other use cases

6 comments

Join the conversation:

Comment
Photo of KatieWalsh 100
Team

Hi again Dana - I watched your video - for which extra thanks - it's very informative and extremely impressive. So I hope you don't mind me asking this - but it also seems a little big-brotherish. Have you found for drivers that the upside of finding parking more easily outweighs the potential downside of the feeling of being tracked and scrutinised? I imagine this system would be interesting to police and private detectives too! (Not that I have anything to hide of course....)

Photo of Dana Klein
Team

Thanks Katie for your comments. Machine Learning is very specific and actually protects privacy. The software is like a robot. It picks up what it's told to pick up. It actually transmit information about open spots to the driver and doesn't pick up information about the driver unless the driver parks. Drivers are already downloading payment apps. License plates are meant to be read and are currently being read now. Even so, we encrypt them all the way through the process. There is nothing that is picked up that is private. It's like watching a football player run on the field. You zoom into the player and the audience is blurred. That's machine learning with computer vision. It only does what it's told to do. In this case, it transmits availability, automatically meters, automatically adjusts pricing based on variables, and automatically captures and enforces violations, all based on anonymous data. Other uses cases capture anonymous data as well.

Photo of KatieWalsh 100
Team

Thanks Dana - that's really fascinating. Does it record what it sees too? Could it help police with their enquiries? Or more importantly perhaps - if someone had an objection to a parking fine or something can you / someone go back and take a look? Does it know to allow a little old lady or man a bit of extra leeway in a two minute drop off scenario?

Photo of Dana Klein
Team

It can record what it's trained to record. It can work for security, infrastructure maintenance, all kinds of data collection, etc. There are photo images so dismissals would be extremely difficult. We lower costs and dismissals so they actually become new revenue streams. The business rules are set by the client and we believe in making win-wins with all stakeholders. We can provide warnings if the client wishes and we can also do dynamic and variable pricing based on anything such as senior citizen pricing, low income pricing, VIPs, military, demand, low emission cars, size of vehicles, 2 wheelers, etc.

View all comments