Roadside Vehicle People Counter

In this project, we have developed a sensor-based system that can count and classify people in passing cars and vehicles. The solution has been installed and developed in 3 different pilots. 1) for counting in passenger cars in one lane. 2) For counting cars and trucks in 1 lane and 3) for counting all vehicles in 2 lanes. The solution has been piloted for boarding cars on car ferries. Tolls, carpooling and parking are secondary markets. The solution improves safety on car ferries. Currently, vehicle passengers are counted manually when cars board. This gives inaccurate results.

Prosjektet har utviklet og pilotert en fungerende løsning og Counting Hero jobber nå med å bringe løsningen fra pilot til kommersiell drift. Videreutvikling pågår. Med bakgrunn i prosjektet og prosjektresultatene har vi etablert en ny bedrift med et ledende fagmiljø som jobber med ulike løsninger for maskinsyn og lydgjennkjenning innen samferdsel. Selskapet har etablert inntektsstrømmer men er fortsatt pre-revenue i forhold til salg og lisensiering av teknologien utviklet i prosjektet. For ferjeoperatørerene har vi nå startet salgsprosessene for kommersielt salg av teknologi som kan bedre sikkerheten på norske ferger. Vi ser også at de første oppdragsgiverne stiller krav til bruk av slik teknologi. Vi forventer også å realisere et internasjonalt potensial innen telling av personer i kjøretøy og ser et spesielt potensiale innen kontroll for å gi goder til billister som velger å samkjøre.

In this project we are developing a camera-based sensor system capable of counting and classifying people in passing vehicles. Project is targeted for vehicle ferries applications, with tolling, carpooling, parking and security as secondary opportunity markets. A successfully developed solution will improve the safety precautions on Norwegian vehicle ferries. Currently the passengers in vehicles are manually counted when cars are driving onboard. This returns inaccurate results. The proposed project is based on performed field tests of existing technology and solutions where we have experienced that remote video counting through car windows in changing light conditions is a difficult task which needs further research and development. Different vehicles types, changing light, changing weather, tinted windows and coloured glass makes it difficult to see how many people are inside each vehicle. In this project we will address this imaging challenge and also develop computer vision algorithms to detect people from several different camera viewpoints, using innovative camera solutions and data processing based on deep learning machine vision technology.