--- title: "Regional Vehicle Classification Schemes: Why One Model Does Not Travel" description: Singapore, the Philippines and Latin America each classify vehicles differently. Compare the schemes and see where a generic 8-class model breaks. image: https://blog.goodvisionlive.com/hubfs/blog-header-1.png --- ###### Stay in touch ### Subscribe to Newsletter Get latest updates and news about GoodVision directly to your inbox. [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) - [Free demo](https://goodvision.typeform.com/freetrial25?utm_source=gv-blog&utm_medium=menu) - [Case studies](https://casestudies.goodvisionlive.com) - [Blog](https://blog.goodvisionlive.com) - [Return to homepage](https://goodvisionlive.com/) [Contact us](https://goodvisionlive.com/contacts/) [![GoodVision - Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/TITLE-R-black.png?width=175&height=30&name=TITLE-R-black.png "GoodVision - Smart cities matter.")](https://goodvisionlive.com/) - [Case studies](https://casestudies.goodvisionlive.com) - [Blog](https://blog.goodvisionlive.com) - [Return to homepage](https://goodvisionlive.com/) - [Contact us](https://goodvisionlive.com/contacts) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/h-logo-white.png?width=1227&height=209&name=h-logo-white.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) - [Solutions](https://goodvisionlive.com/solutions/) [Real-time Traffic Monitoring](https://goodvisionlive.com/solutions/real-time-traffic-monitoring/) [![refresh\_icon-1](https://blog.goodvisionlive.com/hubfs/refresh_icon-1.svg) ![refresh\_icon\_green](https://blog.goodvisionlive.com/hubfs/refresh_icon_green.svg) AID](https://goodvisionlive.com/solutions/aid/) [![money\_icon](https://blog.goodvisionlive.com/hubfs/money_icon.svg) ![money\_icon\_green](https://blog.goodvisionlive.com/hubfs/money_icon_green.svg) Tolling](https://goodvisionlive.com/solutions/tolling/) [![road\_icon](https://blog.goodvisionlive.com/hubfs/road_icon.svg) ![road\_icon\_green](https://blog.goodvisionlive.com/hubfs/road_icon_green.svg) Traffic Flow Monitor](https://goodvisionlive.com/solutions/traffic-flow-monitor/) [![warning\_icon](https://blog.goodvisionlive.com/hubfs/warning_icon.svg) ![warning\_icon\_green](https://blog.goodvisionlive.com/hubfs/warning_icon_green.svg) Traffic Violation Detection](https://goodvisionlive.com/solutions/traffic-violation-detection/) [![car\_icon\_white](https://blog.goodvisionlive.com/hubfs/car_icon_white.svg) ![car\_icon\_green-1](https://blog.goodvisionlive.com/hubfs/car_icon_green-1.svg) Parking Monitor](https://goodvisionlive.com/solutions/parking-occupancy/) [![lights\_icon](https://blog.goodvisionlive.com/hubfs/lights_icon.svg) ![lights\_icon\_green](https://blog.goodvisionlive.com/hubfs/lights_icon_green.svg) Traffic Controller](https://goodvisionlive.com/solutions/traffic-controller/) [Traffic Data Collection From Camera and Drones](https://goodvisionlive.com/solutions/traffic-data-collection/) [Traffic Data Analytics For Traffic Modelling](https://goodvisionlive.com/solutions/traffic-modelling/) [![alt](https://blog.goodvisionlive.com/hs-fs/hubfs/adad4.webp?width=300&height=96&name=adad4.webp) Go to our APP](https://my.goodvisionlive.com/en/login) - [Products](https://goodvisionlive.com/products/) - [Video Insights Platform](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) - Partners - [Global Sales Partners](https://goodvisionlive.com/partners/) - [Technology Partners](https://goodvisionlive.com/technology-partners/) - [Academy Program](https://goodvisionlive.com/goodvision-academy/) - Resources - [Case Studies](https://casestudies.goodvisionlive.com/) - [Help Portal](https://goodvisionlive.com/support/) - [Webinars](https://goodvisionlive.com/webinars/) - [Blog](https://blog.goodvisionlive.com/) - [Company](https://goodvisionlive.com/about-goodvision/) - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) - [Contact us](https://goodvisionlive.com/contacts/) [Contact us](https://goodvisionlive.com/contacts/) [![GoodVision - Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/TITLE-R-black.png?width=175&height=30&name=TITLE-R-black.png "GoodVision - Smart cities matter.")](https://goodvisionlive.com/) - [Solutions](https://goodvisionlive.com/solutions/) [Real-time Traffic Monitoring](https://goodvisionlive.com/solutions/real-time-traffic-monitoring/) [![refresh\_icon-1](https://blog.goodvisionlive.com/hubfs/refresh_icon-1.svg) ![refresh\_icon\_green](https://blog.goodvisionlive.com/hubfs/refresh_icon_green.svg) AID](https://goodvisionlive.com/solutions/aid/) [![money\_icon](https://blog.goodvisionlive.com/hubfs/money_icon.svg) ![money\_icon\_green](https://blog.goodvisionlive.com/hubfs/money_icon_green.svg) Tolling](https://goodvisionlive.com/solutions/tolling/) [![road\_icon](https://blog.goodvisionlive.com/hubfs/road_icon.svg) ![road\_icon\_green](https://blog.goodvisionlive.com/hubfs/road_icon_green.svg) Traffic Flow Monitor](https://goodvisionlive.com/solutions/traffic-flow-monitor/) [![warning\_icon](https://blog.goodvisionlive.com/hubfs/warning_icon.svg) ![warning\_icon\_green](https://blog.goodvisionlive.com/hubfs/warning_icon_green.svg) Traffic Violation Detection](https://goodvisionlive.com/solutions/traffic-violation-detection/) [![car\_icon\_white](https://blog.goodvisionlive.com/hubfs/car_icon_white.svg) ![car\_icon\_green-1](https://blog.goodvisionlive.com/hubfs/car_icon_green-1.svg) Parking Monitor](https://goodvisionlive.com/solutions/parking-occupancy/) [![lights\_icon](https://blog.goodvisionlive.com/hubfs/lights_icon.svg) ![lights\_icon\_green](https://blog.goodvisionlive.com/hubfs/lights_icon_green.svg) Traffic Controller](https://goodvisionlive.com/solutions/traffic-controller/) [Traffic Data Collection From Camera and Drones](https://goodvisionlive.com/solutions/traffic-data-collection/) [Traffic Data Analytics For Traffic Modelling](https://goodvisionlive.com/solutions/traffic-modelling/) [![alt](https://blog.goodvisionlive.com/hs-fs/hubfs/adad4.webp?width=300&height=96&name=adad4.webp) Go to our APP](https://my.goodvisionlive.com/en/login) - [Products](https://goodvisionlive.com/products/) - [Video Insights Platform](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) - Partners - [Global Sales Partners](https://goodvisionlive.com/partners/) - [Technology Partners](https://goodvisionlive.com/technology-partners/) - [Academy Program](https://goodvisionlive.com/goodvision-academy/) - Resources - [Case Studies](https://casestudies.goodvisionlive.com/) - [Help Portal](https://goodvisionlive.com/support/) - [Webinars](https://goodvisionlive.com/webinars/) - [Blog](https://blog.goodvisionlive.com/) - [Company](https://goodvisionlive.com/about-goodvision/) - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) - [Contact us](https://goodvisionlive.com/contacts/) ![Regional Vehicle Classification Schemes: Why One Model Does Not Travel](https://blog.goodvisionlive.com/hubfs/blog-header-1.png) ![Regional Vehicle Classification Schemes: Why One Model Does Not Travel](https://blog.goodvisionlive.com/hubfs/blog-header-1.png) # Regional Vehicle Classification Schemes: Why One Model Does Not Travel Oct 6, 2026, 7:28:39 PM Regional Vehicle Classification Schemes: Why One Model Does Not Travel A traffic count that is highly accurate against the wrong classification scheme is still the wrong data. That is the problem hiding inside a lot of AI traffic counting tools sold as global products. A vehicle classification model trained on European traffic mixes will cheerfully count a jeepney in Manila as a van, a trishaw as a motorcycle, or a Chilean micro as a bus. The count total might look fine. The breakdown that a client, a regulator, or a transport model actually needs will not. For traffic engineering leads running surveys in Singapore, the Philippines, Chile, or anywhere outside the markets a vendor originally built for, this is not a minor labeling issue. Classification categories feed directly into capacity analysis, pavement design inputs and signal timing models. Get the categories wrong and every downstream calculation inherits the error. ## Why One Classification Scheme Does Not Fit All Regions Vehicle classification schemes exist because different road authorities group vehicles differently, for reasons tied to their own regulation, taxation, and infrastructure planning. A scheme built for European roads typically separates cars, vans, trucks, heavy trucks, and buses, which works because that is how European fleets and freight regulation are structured. Singapore's Land Transport Authority works with a finer breakdown. Goods vehicles split into light, heavy, and very heavy tiers, with the [LTA's goods vehicle categories](https://onemotoring.lta.gov.sg/content/onemotoring/home/buying/vehicle-types-and-registrations/commercial-vehicle/goods-vehicle-and-engineering-plant.html) drawing the lines at 3,500 kg and 16,000 kg. Taxis get their own category, separate from private cars. Buses split into public route buses and private, charter and school buses. A camera does not weigh anything, so a visual model has to learn what those weight tiers look like on the road. ![GoodVision detecting vehicles in highway footage, next to Singapore's LTA goods vehicle tiers: light up to 3,500 kg, heavy from 3,500 to 16,000 kg, and very heavy over 16,000 kg.](https://blog.goodvisionlive.com/hs-fs/hubfs/inline-03-singapore-tiers.png?width=1600&height=900&name=inline-03-singapore-tiers.png) None of that distinction exists in a standard European or North American scheme, and none of it is optional if your deliverable needs to match local planning standards. The Philippines and Latin America present their own vehicle mixes again: jeepneys, tricycles, and informal transit modes that a generic 8-class model was never trained to recognize, let alone label correctly. A classification engine built around US or UK vehicle types has no category for them and will force them into whatever class looks closest, usually wrong. ## Why Generic AI Counting Tools Fail Outside Their Home Market Most AI video analytics vendors build one global detection model and sell it everywhere. That approach works reasonably well in the regions the model was trained on and degrades quickly outside them, particularly on the vehicle types that do not exist in the training data at all. This shows up in two ways. First, accuracy drops on vehicle types the model rarely or never saw in training, and local transit modes are the obvious case. Second, even where detection accuracy holds up, the category labels themselves do not match what a local transport authority or client actually requires, which means a traffic engineer ends up manually remapping categories after the fact, defeating the point of automation. ![How a generic model mislabels regional vehicles: a jeepney counted as a van, a tricycle as a motorcycle, a taxi colectivo as a car, and a very heavy goods vehicle as a truck.](https://blog.goodvisionlive.com/hs-fs/hubfs/inline-02-generic-vs-regional.png?width=1600&height=900&name=inline-02-generic-vs-regional.png) For a consultancy delivering a Traffic Impact Assessment to a Philippine LGU or a saturation flow study to a Chilean municipality, a mismatched scheme means extra QA time, extra client questions, and a deliverable that looks less defensible than the manual count it was meant to replace. If you are weighing AI counting against a traditional survey, see our guide on [traffic engineering methods](https://blog.goodvisionlive.com/traffic-engineering-methods) for how classification accuracy factors into that comparison. It is worth being direct about the limits here too. Axle-based schemes like FHWA's 13-class system classify vehicles by axle count and trailer configuration, information a camera cannot see. Visual classification can approximate these categories closely, but a validated axle-class crosswalk is a different kind of engineering problem. Be wary of any vendor, including us, that implies a camera-based system reproduces an axle-based scheme out of the box. ## Regional Vehicle Classification Schemes Compared The table below lines up the classification engines GoodVision runs today. The class counts are per engine. The contested boundaries are the ones a generic model is most likely to get wrong. ![Five GoodVision classification engines compared: Global with 8 classes, EU with 9, Singapore with 10, Philippines with 9 and Latin America with 16. Each engine adds its own regional vehicle types.](https://blog.goodvisionlive.com/hs-fs/hubfs/inline-01-engines-1.png?width=759&height=427&name=inline-01-engines-1.png) | Engine | Classes | What it adds beyond a generic set | The contested boundary | Where a generic model breaks | | --- | --- | --- | --- | --- | | Global | 8 | Pedestrian, bicycle rider, motorcycle, car, van, truck, heavy truck, bus | Van vs truck | It is the generic set | | EU | 9 | Light truck as its own class | Van vs light truck vs truck | Light trucks rounded into vans or trucks | | Singapore | 10 | Taxi, light, heavy and very heavy goods vehicles, public and private bus | Heavy vs very heavy goods vehicle, public vs private bus | Three goods tiers collapsed into one or two, every bus counted as one class | | Philippines | 9 | Jeepney, tricycle | Jeepney vs bus or van, tricycle vs motorcycle | Jeepneys and tricycles forced into the nearest generic class | | Latin America | 16 | Taxi básico, taxi colectivo, urban taxi bus, urban bus, articulated urban bus, intercity bus, rural minibus, school transport van | Urban vs intercity vs articulated bus, taxi colectivo vs car | Eight transit modes reported as "bus" or "car" |   The Global engine is available to every user. The EU, Singapore, Philippines and Latin America engines are enabled on request for projects that need them. ## How GoodVision Builds Regional Classification Models GoodVision runs purpose-built classification engines trained on region-specific vehicle mixes, rather than forcing every market through one global model. The Global engine covers 8 classes and handles most European and North American surveys well. Alongside it sit a 10-class Singapore engine built around LTA categories, a Philippines engine that recognizes jeepneys and tricycles, and a 16-class Latin America engine built around Chilean transit modes. Mott MacDonald saw this on a transit-oriented development in Manila. GoodVision's pre-trained models already included vehicle classes for Filipino transport modes, so jeepneys and tricycles were classified without any extra machine learning setup. Full details are in the [Mott MacDonald Manila case study](https://casestudies.goodvisionlive.com/mott-macdonald-accelerates-manilatransit-development-with-goodvision-platform). Where a project needs a classification scheme outside these existing engines, GoodVision also supports custom configuration for specific survey requirements rather than forcing a mismatched global category onto local data. The result for an engineer in Singapore, Manila, or Santiago is the same as for one in London: data that lands in your report already matching the categories your client or regulator expects, without a manual remapping step eating into the time savings the AI was supposed to deliver. [![GoodVision regional classification engines by survey city: London on the Global engine with 8 classes, Singapore with 10, Manila on the Philippines engine with 9, Santiago on the Latin America engine with 16, plus custom configuration for other projects. Mott MacDonald classified jeepneys and tricycles in Manila with no extra setup. Book a demo at goodvisionlive.com/request-demo/.](https://blog.goodvisionlive.com/hs-fs/hubfs/inline-04-regional-engines-cta.png?width=1600&height=900&name=inline-04-regional-engines-cta.png)](https://goodvisionlive.com/request-demo/) Book a demo at [goodvisionlive.com/request-demo/](https://goodvisionlive.com/request-demo/) and run your next regional survey against the classification scheme your project actually needs.   [Back to Blog](https://blog.goodvisionlive.com) ## Related Articles ## [How to Get FHWA 13-Class Vehicle Classification When the Camera Can't See Every Axle](https://blog.goodvisionlive.com/fhwa-13-class-vehicle-classification) Every FHWA 13-class count runs into the same problem eventually. A truck passes at a head-on angle,... [Read More](https://blog.goodvisionlive.com/fhwa-13-class-vehicle-classification) ## [GoodVision Vehicle Classification Guide](https://blog.goodvisionlive.com/goodvision-vehicle-classification-guide) GoodVision’s Video Insights platform can classify traffic objects (meaning vehicles and... [Read More](https://blog.goodvisionlive.com/goodvision-vehicle-classification-guide) ## [What's New in the GoodVision Platform: A Redesigned Interface](https://blog.goodvisionlive.com/whats-new-goodvision-platform-redesigned-interface) The GoodVision platform has a redesigned interface. A more compact navigation menu and a rebuilt... [Read More](https://blog.goodvisionlive.com/whats-new-goodvision-platform-redesigned-interface) ##### Subscribe to our Newsletter Get latest updates and news about GoodVision directly to your inbox Subscribe [![GoodVision – Smart cities matter.](https://blog.goodvisionlive.com/hs-fs/hubfs/raw_assets/public/GoodVisionLive_August2021/images/LOGO-WITH-TITLE_R.png?width=284&height=48&name=LOGO-WITH-TITLE_R.png "GoodVision – Smart cities matter.")](https://goodvisionlive.com/) ###### Products - [GoodVision Video Insights](https://goodvisionlive.com/goodvision-video-insights/) - [GoodVision Live Traffic](https://goodvisionlive.com/goodvision-live-traffic/) ###### Company - [About GoodVision](https://goodvisionlive.com/about-goodvision/) - [Our Vision](https://goodvisionlive.com/our-vision/) - [Careers](https://goodvisionlive.com/careers/) - [Press kit](https://goodvisionlive.com/press-kit/) ###### Resources - [Blog](https://blog.goodvisionlive.com/) - [Case Studies](https://casestudies.goodvisionlive.com/) - [Webinars](https://goodvisionlive.com/webinars/) Copyright © 2026 GoodVision Ltd. All rights reserved [Privacy Policy](https://goodvisionlive.com/privacy-policy) [Terms of Service](https://goodvisionlive.com/terms-of-service) - - - - ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Tomas Bui", "url" : "https://blog.goodvisionlive.com/author/tomas-bui" }, "dateModified" : "2026-10-06T17:29:20.744Z", "datePublished" : "2026-10-06T17:28:39.000Z", "headline" : "Regional Vehicle Classification Schemes: Why One Model Does Not Travel", "image" : [ "https://blog.goodvisionlive.com/hubfs/blog-header-1.png" ], "mainEntityOfPage" : { "@id" : "https://blog.goodvisionlive.com/regional-vehicle-classification-schemes", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://blog.goodvisionlive.com/hubfs/aas-1.png" }, "name" : "GoodVision Ltd" } } ``` ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Organization", "name" : "GoodVision", "url" : "https://www.goodvisionlive.com" }, "dateModified" : "2026-10-06T00:00:00Z", "datePublished" : "2026-10-06T00:00:00Z", "description" : "GoodVision runs region-specific vehicle classification models (Singapore, Philippines, LATAM) instead of one global scheme. See why that matters for APAC surveys.", "headline" : "Regional Vehicle Classification Schemes: Why One Model Does Not Travel", "image" : "https://20473359.fs1.hubspotusercontent-na1.net/hubfs/20473359/GoodVision_logo_full_GREEN.png", "mainEntityOfPage" : { "@id" : "https://www.goodvisionlive.com/blog/regional-vehicle-classification-schemes:-why-one-model-does-", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://20473359.fs1.hubspotusercontent-na1.net/hubfs/20473359/GoodVision_logo_full_GREEN.png" }, "name" : "GoodVision", "url" : "https://www.goodvisionlive.com" }, "url" : "https://www.goodvisionlive.com/blog/regional-vehicle-classification-schemes:-why-one-model-does-" } ```