Vehicle Category Recognition API
Vehicle Category Recognition API - VehicleCRA (also known as vehicles categories detection API) is a cross browsers REST API which get a JSON input with a still photo
(as base64 encoded string) or an url of the image and returns
a JSON string which contains predictions with certain amount of probability (filtered for output with minimum 20%), bounding boxes of
detected vehicle category(ies) with its top, left, width, height values and, if required, for each prediction, a boundingBoxPhoto as base64 encoded string of the detected vehicles categories.
Also it outputs a base64 encoded string photo which is the original input photo with drawned bounding boxes upon it. For one still photo the API may return multiple predictions with different probability scores of detected vehicles categories.
Our pricing packages count the predictions, so for one request, multiple predictions may be counted. We filter the results of predictions so we display only the predictions with a probability score higher than 20%.
Of course, there are some limitations in order to get a higher accuracy. We recommend properly exposed, unobstructed JPEG photos at 1920x1080 (full HD resolution) where
target vehicles may fill an important space in the input photo as you see in the example below. We do not store pictures. Also, the quality and the angles of the camera (30 degrees for side camera) are very important and it contribute to a higher detecting accuracy.
It should have varifocal lenses, high shutter speed, good infrared lighting beam, full HD resolution.
Allthough this Vehicle Category Detection API (currently we do not offer a face vehicle category recognition sdk) is intended for software development and therefore developers, we have also here an
vehicle category detector online application that may be used to check the input and output JSONs of the API.
The necessary steps are written below, basically for this real time vehicle category detection or recognition API you send an authorized POST request
in JSON format to the API endpoint and you get as JSON response the output as described below through parameters and examples.
This Vehicles Categories Recognition API is useful for a large number of domains like: checking private entrances in parkings for restaurants, malls, close spaces, airports, bus stations, railway stations, traffic control for each category of vehicles etc.
You own the commercial copyright of the resulted JSON with no additional fee meaning you may use it in your own apps for sale.
For using our vehicle category recognition API and/or APP you must create an account (free of charge, no card required), activate it from your received email, login and then start your TRIAL package with no fees as you can see at our pricing packages.
After you have tested the API and/or APP and you are satisfied, you may buy a paid package. You will always see at your Admin Console page the real resources
consumption in real time, your invoices, you may see/edit/delete your profile or export log consents as GDPR instructed, you may read our FAQs.
Vehicle Category Recognition APP
Parameter Name
Parameter Description
created
This is the timestamp as [string] at the moment that request is made.
final_photo
This is the final photo base64 encoded string [string] upon which bounding boxes are drawn.
predictions
This is a list or array which contains the parameters explained below.
probability
This is the probability score [real] of the detected vehicle category.
tagId
This is the tagId [string] for the detected vehicle category.
Example: 6b333d95-e461-4155-890c-9921158f7d17.
tagName
This is the tagName [string] for the detected vehicle category.
Function of the tagName, different colors are used for boundingBox outline as legend below. Example of tagName: Big Truck.
Color used for "ATV" category boundingBox outline.
Color used for "Bicycle" category boundingBox outline.
Color used for "Big Truck" category boundingBox outline.
Color used for "Bus" category boundingBox outline.
Color used for "Harvesting Machine" category boundingBox outline.
Color used for "Limousine" category boundingBox outline.
Color used for "Locomotive" category boundingBox outline.
Color used for "Mini Bus" category boundingBox outline.
Color used for "Motor Cycle" category boundingBox outline.
Color used for "Motor Scooter" category boundingBox outline.
Color used for "Pickup Truck" category boundingBox outline.
Color used for "RV" category boundingBox outline.
Color used for "Scooter" category boundingBox outline.
Color used for "Sedan" category boundingBox outline.
Color used for "Sleigh" category boundingBox outline.
Color used for "Snowmobile" category boundingBox outline.
Color used for "Sport Car" category boundingBox outline.
Color used for "SUV" category boundingBox outline.
Color used for "Tractor" category boundingBox outline.
Color used for "Tram" category boundingBox outline.
Color used for "Tricycle" category boundingBox outline.
Color used for "Van" category boundingBox outline.
Color used for "Waggon" category boundingBox outline.
boundingBox
This is an object that contains the below explained parameters.
left
This is the upper left coordinate [real] of the rectangular bounding box surrounding the detected vehicle category.
top
This is the upper top coordinate [real] of the rectangular bounding box surrounding the detected vehicle category.
width
This is the width [real] of the rectangular bounding box surrounding the detected vehicle category.
height
This is the height [real] of the rectangular bounding box surrounding the detected vehicle category.
boundingBoxPhoto
This is the base64 encoded string crop photo [string] based upon bounding box surrounding the detected vehicle category.
VehicleCRA Online Video Presentation
Vehicle Category Recognition API, VehicleCRA is in the video presentation below.
There are several search terms which you may use like: vehicle category recognition api, vehicles categories detection api, vehicle type recognition api
Please choose one of the below pricing packages for start using our Vehicle Category Recognition API and online APP!
Yearly TIER
(15% Discount)
Note: VAT rate may be added or not, function to your country and/or if you are a taxable person or company.
* Prediction - on the input photo may exist many predictions, each of it with certain amount of probability of detected vehicle category.
Even we filter the output predictions to those with probability score greater than 20%, for the input photo all predictions are counted.