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

Photo File
Image URL(*)
* Let the "NO" value of Image URL if you upload a Photo File, otherwise write the image url like http://domainname.com/image.jpg



API Endpoint (method POST):
https://gatiosoft.ro/vehiclecra.aspx
Headers:
Authorization: Basic //Your username:password are base64 encoded string
Content-Type: application/json
Accept: application/json
JSON Request Body (change inputs here and see in real time below):
                   {
  "base64_Photo_String": "iVBORw0KGgoAAAA...base64 encoded string photo...GAAAAAElFTkSuQmCC",
  "photo_url": "NO",
  "boundingBoxCrop": "YES"
}
               
JSON Response From API (change inputs here and see in real time below):
{
  "created": "2020-05-02T12:28:09.989Z",
  "predictions": [
    {
      "probability": 0.5453594,
      "tagId": "6b333d95-e461-4155-890c-9921158f7d17",
      "tagName": "Big Truck",
      "boundingBox": {
        "left": 0.590857267,
        "top": 0.049960345,
        "width": 0.153553188,
        "height": 0.287757039
      },
      "boundingBoxPhoto": "iGgoAAAA..vehicle crop base64 encoded string photo...GTkSuQmCC"
    },
    {
      "probability": 0.6109611,
      "tagId": "6b333d95-e461-4155-890c-9921158f7d17",
      "tagName": "ATV",
      "boundingBox": {
        "left": 0.241624564,
        "top": 0.2652982,
        "width": 0.137271315,
        "height": 0.2830975
      },
      "boundingBoxPhoto": "iNgfdEERA..vehicle crop base64 encoded string photo...RmbTrdeCC"
    }
  ],
  "final_photo": "iRRfdewqRA..final base64 encoded string photo with drawn bounding boxes...SwervasCC"
}
JSON Response (Example) From API in case of ERROR:

 [
  {
    "cd": "1001",
    "description": "The authorization header Is either empty Or isn't Basic"
  }
]

Request Parameters Table

Parameter Name
Parameter Description
base64_Photo_String
This is the input photo as base64 encoded string[string] which will be scaned for vehicles categories. If you set this parameter, the below photo_url parameter value must be set to NO
photo_url
This is the image url [string] used for detecting vehicle categories. Its default value is NO because the above parameter base64_Photo_String is set. If this parameter is set to an image url, base64_Photo_String value must be NO.
boundingBoxCrop
This parameter [string] is used with YES or NO values. If YES then a photo crop of the vehicle bounding box will be output as base64 encoded string.

Response Parameter Table

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.
ATV category boundingBox outline color
Color used for "ATV" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Bicycle" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Big Truck" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Bus" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Harvesting Machine" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Limousine" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Locomotive" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Mini Bus" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Motor Cycle" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Motor Scooter" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Pickup Truck" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "RV" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Scooter" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Sedan" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Sleigh" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Snowmobile" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Sport Car" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "SUV" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Tractor" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Tram" category boundingBox outline.
ATV category boundingBox outline color
Color used for "Tricycle" category boundingBox outline.
Bicycle category boundingBox outline color
Color used for "Van" category boundingBox outline.
ATV category boundingBox outline color
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.

Response Error Codes Table

Parameter Name
Parameter Description
cd

This is the error code which may be:

  • 1001
  • 1002
  • 1003
  • 1004
  • 1005
  • 1006
  • 1007
  • 1008
  • 1009
  • 1010
  • 1011
  • 1012
  • 1013
  • 1014
  • 1015
  • 1016
  • 2001
description

This is the description of the error code which may be:

  • 1001 - The authorization header is either empty or isn't Basic.
  • 1002 - Daily requests number exceeded in TRIAL mode!
  • 1003 - Trial expired!
  • 1004 - Predictions number exceeded!
  • 1005 - Package expired!
  • 1006 - No invoice!
  • 1007 - Reader is NULL for TRIAL!
  • 1008 - Cannot Read if TRIAL exists!
  • 1009 - Error connecting to database looking for TRIAL! (and a detailed description message of the encountered error)
  • 1010 - Reader is NULL for Invoice!
  • 1011 - Cannot Read if Invoice exists!
  • 1012 - Error connecting to database! (and a detailed description message of the encountered error)
  • 1013 - Input request too long! Maximum 5 MB per request are allowed / Nothing to upload
  • 1014 - Invalid request data! (and a detailed description message of the encountered error)
  • 2001 - Invalid request data after passing to the API (and a detailed description message of the encountered error)

Source Code Examples for Using Our Vehicle Category Recognition API

                       
Imports System
Imports System.Text
imports System.Collections.Generic
Imports System.Net
Imports Newtonsoft.Json

Public Class vehicle_category_recognition_api
    Public Class ResponseFields
	 Public Property created As String
         Public Property predictions As New List(Of prediction)
         Public Property final_photo As String
    End Class

    Public Class prediction
	 Public Property probability As Single
         Public Property tagId As String
         Public Property tagName As String
         Public Property boundingBox As New boundingbox
         Public Property boundingBoxPhoto As String
    End Class

    Public Class boundingbox
	 Public Property left As Single
         Public Property top As Single
         Public Property width As Single
         Public Property height As Single
    End Class
    
    Public Class ErrorFields
        Public Property cd As String
        Public Property description As String
    End Class

    Protected Sub SendRequest()
        Dim Client As WebClient = New WebClient()
        Dim credentials As String = Convert.ToBase64String(Encoding.ASCII.GetBytes("your_username:your_password"))
        Client.Headers(HttpRequestHeader.Authorization) = String.Format("Basic {0}", credentials)
        Client.Headers(HttpRequestHeader.Accept) = "application/json"
        Client.Headers(HttpRequestHeader.ContentType) = "application/json"
	Client.BaseAddress = "https://gatiosoft.ro/vehiclecra.aspx"
        Dim resString As String = ""

        Try
            Dim js As String = "Replace this string with your JSON Request Body string like in the example above on the website"
            Dim reqString As Byte() = Encoding.UTF8.GetBytes(js)
            Dim url As Uri = New Uri(Client.BaseAddress)
            Dim resByte As Byte() = Client.UploadData(url, "post", reqString)
            resString = Encoding.UTF8.GetString(resByte)

	    If resString.IndexOf("predictions") > 0 Then
                Dim r As ResponseFields = New ResponseFields()
                r = JsonConvert.DeserializeObject(Of ResponseFields)(resString)
                Console.Write(resString)
            Else
		Dim e As list(of ErrorFields) = New list(of ErrorFields)
		e = JsonConvert.DeserializeObject(Of list(of ErrorFields))(resString)
                Console.Write(e(0).cd)
                Console.Write(e(0).description)
            End If

            Client.Dispose()
        Catch exception As Exception
            Dim ex As System.Exception = exception
            Console.Write("ERROR: " & resString & ex.Message)
        End Try
    End Sub

    Public Shared Sub Main()
	Dim b As vehicle_category_recognition_api = New  vehicle_category_recognition_api
        b.SendRequest()
    End Sub
End Class



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

 



Pricing Packages

Please choose one of the below pricing packages for start using our Vehicle Category Recognition API and online APP!

Start TRIAL
No catches

  • 7 days TRIAL.
  • Use our cloud REST API and online APP.
  • Maximum 50 requests per DAY in trial period.
  • You do NOT own the commercial copyright for using the API in your apps in trial period.
  • Get bounding boxes for each vehicle category detected with different color according to legend.
  • Get the probability score of each detected vehicle category in the input photo.
  • Get timestamp at the moment of the request
  • Administration console
  • Support through online chat and/or tickets
  • We do NOT allow spam accounts for TRIAL



Monthly TIER
Popular

  • 80 USD per month
  • Use our cloud REST API and online APP
  • Maximum 10000 predictions(*) per month
  • Maximum 50 requests per MINUTE
  • You own the commercial copyright to use it in your apps.
  • Get bounding boxes for each vehicle category detected with different color according to legend.
  • Get the probability score of each detected vehicle category in the input photo.
  • Get timestamp at the moment of the request
  • Administration console
  • Premium support through online chat and/or tickets, very supportive help and quick responses.



Yearly TIER
(15% Discount)

  • 816 USD per year
  • Use our cloud REST API and online APP
  • Maximum 10000 predictions(*) per month
  • Maximum 50 requests per MINUTE
  • You own the commercial copyright to use it in your apps.
  • Get bounding boxes for each vehicle category detected with different color according to legend.
  • Get the probability score of each detected vehicle category in the input photo.
  • Get timestamp at the moment of the request
  • Administration console
  • Premium support through online chat and/or tickets, very supportive help and quick responses.



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.