Skip To Content

Introduction to the model

Common object detected in a street scene

This is an open-source object detection model by TensorFlow in TensorFlow Lite format.

This model was trained using the Common Objects in Context (COCO) dataset. COCO is a large-scale object detection dataset that is available for use under the Creative Commons Attribution 4.0 License. The dataset contains 80 object categories and 1.5 million object instances that include people, animals, food items, vehicles, and household items.

The model can be used in ArcGIS Survey123 to detect common objects in captured photos.

Note:
While it is not recommended to use this model in production surveys, it can be useful for demonstration purposes and to get started with smart assistants in Survey123. You are responsible for the use of this model. When using Survey123, it is your responsibility to review and manually correct its outputs.

License requirements

To complete this workflow, a Survey123 license is required. This model works with Survey123 Connect and the field app.

Model details

This model has the following characteristics:

  • Input—A camera feed (either low-resolution preview or high-resolution capture) is used as input.
  • Output—An image with common object detections written to its EXIF metadata or an image with redacted objects is output.
  • Compute—This workflow is computationally intensive and performance may be impacted on some mobile devices.
  • Architecture—An open source object detection model by TensorFlow in TensorFlow Lite format with MobileNet architecture.

Classes

You can limit the classes of objects that can be detected by specifying them using the class parameter. The class names are listed in the following table.

person

elephant

wine_glass

dining_table

bicycle

bear

cup

toilet

car

zebra

fork

tv

motorcycle

giraffe

knife

laptop

airplane

backpack

spoon

mouse

bus

umbrella

bowl

remote

train

handbag

banana

keyboard

truck

tie

apple

cell_phone

boat

suitcase

sandwich

microwave

traffic_light

frisbee

orange

oven

fire_hydrant

skis

broccoli

toaster

stop_sign

snowboard

carrot

sink

parking_meter

sports_ball

hot_dog

refrigerator

bench

kite

pizza

book

bird

baseball_bat

donut

clock

cat

baseball_glove

cake

vase

dog

skateboard

chair

scissors

horse

surfboard

couch

teddy_bear

sheep

tennis_racket

potted_plant

hair_dryer

cow

bottle

bed

toothbrush

Access and download the model

Download the Common Object Detection pretrained model from ArcGIS Living Atlas of the World. Alternatively, link the model to a survey in Survey123 Connect.

  1. Browse to ArcGIS Living Atlas of the World.
  2. Sign in with your ArcGIS Online credentials.
  3. Search for Common Object Detection and open the item page from the search results.
  4. Click the Download button to download the model.

    The downloaded compressed .dlpk file contains the required .tflite and .emd files.

    You can use the extracted .tflite and .emd files directly in Survey123 Connect by copying these to the media folder for a survey with smart assistants configured.

Release notes

The following are the release notes:

DateDescription

February 2023

First release of Common Object Detection