Edge Impulse Experts / Digital twin-enabled Smart Shipping Workstation Public

Target: Raspberry Pi 5 Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Digital twin-enabled Smart Shipping Workstation

Object detection

About this project

This FOMO (Faster Objects, More Objects) object detection model is trained on synthetic sample product images to detect their real-world counterparts to create an AI-oriented solution for shipping operations.

While labeling my synthetic image samples, I simply applied the names of the represented real-world objects:

wrench
mouse
basketball
tea_cup
hammer
screwdriver

After training and validating, I deployed my FOMO model as a Linux (AARCH64) application (.eim) compatible with Raspberry Pi 5.

Data (238 items)

View all

tea_cup_omniverse_sample_16

ID: 1367836191

tea_cup_omniverse_sample_12

ID: 1367836179

hammer_omniverse_sample_18

ID: 1367836096

basketball_omniverse_sample_13

ID: 1367836064

wrench_omniverse_sample_14

ID: 1367836222

tea_cup_omniverse_sample_21

ID: 1367836196

wrench_omniverse_sample_30

ID: 1367836239

hammer_omniverse_sample_19

ID: 1367836097

Model accuracy (Unoptimized (float32))

Validation set

80.0%

Test set

93.1%

On-device performance (Raspberry Pi 5, Unoptimized (float32))

Latency

9 ms.

Flash usage

-

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

238 items

Labels

basketball, hammer, mouse, screwdriver, tea_cup, wrench

Project info

Project ID	538874
Project version	3
License	Apache 2.0
No. of views	2,533
No. of clones	0