ANTOINE PORTE / Visual Wake Words for traffic light detection Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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.

Visual Wake Words for traffic light detection

Images

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (1,001 items)

View all

000000515022

ID: 257151338

Label: traffic light

000000096762

ID: 257151638

Label: traffic light

000000282366

ID: 257151502

Label: traffic light

000000417653

ID: 257151403

Label: traffic light

000000497312

ID: 257150924

Label: no traffic light

000000394892

ID: 257150991

Label: no traffic light

000000457691

ID: 257151381

Label: traffic light

000000258702

ID: 257151522

Label: traffic light

Model accuracy (Unoptimized (float32))

Validation set

71.9%

Test set

76.5%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

1243 ms.

Peak RAM usage

130.9K

Flash usage

307.0K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

1,001 items

Labels

no traffic light, traffic light

Project info

Project ID	208435
Project version	3
License	Apache 2.0
No. of views	29,255
No. of clones	4