Shakhizat Nurgaliyev / Hand Gesture Recognition Public

Target: Raspberry Pi RP2040 (Cortex-M0+ 133MHz) 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.

Hand Gesture Recognition

Accelerometer

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 (82 samples)

View all

up-down.37ghs7rg

ID: 115652554

Label: up-down

Sample length: 10s

up-down.37gis10l

ID: 115652514

Label: up-down

Sample length: 10s

idle.37e8oqq5

ID: 115652561

Label: idle

Sample length: 10s

idle.37gijnrd

ID: 115652529

Label: idle

Sample length: 10s

idle.37e8h51r

ID: 115652568

Label: idle

Sample length: 10s

left-right.37ginmr6

ID: 115652524

Label: left-right

Sample length: 10s

forward-backward.37gj8i1v

ID: 115652515

Label: forward-backward

Sample length: 10s

idle.37e8aevf

ID: 115652574

Label: idle

Sample length: 10s

Model accuracy (Unoptimized (float32))

Validation set

98.5%

Test set

On-device performance (Raspberry Pi RP2040 (Cortex-M0+ 133MHz), Unoptimized (float32))

Latency

36 ms.

Peak RAM usage

5.1K

Flash usage

25.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

13m 40s

Sensors

accX, accY, accZ @ 9Hz

Labels

forward-backward, idle, left-right, up-down

Project info

Project ID	115505
Project version	1
License	No license attached
No. of views	12,053
No. of clones	69