Nilanjan Mandal / Wounded Animal Detection Public

Target: Cortex-M4F 80MHz 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.

Wounded Animal Detection

Images

About this project

Wounded animal detection in wild using Kria KV260 and Edge Impulse

Data (92 items)

View all

injured_animal38.jpg.2vcevqmj

ID: 86806257

Label: Wounded

injured_animal39.jpg.2vcevqm6

ID: 86806256

Label: Wounded

injured_animal3.jpg.2vcevq1g

ID: 86806266

Label: Wounded

injured_animal50.jpg.2vcevo4g

ID: 86806274

Label: Wounded

background5.jpg.2vcf1dnt

ID: 86806220

Label: Background

background19.jpg.2vcf1dq1

ID: 86806214

Label: Background

injured_animal46.jpg.2vcevr6h

ID: 86806246

Label: Wounded

injured_animal30.jpg.2vcevqs7

ID: 86806253

Label: Wounded

Model accuracy (Unoptimized (float32))

Validation set

86.7%

Test set

89.5%

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

1092 ms.

Peak RAM usage

733.2K

Flash usage

627.7K

Run this model

On any device

Clone project

Dataset summary

Data collected

92 items

Labels

Background, Wounded

Project info

Project ID	90814
Project version	1
License	No license attached
No. of views	23,001
No. of clones	79