Alif Semiconductor / License Plate Detection Public

Target: Alif HP (Cortex-M55 400MHz + U55-256MACC) 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.

License Plate Detection

Object detection

About this project

A license plate detector that uses a combination of AI generated and real license plates to traing a model for finding license plates on cars. The models used are NVIDIA TAO models. This project is specifically tuned to work with Alif Ensemble devices. More documentation may be found at https://docs.edgeimpulse.com/docs/edge-ai-hardware/mcu-+-ai-accelerators/alif-ensemble.

Data (597 items)

View all

d_license_plate_226_jpg.rf.420fa0b20bfe414448f7b79bcccd690c

ID: 1174580577

130_0040_jpg.rf.be01b396cf8fb6445d38a22887125192

ID: 1174580951

d_license_plate_222_jpg.rf.9f2ae32b4bb64305447946c49b2d5386

ID: 1174580486

130_0023_jpg.rf.7f8c5414ae44241c92461de97f3609f6

ID: 1174580721

130_0076_jpg.rf.e237abeb75d7abf2510289faa7b2f085

ID: 1174580952

130_0055_jpg.rf.9a4f4d55491a378a0802e82ca51f9969

ID: 1174580751

d_license_plate_11_jpg.rf.cbf493284411020fe28e90bf41dd6579

ID: 1174580709

d_license_plate_126_jpg.rf.d8e3bea84a3caa0ca3fc742d46d378f8

ID: 1174580974

Model accuracy, 350 epoch TAO MBv2 0.25 SSD (Unoptimized (float32))

View 4 other experiments

Validation set

0.44

Test set

0.38

On-device performance (Alif HP (Cortex-M55 400MHz + U55-256MACC), Quantized (int8))

Latency

4 ms.

Peak RAM usage

726.0K

Flash usage

690.2K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

597 items

Labels

plaque

Project info

Project ID	367451
Project version	6
License	Apache 2.0
No. of views	85,616
No. of clones	90