License Plate Detection

Our new model ZOO works with DepthAI V3. Find out more in our documentation.

0 Likes

Model Details

Model Description

YOLOv8n is a cutting-edge, state-of-the-art (SOTA) model that builds upon the success of previous YOLO versions and introduces new features and improvements to further boost performance and flexibility. YOLOv8 is designed to be fast, accurate, and easy to use, making it an excellent choice for a wide range of object detection and tracking, instance segmentation, image classification and pose estimation tasks.

Original model:
Re-implenented by:
Model type: Computer Vision
License:
Resources for more information:

Training Details

The model was trained on consisting of roughly 21 000 training images with one single "License plate" class. The images include cars, trucks and motorcycles from multiple countries as to help with generalization.

Testing Details

Testing was performed on a test split of 1018 images from the same dataset. The below metrics are based on the underlying source model before it was converted to RVC2 and RVC4 compatible format.

Metrics

Class	Images	Instances	Precision	Recall	AP@50	AP@50-95
License Plate	1218	1048	0.831	0.96	0.895	0.637

Technical Specifications

Input/Output Details

Input:
- Name: images
  - Info: NCHW BGR non-normalized image
Output:
- Name: output1_yolov6r2
  - Info: Unprocessed output of the first channel
- Name: output2_yolov6r2
  - Info: Unprocessed output of the second channel
- Name: output3_yolov6r2
  - Info: Unprocessed output of the third channel

Model Architecture

Please consult the for more information on model architecture.

Throughput

Model variant: license-plate-detection:640x640

• Input shape: [1, 3, 640, 640] • Output shapes: [[1, 6, 80, 80], [1, 6, 40, 40], [1, 6, 20, 20]]

• Params (M): 3.006 • GFLOPs: 4.530

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	13.****/A
RVC4	INT8	562.50	3.77

* Benchmarked with , using 2 threads (and the DSP runtime in balanced mode for RVC4).

* Parameters and FLOPs are obtained from the package.

Utilization

Models converted for RVC Platforms can be used for inference on OAK devices. DepthAI pipelines are used to define the information flow linking the device, inference model, and the output parser (as defined in model head(s)). Below, we present the most crucial utilization steps for the particular model. Please consult the docs for more information.

Install DAIv3 library:

pip install depthai

Define model:

model_description = dai.NNModelDescription(
    "luxonis/license-plate-detection:640x640"
)

nn = pipeline.create(dai.node.DetectionNetwork).build(
    <CameraNode>, model_description
)

The model is automatically parsed by DAI and it outputs the message (bounding boxes, labels, and scores of the detected licence plates).

Get model output(s):

while pipeline.isRuning():
    nn_output: dai.ImgDetections = parser_output_queue.get()

Example

You can quickly run the model using our example.

The example demonstrates how to build a 3-stage DepthAI pipeline consisting of a car detection model, a licence plate detection model, and a text recognition model. It automatically downloads the models, creates a DepthAI pipeline, runs the inference, and displays the results using our DepthAI visualizer tool.

To try it out, run:

python3 main.py

Pretrained YOLOv8 model for detecting vehicle license plates
License	MIT Commercial use
Downloads	409
Tasks	Object Detection
Model Types	ONNX

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2, RVC4	10 months ago