Barcode detection

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

0 Likes

Model Details

Model Description

Luxonis Barcode Detection is a keypoint detection model trained to detect three classes of barcodes:

Bar Code
Data Matrix
QR Code

In addition to detecting the bounding box of each barcode, the model predicts the keypoints of its corners in a specific, clockwise order: top-left, top-right, bottom-right, and bottom-left. This detailed keypoint information can be useful for precise alignment or decoding tasks where the exact positioning of the barcode corners is critical.

Developed by: Luxonis
Shared by:
Model type: Computer vision / Keypoint detection
License:
Resources for more information:

Training Details

Training Data

The model was trained on a custom dataset of 16k images, containing bar codes, data matrix, and QR codes in various conditions.

Training parameters:

Resolution: 768×576 (training resolution)
Epochs: 600
Model variant: Medium

Testing Details

Metrics

On a test set of 200 images, the keypoint mAP was 0.79.
This metric is highly sensitive to the sigma values used (here, 0.04 for each keypoint), which also influences training performance.

Technical Specifications

Input/Output Details

Input:
- Name: image
  - Info: NCHW BGR image scaled to 0–255.
Output:
- Name: output1_yolov6
- Name: output2_yolov6
- Name: output3_yolov6
- Name: kpt_output1
- Name: kpt_output2
- Name: kpt_output3

These outputs include both YOLO-like feature maps for bounding box detection and additional keypoint outputs for corner localization.

Model Architecture

This model has an efficient backbone and neck, along with a detection head and a keypoints head.
The keypoints are predicted in a fixed order (top-left, top-right, bottom-right, bottom-left), facilitating downstream tasks that rely on corner geometry.

For more information about the underlying architecture and training methodology, please refer to .

Throughput

Model variant: barcode-detection:768x576

• Input shape: [1, 3, 576, 768] • Output shapes: [[1, 8, 72, 96], [1, 8, 36, 48], [1, 8, 18, 24], [1, 12, 6912], [1, 12, 1728], [1, 12, 432]]

• Params (M): 17.276 • GFLOPs: 24.074

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	4.44	N/A
RVC4	FP32	142.99	6.02

Model variant: barcode-detection:512x384

• Input shape: [1, 3, 384, 512] • Output shapes: [[1, 8, 48, 64], [1, 8, 24, 32], [1, 8, 12, 16], [1, 12, 3072], [1, 12, 768], [1, 12, 192]]

• Params (M): 17.266 • GFLOPs: 10.700

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	17.39	N/A
RVC4	INT8	732.29	3.32

* 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 the model head(s)).
Below, we present the most crucial utilization steps for this particular model.
Please consult the for more information.

Install DAIv3 and depthai-nodes libraries:

pip install depthai
pip install depthai-nodes

Define model:

model_description = dai.NNModelDescription(
    "luxonis/barcode-detection:512x384"
)

nn = pipeline.create(ParsingNeuralNetwork).build(
    <CameraNode>, model_description
)

Inspect model head(s):

YOLOExtendedParser that outputs message (bounding boxes and corner keypoints of detected barcodes).

Get parsed output(s):

while pipeline.isRuning():
    parser_output: dai.ImgFrame = parser_output_queue.get()

Example

You can quickly run the model using the script. It automatically downloads the model, creates a DepthAI pipeline, runs inference, and visualizes the results with the DepthAI visualizer tool.

python3 main.py \
    --model luxonis/barcode-detection:512x384

Bounding box and keypoint detection model for QRs, barcodes and datamatricies
License	Apache 2.0 Commercial use
Downloads	487
Tasks	Object Detection
Model Types	ONNX

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2, RVC4	2 months ago
		RVC2, RVC4	2 months ago