Image Quality Assessment

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

0 Likes

Model Details

Model Description

EdgeSegNet-Classifier is an efficient and compact deep convolutional neural network based on the EdgeSegNet architecture. It can recognize 4 image quality cases such as Clean, Blur, Occlusion, and Bright.

Developed by: Zhong Qiu Lin
Model type: Computer vision
License: License
EdgeSegNet:

Training Data

The dataset used to train this model is proprietary and is not publicly available.

Technical Specifications

Input/Output Details

Input:
- Name: 77
  - Info: NCHW BGR 0-255 image.
Output:
- Name: 147
  - Info: Predictions for quality of image.

Throughput

Model variant: image-quality-assessment:256x256

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	26.84	N/A

* 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 and depthai-nodes libraries:

pip install depthai
pip install depthai-nodes

Define model:

model_description = dai.NNModelDescription(
    "luxonis/image-quality-assessment:256x256"
)

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

Inspect model head(s):

ClassificationParser that outputs message (predicted emotion classes and scores.).

Get parsed output(s):

while pipeline.isRuning():
    parser_output: Classifications = parser_output_queue.get()

Example

You can quickly run the model using our script. It automatically downloads the model, creates a DepthAI pipeline, runs the inference, and displays the results using our DepthAI visualizer tool. To try it out, run:

python3 main.py \
    --model luxonis/image-quality-assessment:256x256

Image quality assessment using EdgeSegNet-Classifier.
License	MIT Commercial use
Downloads	37
Tasks	Classification
Model Types	IR

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2	11 months ago