Fire Detection | Luxonis

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

0 Likes

Model Details

Model Description

Fire Detection model is a YOLOv5 based model. It runs real-time and can be deployed on cameras, drones, IoT devices, and other surveillance systems to enhance fire safety measures. It is based on the small version of the model.

Shared by:
Model type: Computer vision
License:

Training Details

It was trained on fire images from .

Testing Details

No testing details available.

Technical Specifications

Input/Output Details

Input:
- Name: images
- Info: NCHW BGR un-normalized image
Output1:
- Name: output1_yolov5
  - Info: Detection output 1
Output2:
- Name: output2_yolov5
  - Info: Detection output 2
Output3:
- Name: output3_yolov5
  - Info: Detection output 3

Model Architecture

Backbone: CSPDarknet53 - Extracts meaningful features from the input image, such as edges, textures, and object structures.
Neck: PAN - Enhances feature maps for detecting objects of different sizes.
Head: Outputs final detection results, including bounding boxes, confidence scores, and class labels.

Throughput

Model variant: fire-detection:512x288

• Input shape: [1, 3, 288, 512] • Output shapes: [[1, 18, 36, 64], [1, 18, 18, 32], [1, 18, 9, 16]]

• Params (M): 7.013 • GFLOPs: 3.131

Platform	Precision	Throughput (infs/sec)	Power Consumption (W)
RVC2	FP16	27.71	N/A
RVC4	FP16	586.10	5.85

* 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/fire-detection:512x288"
)

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

The model is automatically parsed by DAI and it outputs the dai.ImgDetections message (bounding boxes and scores of the detected fire).

Get model output(s):

while pipeline.isRuning():
    nn_output: dai.ImgDetections = 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/fire-detection:512x288

A YOLOv5s based fired detection model.
License	GNU Affero General Public License v3.0 Commercial use
Downloads	83
Tasks	Object Detection
Model Types	ONNX PYTORCH

Model Variants

Name	Version	Available For	Created At	Deploy
		RVC2, RVC4	3 months ago