Browse » Smoking
Top Smoking Datasets
Smoking and smoke detection datasets can be used in a wide variety of use cases such as early identification of wildfires, building fires, and manufacturing fires. Detecting fires visually can help alert security teams before smoke detectors sense smoke particles.
Along with fires, smoke detection can be used to identify cigarettes and cigarette smoking for media and content moderation. Content moderation ensures broadcasting, television, and other media organizations are meeting all local laws regarding age appropriate content.
This dataset was originally created by Matteo Pacini. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/sigma-pub/smoke-detection-sigma.
Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark
Here are a few use cases for this project:
Environmental Cleaning Initiatives: This model can be used in helping clean-up teams to locate and clean cigarette buds in parks, beaches, and streets, thereby contributing to environmental protection.
Surveillance Systems: Security agencies or businesses can use this model in surveillance systems to enforce no-smoking areas or to identify individuals who are littering public areas, potentially leading to fines.
Robotics & Automation: This could be integrated into autonomous cleaning robots for more effective waste segregation and handling, specifically targeting cigarette litter.
Health and Safety Inspection: In environments like factories, warehouses, etc., where smoking might pose a serious risk (due to flammable goods), this model could be used to identify potential safety violations and reduce the risk of fire hazards.
Research and Public Policy: Researchers studying patterns in smoking habits and urban waste can use this model for better data collection. This can inform policymaking such as the placement of designated smoking areas or public ashtrays.
Smoke Detection Dataset
This computer vision smoke detection dataset contains images of synthsized smoke in both indoor and outdoor settings. Check out the source link below for more information on this dataset.
- Identifying smoke indoors
- Identifying smoke outdoors (but not with aerial imagery)
- Identifying smoke-like object (eg: mist/steam from humidifiers)
You can test this model by using the Roboflow Inference Widget found above. The action hits the model inference API, which in turn produces the color coded bounding boxes on the objects the model was trained to detect, along with its labels, and confidence for each prediction. The feature also produces the JSON output provided by the API.