Smoking_person Object Detection Dataset and Pre-Trained Model by visionwork

Images

3895 images

Explore Dataset

Here are a few use cases for this project:

Public Health Research: The "Smoking_person" model can be used in public health surveillance to quantify the prevalence of smoking and vaping in certain areas or among specific demographics. By implementing this model on public video feeds or social media images, public health researchers can gather quantitative data about cigarette and vape usage.
Content Moderation: This model can be used in platforms that want to enforce content moderation rules related to smoking or vaping. Social media platforms or community forums that want to limit visibility or sharing of such content can apply this model to automatically detect and flag these images.
Anti-Smoking Campaigns: NGOs and Governmental institutions could use this model to monitor the effect of anti-smoking campaigns over time. They could analyze historical and recent images to evaluate changes in smoking events and measure the impact of their campaigns on public smoking habits.
Retail Compliance Monitoring: This model could be used by retailers in jurisdictions where in-store smoking is restricted. By integrating the model into surveillance systems, alerts could be sent if customers are smoking inside the store, ensuring the premises stay compliant with local regulations.
Parental Control Applications: For parental control software, the model could enhance functionality by allowing parents to block or limit explicit material containing smoking or vaping, offering a more customizable user experience and additional protection layer for underage internet users.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            smoking_person_dataset,
                            title = { Smoking_person Dataset },
                            type = { Open Source Dataset },
                            author = { visionwork },
                            howpublished = { \url{ https://universe.roboflow.com/visionwork/smoking_person } },
                            url = { https://universe.roboflow.com/visionwork/smoking_person },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2022 },
                            month = { dec },
                            note = { visited on 2024-04-26 },
                            }