snakes Computer Vision Project

Akhil

Updated 2 months ago

0

views

0

downloads
Description

In the current day and age where we are bombarded with thousands of digital text, images and videos daily, we are bound to come across text, images or videos that we do not want or should not see (including snakes!).

Under constant influence of such texts, images and/or videos, a person may experience the following short term effect

  • Sweating / Chills
  • Shortness of breath
  • Nausea / Headaches / Numbness
  • Confusion or disorientation
  • Loss of appetite

Therefore, how can we utilise machine learning to block off and filter out snakes (pixel by pixel) from images and videos?

In this project, we utilise Roboflow to assist with annotating of our project using the smart polygon features. After annotation, we utilise the dataset to train our customised YOLOv7 model. Our deployed model can be found streamlit at: https://erjieyong-v-instance-segmentation-streamlitstreamlit-app-2r2fpv.streamlit.app/

Active learning is engaged to continuously push low confidence image output back to roboflow for further training!

Learn more about this project at my github: https://github.com/erjieyong/ViShield_Computer_Vision

Supervision

Build Computer Vision Applications Faster with Supervision

Visualize and process your model results with our reusable computer vision tools.

Cite This Project

LICENSE
CC BY 4.0

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

                        @misc{
                            snakes-oozrc-wgykw_dataset,
                            title = { snakes Dataset },
                            type = { Open Source Dataset },
                            author = { Akhil },
                            howpublished = { \url{ https://universe.roboflow.com/akhil-yktip/snakes-oozrc-wgykw } },
                            url = { https://universe.roboflow.com/akhil-yktip/snakes-oozrc-wgykw },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { sep },
                            note = { visited on 2024-11-15 },
                            }
                        
                    

Similar Projects

See More
6.6k images 1 model