Road Mark Detection

[abhisheks008]

Deep Learning Simplified Repository (Proposing new issue)

🔴 Project Title : Road Mark Detection

🔴 Aim : The aim of this project is to detect road marks using DL methods.

🔴 Dataset : https://www.kaggle.com/datasets/pkdarabi/road-mark-detection

🔴 Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

🔴🟡 Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

✅ To be Mentioned while taking the issue :

• Full name :
• GitHub Profile Link :
• Email ID :
• Participant ID (if applicable):
• Approach for this Project :
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[Madhusri02]

Full name : Madhu Sri
GitHub Profile Link : https://github.com/Madhusri02
Email ID : [email protected]
Participant ID (if applicable): -
Approach for this Project : We can use Convolutional Neural Network (CNN), Mask R-CNN , U-Net , YOLO algorithms to make this model .
What is your participant role? (SWOC) : Contributor

[abhisheks008]

Are you a participant of SWOC?

[abhisheks008]

Assigned @Madhusri02

[Madhusri02]

Thank You @abhisheks008

[SrinadhVura]

Hi there,

I would like to work on this issue.
Full name : Srinadh Vura
GitHub Profile Link : https://github.com/SrinadhVura/
Email ID : [email protected]
Participant ID (if applicable):
Approach for this Project : I have two approaches in my mind. First one is to get a pre-trained resnet-50 without top layers and train it on the dataset. Second one is to apply a CNN.
What is your participant role? Contributor | GSSOC 2024

[abhisheks008]

Hi @SrinadhVura wait for the induction session to complete by today evening, after that issues will be assigned to the contributors.

[SHREERAJ11]

Full name : Sobhan Shreeraj Sa
GitHub Profile Link : https://github.com/SHREERAJ11
Email ID : [email protected]
Participant ID (if applicable): --
Approach for this Project : My primary approach would be trying multiple pre-trained CNN models. Apart from CNN, I would also like to try SVM or Decision Trees for comparing accuracy scores with CNNs and I will try to learn and implement Semantic segmentation with FCNs.
What is your participant role? GSSoC | Contributor

I would really like to work on this issue!

[abhisheks008]

Hi @SHREERAJ11 thanks for your interest. As the repository name suggests, the projects are mainly focusing on deep learning methods and you need to implement at least 2-3 deep learning algorithms for any of the projects. Can you please rephrase your approach?

[Vinayakkh]

Full name : Vinayak Khandelwal
GitHub Profile Link :https://github.com/Vinayakkh
Email ID :[email protected]
Participant ID (if applicable):
Approach for this Project :Apply CNN to this and by applying layers to make it more accurate prediction on train data applying various models
What is your participant role? GSSOC | Contributor

[abhisheks008]

Hi @Vinayakkh can you please share the algorithms/models you are planning to use for this dataset. As you need to implement at least 2-3 models, and compare them based on the accuracy scores to find out the best fitted model.

[SHREERAJ11]

Hello @abhisheks008 , sorry for the confusion. Initially I meant to apply image segmentation CNN approaches: Mask R-CNN, U-NET, PSP-NET and DeepLab. Also I would like to try with other algos if permitted to check for accuracies and errors.

[abhisheks008]

Nice approach @SHREERAJ11. You can start working on this issue.

[github-actions]

Hello @SHREERAJ11! Your issue #444 has been closed. Thank you for your contribution!