Object Tracking Project

abhisheks008 commented 2 years ago

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Object Tracking Project
:red_circle: Aim : The aim is to create a deep learning project which will detect the objects and recognize them accordingly.
:red_circle: Dataset : https://www.kaggle.com/datasets/kmader/videoobjecttracking
:red_circle: 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.

:red_circle::yellow_circle: 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.

:white_check_mark: 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. 😎

Daksh1603 commented 2 years ago

Hello ! I would love to work on this project . Please assign this to me :)

abhisheks008 commented 2 years ago

Thanks for commenting and showing interest in this issue @Daksh1603. Program will start from 1st of August, till then brush up your skills in DL.

Rushijaviya commented 2 years ago

@Daksh1603 you want to work on this?

narpatchoudhary777 commented 2 years ago

Hey @abhisheks008 I would like to work on this project. If no one is working on this project consider me for the same. Full name : Narpat Choudhary GitHub Profile Link : https://github.com/narpatchoudhary777 Email ID : choudharynama19ie@student.mes.ac.in Approach for this Project : I will use CNN in this project implementation

Rushijaviya commented 2 years ago

Assigning this to you @narpatchoudhary777. Happy contributing!

ShashwatGaikwad24 commented 2 years ago

Hey @abhisheks008 I would like to work on this project. If no one is working on this project, let me do this. Full name : Shashwat Gaikwad GitHub Profile Link : https://github.com/ShashwatGaikwad24 Email ID : gaikwadshsa19ie@student.mes.ac.in Approach for this Project : I will use CNN in this project implementation

abhisheks008 commented 2 years ago

Issue assigned to you @ShashwatGaikwad24

ShashwatGaikwad24 commented 2 years ago

Thanks! Will start working on it.

Garvanand commented 1 year ago

@abhisheks008 please assign this issue to me

abhisheks008 commented 1 year ago

Can you please share the approach for this project @Garvanand

Garvanand commented 1 year ago

Initially I would do Exploratory Data Analysis (EDA):

1:Download the dataset from the provided link and familiarize yourself with its structure and contents. 2:Explore the dataset to gain insights into its features, labels, and distribution of data. 3:Visualize sample images and their corresponding object annotations to understand the task at hand.

*Data Preprocessing:

Preprocess the dataset to prepare it for training the deep learning models. Perform necessary data transformations, such as resizing images, normalizing pixel values, and handling missing or corrupted data. Split the dataset into training and testing sets to evaluate the models' performance. *Model Selection and Training:

Choose 3-4 deep learning algorithms suitable for object detection and recognition tasks. Popular choices include Faster R-CNN, YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), and RetinaNet. Implement each algorithm using a deep learning framework such as TensorFlow or PyTorch. Train each model on the training set and fine-tune the hyperparameters as necessary. *Model Evaluation and Comparison:

Evaluate the trained models using the testing set and measure their performance metrics such as accuracy, precision, recall, and F1-score. Compare the performance of each algorithm and identify the best-fitted algorithm for your project based on the evaluation results. Consider other factors such as computational efficiency, model complexity, and ease of implementation when making the final decision. *Model Deployment and Application:

Once you have selected the best-fitted algorithm, save the trained model for future use. Develop a user-friendly interface or application to showcase the object detection and recognition capabilities of your model. Test the deployed model on new images or videos to verify its performance in real-world scenarios.

abhisheks008 commented 1 year ago

Issue assigned to you @Garvanand