Loading
AI Blitz XI: Completed #educational #blitz Weight: 30.0
873
183
13
225

Welcome to AI Blitz XI! πŸš€ |  Starter Kit For This Challenge! πŸ› 

Community Contribution Prizes πŸ““  |  Find Teammates πŸ‘―β€β™€οΈ

Easy-2-Follow Notebooks πŸ’»   | Discord AI Community πŸŽ§

πŸ”₯ Introduction

Self-driving cars collect a large amount of visual data for decision-making. It uses three tools to replicate human eyes - cameras, radar, and lidar. Together they create a complete picture of the car’s environment. They help the car identify the place, speed, and objects around it. 

Understanding the environment around the self-driving car is really critical to driving safely on the roads. Having an understanding of individual elements such as sidepaths, buildings, lanes, trees, people and other objects around the road allows safe driving.  With detailed segmentation of the scenes, self-driving cars will become more accurate & safer.

For this puzzle, your task is to segment the scene of the input image. The starter kit gives a walkthrough of image segmentation and its basics.

βœ”  The Task

In this challenge your task will be to build an automated algorithm that will take the road scene image and will output the semantic segmentation from the input image :

In machine learning terms: this is a multi-class semantic segmentation task.

πŸš€ Getting Started

Make your first submission using starter kit. πŸš€


πŸ’Ύ Dataset

The dataset files are available here.

The semantic segmentation dataset was generated using the Carla Simulator. The dataset contains over 23 different classes.

The images ( RGB format ) are in image folder where the corresponding semantic segmentation labels ( grayscale format ) are in the segmentation folder. 

data
β”œβ”€β”€ train.zip
β”‚   β”œβ”€β”€ image
β”‚   β”‚   β”œβ”€β”€ 0.jpg
β”‚   β”‚   β”œβ”€β”€ 1.jpg
β”‚   β”‚   β”œβ”€β”€ ...
β”‚   β”‚   └── 3999.jpg
β”‚   └── segmentation
β”‚       β”œβ”€β”€ 0.png
β”‚       β”œβ”€β”€ 1.png
β”‚       β”œβ”€β”€ ...
β”‚       └── 3999.png
└── test.zip
    └── image
        β”œβ”€β”€ 0.jpg
        β”œβ”€β”€ 1.jpg
        β”œβ”€β”€ ...
        └── 999.jpg

πŸ“ Files

Following files are available in the resources section:

  • train.npz - ( 4k samples ) The training images and corresponding semantic segmentation labels. 

  • test.zip- ( 1k samples ) It contains the images for testing data and the generate labels will be used in the leaderboard. 


πŸ“¨ How to submit

Make your first submission using the starter kit πŸš€

  1. Use segmentation folder and fill the corresponding segmentation image.

  2. Inside a submission directory, put the .ipynb notebook from which you trained the model and made inference and save it as notebook.ipynb.

  3. Zip the submission directory

  4. Overall, this is what your submission directory should look like - 

submission.zip
β”œβ”€β”€ segmentation
β”‚   β”œβ”€β”€ 0.png
β”‚   β”œβ”€β”€ 1.png
β”‚   β”œβ”€β”€ ...
β”‚   └── 999.png
└── notebook.ipynb

πŸ–Š Evaluation Criteria

The evaluation metric for this competition is F1 Score with weighted average.

πŸ“± Contact

If you have any questions, consider posting on the Blitz 11 Community Discussion board, or join the party on our Discord!