# DL Enigma 1.0 - SUST CSE Carnival 2024 — Data

来源：https://www.kaggle.com/competitions/dl-enigma-10-sust-cse-carnival-2024/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Dataset Paper Link: https://arxiv.org/abs/2401.10659

## **Dataset Overview:**
The dataset covers the following 9 districts in Bangladesh: Sylhet, Dhaka, Rajshahi, Mymensingh, Maowa, Chittagong, Sirajganj, Sherpur, and Khulna. This dataset contains 9825 images with 78,943 Objects with 13 different classes. It is annotated with rectangular bounding box.Participants will encounter a wide range of road types, including towns, expressways, highways, and village roads. This diversity in locations aims to challenge algorithms to perform well across various driving contexts commonly encountered on Bangladesh roads. 

## **Data Collection:**
To ensure the authenticity of the dataset, all images were collected using smartphone cameras, simulating the real-world conditions faced by autonomous vehicles. The absence of online images ensures that participants are working with a dataset representative of the actual driving scenarios in Bangladesh, promoting the development of models with practical applicability.

**Goal**: Participants will develop solutions to detect objects in various Road Conditions fo Bangladesh.

## **Classes** : 13
- auto_rickshaw
- bicycle
- bus
- car
- cart_vehicle
- construction_vehicle
- motorbike
- person
- priority_vehicle
- three_wheeler
- train
- truck
- wheelchair

## **Sample Dataset**:

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F5328059%2F2c69790db325e71f9bfa40fb8d3012d0%2Fimage%20(1).png?generation=1705692179963469&alt=media)

## **Dataset Format**

This dataset is in Yolov5 format. The train and test images can be found in in `dlenigma1/BadODD/images/`, and the labels for the train dataset can be found in `dlenigma1/BadODD/labels/` directory.

- Train Image Count: 5896
- Test Image Count: 1964

**Each training image has a txt file of the same name in the labels directory.**

**Test**
Test set images are in `dlenigma1/BadODD/images/test`.

The test set has no provided annotations. Your task is to learn the bounding box from the train set and predict it for the test set images.