The creators of the Dhaka-AI: Dhaka Traffic Detection Challenge Dataset emphasize the distinctive traffic conditions in Dhaka city. Although it's a city of significant size, only 7% of its roads meet urban standards. However, it contends with a staggering 8 million daily commuters, all within a 306 square kilometer area. In response to this complex challenge, they introduced the AI-based Dhaka Traffic Detection Challenge.

Dhaka AI

## Overview

Dhaka AI is a dataset for object detection tasks - it contains Cars annotations for 270 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset

This dataset was created by Khan Fashee Monowar (Sawrup)

Released under CC0: Public Domain

Contents

Dhakaai
This dataset falls under the category Individual Transport Traffic Control Systems.
It contains the following data: The capital city of Dhaka has only 7% traffic roads (compared to 25% urban standard) in presence of approximately 8 million computers a day with in 306 sq km area. The senario of Dhaka traffic is unique which poses complex new challanges in terms of automated traffic detection. To solve the problem using advances in AI-based technology and ICT solutions, we are calling for splutions to automatic Dhaka traffic detection problems on optical images. This new AI-Based Dhaka Traffic Detection Challenge aims at accessing the ability of state-of-the-art methods to detect and recognize traffic vehicles. This solution is encountered in mordern cities where multile cultures live and communicate together, where users see various scripts and languages in a way that prevents using much a priori knowledge. Alos, at the same time, the academics and researches from region who are experts in AI or interested in exploring possibilities could be brought to a networking community throug this campaign. Working together on a common problem statement can create the right synergies needed to build AI-based community in South-East Asia. (2020-09-15)
This dataset was scouted on 2022-02-27 as part of a data sourcing project conducted by TUMI. License information might be outdated: Check original source for current licensing. The data can be accessed using the following URL / API Endpoint: https://dataverse.harvard.edu/dataset.xhtml;jsessionid=6c5cd96a9018797ddba286e3f404?persistentId=doi%3A10.7910%2FDVN%2FPOREXF&version=&q=&fileTypeGroupFacet=&fileAccess=Public

Dataset

This dataset was created by TheDarkKnight

Contents

Dhaka Traffic

## Overview

Dhaka Traffic is a dataset for object detection tasks - it contains Vehicle annotations for 334 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Urban Road Network Data
This dataset falls under the category Individual Transport Street Network Geometries (Geodata).
It contains the following data: Tool and data set of road networks for 80 of the most populated urban areas in the world. The data consist of a graph edge list for each city and two corresponding GIS shapefiles (i.e., links and nodes).
This dataset was scouted on 2022-02-27 as part of a data sourcing project conducted by TUMI. License information might be outdated: Check original source for current licensing. The data can be accessed using the following URL / API Endpoint: https://figshare.com/articles/dataset/Urban_Road_Network_Data/2061897?file=3663381

Dhaka

## Overview

Dhaka is a dataset for object detection tasks - it contains Characters annotations for 389 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Visual Pollution Dhaka Streets

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F6898530%2F1b657921ea31dccbb9833c6a7f0fd868%2F1-s2.0-S2772662223001236-gr11_lrg.jpg?generation=1715415517456859&alt=media" alt="">

This dataset was created and used in the paper "Visual Pollution Detection Using Google Street View and YOLO". Later the dataset was further utilized in the paper "An end-to-end pollution analysis and detection system using artificial intelligence and object detection algorithms".

The dataset contains 1400 bounding box annotated images belonging to 6 different classes of visual pollutants commonly seen in the streets of Dhaka, Bangladesh. The visual pollutants are Billboards, Bricks, Construction Materials, Street Litter, Wires, and Towers. All the images were collected from Google Street View and later annotated by the authors for the individual pollutants. The images are 500 x 500 sized RGB images and text annotations are in YOLO format. Each of the following categories within the class: construction materials and street litter comprise 300 images, while billboards, bricks, and wires each contain 200 bounding box annotated images. However, individual images may contain multiple annotations (multiple similar objects in the same image) of the same class along with other classes (ie: towers and bricks in the same image).

For both of the aforementioned studies, the authors took the first 80% of the images from each class for training and the last 20% of the images for validation.

If you use the dataset for any research, kindly consider citing the following papers:

[1] Md Yearat Hossain, Ifran Rahman Nijhum, Abu Adnan Sadi, Md Tazin Morshed Shad, and Rashedur M. Rahman. "Visual pollution detection using google street view and YOLO." In 2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 0433-0440. IEEE, 2021.

[2] Md Yearat Hossain, Ifran Rahman Nijhum, Md Tazin Morshed Shad, Abu Adnan Sadi, Md Mahmudul Kabir Peyal, and Rashedur M. Rahman. "An end-to-end pollution analysis and detection system using artificial intelligence and object detection algorithms." Decision Analytics Journal 8 (2023): 100283.

Excel data files containing model and ambient PM2.5 concentrations at the U.S. Embassy in Dhaka.

This dataset is associated with the following publication: Sarwar, G., C. Hogrefe, B. Henderson, K. Foley, R. Mathur, B. Murphy, and S. Ahmed. Characterizing variations in ambient PM2.5 concentrations at the U.S. Embassy in Dhaka, Bangladesh using observations and the CMAQ modeling system. ENVIRONMENT INTERNATIONAL. Elsevier B.V., Amsterdam, NETHERLANDS, 296: N/A, (2023).

Vehicle Detection In DHAKA

## Overview

Vehicle Detection In DHAKA is a dataset for object detection tasks - it contains Vehicles annotations for 3,003 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Bangladesh Motor Vehicle Registered: Dhaka: Ambulance
This dataset falls under the category Planning & Policy Driving License Ownership Rate.
It contains the following data: Bangladesh Motor Vehicle Registered: Dhaka: Ambulance data was reported at 614.000 Unit in 2021. This records an increase from the previous number of 599.000 Unit for 2020. Bangladesh Motor Vehicle Registered: Dhaka: Ambulance data is updated yearly, averaging 322.500 Unit from Dec 2010 to 2021, with 12 observations. The data reached an all-time high of 614.000 Unit in 2021 and a record low of 114.000 Unit in 2012. Bangladesh Motor Vehicle Registered: Dhaka: Ambulance data remains active status in CEIC and is reported by Bangladesh Road Transport Authority. The data is categorized under Global Databases Bangladesh Table BD.TA001: Motor Vehicle Registered.
This dataset was scouted on 2022-02-27 as part of a data sourcing project conducted by TUMI. License information might be outdated: Check original source for current licensing. The data can be accessed using the following URL / API Endpoint: https://www.ceicdata.com/en/bangladesh/motor-vehicle-registered/motor-vehicle-registered-dhaka-ambulance

Historical dataset of population level and growth rate for the Dhaka, Bangladesh metro area from 1950 to 2025.

PTZ (Dhaka) 28

## Overview

PTZ (Dhaka) 28 is a dataset for object detection tasks - it contains Vehicle UKJH annotations for 971 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

In Bangladesh, general public compliance with traffic regulations is notably low. This dataset aims to analyze the traffic flow patterns in Dhaka, focusing on both vehicular movement and pedestrian activities. Data were gathered from four different locations: Shapla Chattar, Arambag, Bashabo, and Abul Hotel. Video recordings were taken from footover bridges, capturing traffic scenarios involving single-lane and double-lane roads, as well as the erratic movement of pedestrians. A total of 23,678 images were extracted from these recordings, which were collected during five distinct time intervals on a weekday, and subsequently annotated using the Roboflow tool. This dataset offers a detailed perspective on Dhaka’s unstructured traffic systems, highlighting various road conditions and heavy traffic environments. Its applications include vehicle fitness monitoring, pedestrian behavior analysis, and traffic flow assessment under diverse environmental conditions, such as daylight, dusk, night, and rain. Additionally, this dataset presents opportunities for researchers to explore and apply machine learning techniques to complex, real-world traffic scenarios. Readme file contains folder hierarchy of our dataset.

Flood information product over Dhaka (Bangladesh) contains spatial explicit information about the floods and hazard for years 2004, 2007, 2014 & 2016. The level of detail for the classification scheme mainly relies on the input data sources.

Bangladesh Motor Vehicle Registered: Dhaka: Total data was reported at 125,851.000 Unit in 2023. This records a decrease from the previous number of 174,812.000 Unit for 2022. Bangladesh Motor Vehicle Registered: Dhaka: Total data is updated yearly, averaging 54,348.000 Unit from Dec 1995 (Median) to 2023, with 29 observations. The data reached an all-time high of 174,812.000 Unit in 2022 and a record low of 14,548.000 Unit in 1999. Bangladesh Motor Vehicle Registered: Dhaka: Total data remains active status in CEIC and is reported by Bangladesh Road Transport Authority. The data is categorized under Global Database’s Bangladesh – Table BD.TA001: Motor Vehicle Registered.

Probable informal settlements over Dhaka (Bangladesh) contains spatial explicit information about position of slums as identified in 2006 & 2010 from ancillary data sources and in 2017 by interpretation of VHR satellite imagery. The level of detail for the classification scheme mainly relies on the input data sources.

This dataset contains current and historical UV Index data for Dhaka.

Shortest Route Analysis Of Dhaka City Roads Using Various Gis Techniques (Dataset And Sample Outputs)
This dataset falls under the category Public Transport Transport Network Geometries (Geodata).
It contains the following data: This repository is the dataset of the related paper "Shortest Route Analysis of Dhaka City Roads Using Various GIS Techniques".The data presented here are collected and gathered together from several separate locations. All the probable original sources of the dataset are open-source or free to distribute licensed. The dataset has the following items: 1. Road network of Dhaka city. 2. Bus Route network of Dhaka city. 3. Future metro Route network of Dhaka city. 4. All the bus stands in Bangladesh. 5. All planned metro station in Dhaka city. 6. The output of some sample random two points shortest or cheapest path from the related paper.
This dataset was scouted on 2022-02-23 as part of a data sourcing project conducted by TUMI. License information might be outdated: Check original source for current licensing. The data can be accessed using the following URL / API Endpoint: https://data.mendeley.com/datasets/j5b93k2xhk/1\