Streets and Crosswalks Object Detection Dataset and Pre-Trained Model by Data Dynamos

Images

1175 images

Explore Dataset

Here are a few use cases for this project:

Urban Planning and Development: The "Streets and Crosswalks" computer vision model can be used by urban planners and architects to analyze street layouts, identify pedestrian and vehicle traffic patterns, and evaluate the placement of infrastructure such as crosswalks, benches, and greenery, to optimize the design of safer and more efficient city spaces.
Autonomous Vehicle Navigation: This model can assist autonomous vehicles in accurately detecting and understanding their surroundings, including identifying other vehicles, pedestrians, crosswalks, and various street elements. This will enable the vehicles to make informed decisions on how to navigate safely through urban environments.
Traffic Management and Infrastructure Maintenance: The model can be used by local government authorities to monitor and manage traffic flow in real-time, identifying congestions, obstructions, or potential hazards. Additionally, it can support the maintenance of public infrastructure by detecting damaged or deteriorating elements such as benches, bins, or fences that require repair or replacement.
Accessibility Analysis and Improvement: The "Streets and Crosswalks" model can be employed by disability advocates and city planners to evaluate the accessibility of urban spaces for people with mobility impairments. This includes analyzing the ease of navigation for wheelchair users or visually impaired individuals, as well as identifying potential improvements needed for infrastructure, such as better crosswalk design or the addition of ramps.
Augmented Reality (AR) Applications: By recognizing and classifying various street elements, this model can be integrated into AR applications for smartphones or smart glasses aimed at improving navigation, providing context-aware information, or enhancing users' experiences when exploring urban environments. This can include providing directions, highlighting landmarks and points of interest, or even offering interactive and educational content about specific urban features.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

YOLOv8

This project has a YOLOv8 model checkpoint available for inference with Roboflow Deploy. YOLOv8 is a new state-of-the-art real-time object detection model.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            streets-and-crosswalks_dataset,
                            title = { Streets and Crosswalks Dataset },
                            type = { Open Source Dataset },
                            author = { Data Dynamos },
                            howpublished = { \url{ https://universe.roboflow.com/data-dynamos/streets-and-crosswalks } },
                            url = { https://universe.roboflow.com/data-dynamos/streets-and-crosswalks },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2023 },
                            month = { aug },
                            note = { visited on 2024-04-23 },
                            }