Our project focuses on developing a traffic sign detection model using the YOLO framework. YOLO is renowned for its real-time object detection capabilities, making it an ideal choice for addressing the dynamic and time-sensitive nature of traffic environments. By training the model on an extensive dataset of annotated traffic sign images, we aim to equip it with the ability to accurately detect and classify traffic signs commonly encountered on roads.
Within this project, we have harnessed the power of YOLO to proficiently detect a diverse set of 10 essential traffic signs.
list of the traffic signs :
1.Stop
2.No pedestrian crossing
3.No parking
4.Parking
5.Give way
6.One way
7.No left turn
8.Speed limit
9.Bus lane
10.Pedestrian crossing
1.Open Google colab in your browser
2.Open the folder containing this folder
3.Run Traffic_sign_detection.ipynb
You can find our meticulously curated dataset in the dedicated "Dataset" folder within this repository. Our dataset boasts a comprehensive collection of 1027 meticulously labeled images for training purposes, alongside an additional 219 images reserved for validation purposes. Each image within the dataset has been carefully and accurately labeled, ensuring that every traffic sign is precisely annotated. This dedication to precision empowers our dataset to serve as a reliable foundation for training and validating our traffic sign detection model. Your engagement with the dataset is integral to contributing to the development of accurate and efficient traffic sign detection capabilities. Should you have any inquiries or require further information about our dataset, please don't hesitate to reach out.
This project was a collaborative effort between Ahmad Asadi and Kiarash Rahmani . We worked together to develop a robust traffic sign detection model using the YOLO framework. Our project leverages YOLO's real-time object detection capabilities to address the dynamic and time-sensitive nature of traffic environments.
This project is licensed under the MIT License.