Traffic signs detection and classification in real time

capsule networks that achieves outstanding performance on the German traffic sign dataset

Türkiye Trafik İşaretleri Veriseti - Turkish Traffic Sign Dataset

Identifying traffic signs in real time using YOLO for autonomous self driving car

This project is part of the CS course 'Systems Engineering Meets Life Sciences I' at Goethe University Frankfurt. In this Computer Vision project, we present our first attempt at tackling the problem of traffic sign recognition using a systems engineering approach.

A Deep Neural Network to do traffic sign recognition

the project includes system design of a t intersection traffic light controller and its verilog code in vivado design suite.

Code for the paper entitled "Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods".

Repository for TSR-SA

This repository contains my upgraded version of using YoloV4 with OpenCV DNN to detect 4 classes of traffic road signs : traffic lights, speed limit signs, crosswalk and stop signs.

A deep learning model has been developed especially for self-driving cars like Tesla, which uses complete automatic support to drive the vehicle to recognizes traffic signs and follow them properly

In this project, a traffic sign recognition system, divided into two parts, is presented. The first part is based on classical image processing techniques, for traffic signs extraction out of a video, whereas the second part is based on machine learning, more explicitly, convolutional neural networks, for image labeling.

A traffic sign classifier built with TensorFlow

To ease the driver to identify the Traffic Signs and also for the efficient working of Self-Driving Cars.

Recognize traffic sign using Histogram of Oriented Gradients (HOG) and Colorspace based features. Support Vector Machines (SVM) is used for classifying images.

Objects recognition and classification using machine learning, computer vision and real-time object detection algorithm

Workflow for Executing CNN Networks on Zynq Ultrascale+ with VITIS AI. Detailed analysis, configuration, and execution of Convolutional Neural Networks on ZCU102 using VITIS AI, evaluating performance on the board compared to Cloud infrastructure. Developed for educational exam purposes.

Synthetic traffic sign detectron