A Software-in-the-Loop simulator for a lane keeping assist system (LKAS) using V-REP to validate the LKAS controller and the lane detection algorithm.

Search-based software testing of a pedestrian detection system using ESI Pro-SiVIC

ADAS app, for driving safty .YOLOX tiny + lane detection on Android with 15 FPS!

Driver Monitoring System by using deep learning model Gaze, Face detection, Face Landmark, and Head pose estimation.

Thermal imaging is crucial in Advanced driver assistance systems(ADAS) and medical field. Head tracking alongwith body gives an advantage of ability to predict the heading direction.

ADAS Car - with Collision Avoidance System (CAS) - on Indian Roads using LIDAR-Camera Low-Level Sensor Fusion. DIY Gadget built with Raspberry Pi, RP LIDAR A1, Pi Cam V2, LED SHIM, NCS 2 and accessories like speaker, power bank etc

This repository contains the final project work for Autonomous Driving Technologies class. Robust lane detection, Stanley control for steering, UDP communication between 2 systems, and traffic sign detectors form an autonomous navigation system.

A Software-in-the-Loop simulator for lane keeping assist system (LKAS) using Matlab and VREP.

This is an implementation of an adaptive cruise control system based on a computer vision pipeline. This work is based on YOLACT, a State-Of-The-Art real-time instance segmentation network. You're welcome to test and try our code, we hope you'll enjoy this work!

This repository contains all the project submissions for Self-Driving Car Nanodegree

OPEN ADAS Lane detection system v1. Implements OpenCV. non learning platforms. Average accuracy and latency.

Detecting various irregularities in road surfaces using images which can be integrated with an ADAS based vehicular navigation system to provide assistance while driving.

This is my bachelor's thesis, which contains three main features: lane detection, road segmentation, and a Forward Collision Warning (FCW) system

FIR-based trajectory prediction at nighttime

A Autonomous vehicle created using Raspberry and Arduino.

The project is based on deep learning which detects the lane in road and suggest the user/EMI of car to drive as per the lane presence.

Designed and built a prototype of a vehicle that provides a predictive model with maximum accuracy by using TensorFlow as part of an unsupervised machine learning algorithm along with that ADAS feature is used based on input factors like driver’s fatigue, speed, and distance between two vehicles.

A real-time lane detection system applied computer vision techniques and deep learning.