ndrplz/dreyeve
[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.
A multi-branch convolutional architecture combining optical flow and semantic segmentation streams with Keras/Theano to predict driver gaze locations from dashcam video. The repository includes the full experimental pipeline—gaze acquisition via Tobii EyeX integration, semantic segmentation preprocessing, and baseline implementations—with pre-trained weights available for the multi-branch model.
113 stars. No commits in the last 6 months.
Stars
113
Forks
36
Language
C
License
MIT
Category
Last pushed
Sep 03, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ndrplz/dreyeve"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
ykotseruba/attention_and_driving
A curated list of peer-reviewed papers on theoretical and practical aspects of drivers'...
ciglenecki/eeg-driver-fatigue-detection
🧠 + 🚗 Driver fatigue detection through multiple entropy fusion analysis in an EEG-based system
Pratham-mehta/Real-time-Driver-Drowsiness-Detection-System-Using-Deep-Learning
CS-GY 6953 Deep Learning Major Project
ivineetm007/drunk-detection
This repository contains the source code for the paper Dataset of Perceived Intoxicated Faces...
Akarshjha03/IndraNav-Adaptive-Driving-System
Indranav is a real-time computer vision–powered web application built with FastAPI and React,...