Cognitive Surveillance system -- detect any malicious activity (when person is looking away from camera) and alert though warning popups and email notifications (to the concerned authority)

Head pose estimation based FSA-NET & Emotion recognition based VGG-Net

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Attention Indexing Computer Vision POC for ripplecreate

Deep Learning Head Pose Estimation using PyTorch

The application uses gaze detection points with the use of deep learning model to estimate the gaze of user's eyes to move the mouse pointer position.

Pyramid-based structure for head pose estimation

This is a code based on Ruiz's HopeNet, a head pose estimation work which is originally written as PyTorch. However, I try writing and modifying the code to run on Apple's MLX library.

🔥🔥 Deep Learning Head Pose Estimation using PyTorch.

Python-based 6D headpose estimation for video editing (Re-implementation for educational purposes)

[CVPR19] FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image

Head Pose Estimation with RealSense Camera

It controls the computer's mouse pointer with eye gaze. We have used 4 pre-trained model that is provided by Open Model Zoo. The project's main aim is to check the usage of OpenVino ToolKit on different hardware which includes openvino inference API, OpenVino WorkBench, and VTune Profiler.

OneStopVision is an open-source toolkit offering a comprehensive suite of algorithms for face and body analysis, landmark extraction, and ControlNet integration in Stable Diffusion.

Smart Classroom SUTD UROP 2020

Computer Pointer Controller app used for controlling the mouse pointer by using eye and head position.

Engagement Analysis with Head Pose Estimation is a computer vision project that utilizes Mediapipe library for facial landmarks detection, OpenCV for computer vision tasks, and NumPy/Pandas for data manipulation. It estimates head pose and gaze direction to determine whether the user is engaged or not.