shadimsaleh Goto Github PK

tensorflow_recipes

Tensorflow conda recipes

test_cmake

Testing CMake Hallo

tf_files

the-python-mega-course-udemy

A complete python course including basics, databases, flask, data analysis etc. Find the course at

thesis

Master Thesis about Car & Pedestrian Detection

thesis.code

My thesis code from penn

torch-opencv-demos

Torch7+OpenCV+ConvNets

towards-real-time-facial-landmark-detection-in-depth-data-using-auxiliary-information

Modern facial motion capture systems employ a two-pronged approach for capturing and rendering facial motion. Visual data (2D) is used for tracking the facial features and predicting facial expression, whereas Depth (3D) data is used to build a series of expressions on a 3D face models. An issue with modern research approaches is the use of a single data stream that provides little indication of the 3D facial structure. We compare and analyse the performance of Convolutional Neural Networks (CNN) using visual, Depth and merged data to identify facial features in real-time using a Depth sensor. First, we review the facial landmarking algorithms and its datasets for Depth data. We address the limitation of the current datasets by introducing the Kinect One Expression Dataset (KOED). Then, we propose the use of CNNs for the single data stream and merged data streams for facial landmark detection. We contribute to existing work by performing a full evaluation on which streams are the most effective for the field of facial landmarking. Furthermore, we improve upon the existing work by extending neural networks to predict into 3D landmarks in real-time with additional observations on the impact of using 2D landmarks as auxiliary information. We evaluate the performance by using Mean Square Error (MSE) and Mean Average Error (MAE). We observe that the single data stream predicts accurate facial landmarks on Depth data when auxiliary information is used to train the network.

tracking-with-opencv

Source code for the OpenCV tracking tutorial on AI Shack

traffic-sign-detection-homework

nyu-cv-fall-2017 assignment 3

traffic-sign-recognition-and-detection-using-yolo

YOLO is a neural network framework pre-trained on 10,000 objects. In this project we detect and recognize German Traffic Signs using YOLO framework.

trafficlights

iOS app that simulates a set of traffic lights at an intersection.

trafficsignclassification

Traffic Sign Classification with both SVM and Bag of Words model (OpenCV)

tsai-calibration

An implementation of Tsai's camera calibration technique.

tutorials

This is tutorial code how to use OpenCV libraries by Kyle Hounslow

udacity-course

Udacity courses

udacity-intro-to-machine-learning

My solutions to quizzes, exercises, and projects in the Udacity Intro to Machine Learning course

udacity-p3-drivegg

udacity-sdc-radar-driver-micro-challenge

Udacity Self-Driving Car Radar Driver Micro Challenge

udemy_pythonopencvdl

Course Study Repo for Python for Computer Vision with OpenCV and Deep Learning Course

undergraduate-graduation-projects

本科毕业设计。

unknown_object_segmentation

vehicle-plate-recognition

Vehicle plate recognition

vehicle_counting_hog_svm

Vehicle Detection, Tracking and Counting by SVM with HOG Features

vid2depth

This is the separated vid2depth from tensorflow/models, some lines are commented or changed for successfully inference.

video-capture-async

Multithreaded video capture with OpenCV and Python

video2calibration

Camera intrinsic parameters calibration from chessboard video sequence.

video_stream_opencv

A package to open video streams and publish them in ROS using the opencv videocapture mechanism

vision

As of now, OpenCV codes and snippets that I'm working on.

visual-slam-using-stereo-camera-for-autonomous-vehicles

Indoor/Outdoor SLAM using Stereo Vision. This project used ORB_SLAM2 with ZED stereo camera to achieve the task of SLAM and has a custom 2D occupancy grid mapping algorithm using depth.