tooth2 Goto Github PK

followers: 21.0 following: 11.0 repos: 52.0 gists: 0.0

Name: Saeyoung Jeong

Type: User

Company: CMU

Twitter: 08723Mapp

Location: Pittsburgh

Saeyoung Jeong

🔭 I have worked on Computer Vision, Deep learning and Natural Language Processing application development with Python, C++, and JAVA. 🌱 I’m currently working on Autonomous car driving; Vehicle/road lane detection, Lidar/Radar sensor fusion, Localization , Path planning and control so on.

Autonomous Vehicle Projects

Input	Projects	Related
Camera Vision	Perception Lane Detection	Prediction->Behavior Planning->Trajectory Planning
Camera Vision	Perception Traffic Light Detection	Prediction->Behavior Planning
Camera Vision	Perception Traffic Sign Detection	Prediction->Behavior Planning
Camera Vision, Lidar, Radar	Perception Object Detection & Tracking: Lidar/Yolo, SSD, Segmentation	Prediction, Trajectory Planning
Lidar, GPS/Map	Localization:Particle Filter,EKF, UKF,SLAM	Route Planning, Behavior Planning

Machine Learning/Deep Learning/AI

ComputerVision/DeepLearning	CV+DL+NaturalLanguageProcessing	NLP/DeepLearning
Facial Keypoints Detection	Handwritten Digits Generation(GAN)	Sentiment Analysis(RNN)
YOLOv3 Object Detection	Image2Image Translation(CycleGAN)	Spam Detector(Naive Bayesian)
SSD(Single shot detection)	House Number Recognition(DCGAN)	Part-of-Speech Tagger(HMM)
Semantic Image Segmentation	Generating Faces(DCGAN)	TV Script Generation(RNN/LSTM)
Artistic Style Transfer	Image Captioning(CNN-> RNN/LSTM)	Machine Translation(RNN/LSTM)
On-Device AI/CV(private)	Automatic Speech Recognition (private)	On-Device AI/NLP(private)

Reinforcement Learning

Model-free Learning	Model-based learning	DRN (RN+NN)
Monte-Carlo Methods, Temporal-Difference Learning	Value-Iteration, Policy-Iteration	Value-based Methods, Policy-Based Methods, Multi-Agent RL

Teaching Course Examples

Mobile App Development	WebService/ REST API	DataBase/ETL	IoT	ROS/Localization
ObjectiveC, JAVA, Swift, Kotlin	BLE WebService, OpenXC API	RDBMS/ETL, NoSQL/ETL	AlexaSkills, GoogleActions	Robot/ROS, Localization, VehicleModel/Trajectory

Saeyoung Jeong's Projects

1d-localization

1D localization using Bayesian Filter to locate a robot in 1D space and represent uncertainty in robot motion

2d-cfar

2D FFT, Doppler effect and CFAR implementation with matlab

2d-sensor-fusion

Sensor fusion Vehicle Detection by applying Camera(left/right) and Lidar measurements from KITTI data set.

3d-sensor-fusion

Vehicle Tracking using YOLO v3 (image training) and Lidar data

alexa-skill

Alexa Skill -VUI (Voice User Interface)

android-kotlin

Android apps only implemented in kotlin (version >=1.3.7)

artistic-style-transfer

This example projects demonstrate the use of Style Transfer in python, Android and etc.

automatic-image-captioning

A Pytorch implementation of the CNN+RNN architecture on the MS-COCO dataset

autonomous_driving

Autonomous Driving using deep learning to train a deep neural network (CNN+) to drive a vehicle in the simulator in the same way of driving a car in manual mode. Applied "NVIDIA end-to-end deep learning for self-driving cars" architecture.

beaconlocationservice

Using Beacon, this web service provides CMU beacon's fine/coarse grained location database.

celeb-face-generation

A PyTorch Implementation of DCGAN on a dataset of celebrity faces.

charityml

Finding Donors for CharityML

chatbot

A Chatbot implementation. This chatbot answers questions about C++ knowledge! This project is to use modern C++ memory management techniques such as smart pointers and move semantics.

dm-nosql-etl

data modeling for music streaming service

dm-rdbms-etl

ETL-Data modeling for music streaming service

extended-kalman-filter

Extended Kalman Filter implementation to estimate a moving object with Lidar and Radar sensor measurements. With sensor_fusion data, Extended Kalman filters predict and determine with certainty the location of other vehicles on the road.

facial-keypoints-detection

Use image processing techniques and deep learning techniques to detect faces in an image and find facial keypoints, such as the position of the eyes, nose, and mouth on a face.

flowerclassifier

Flower image Classifier

googleactions

Course Example for Google Actions(Voice User Interface)

handwritten-digits-generation

a PyTorch implementation - handwriting number recognition with GAN model using MNIST Dataset

house-number-recognition

Using DCGAN, detect and recognize house number from google street view

idrift_android

iDrift: Drifting log application for Android devices

idrift_ios

iDrift: Drifting log application for iOS devices

image2image-translation

A PyTorch implementation using CycleGAN architecture, to read in an image from a set X and transform it so that it looks as if it belongs in set Y .

landmark-detection-tracking-slam

SLAM (Simultaneous Localization and Mapping) implementation for a 2D world

lidar-obstacle-detection

Lidar Obstacle Detection - Filter(Voxel-Grid filter and Cropping), segment(3D Ransac algorithm), and cluster (3D kd-tree and euclidean clustering) real point cloud data to detect obstacles in a driving environment.

machine-translation

A deep neural network that functions as part of an end-to-end machine translation pipeline.

montecarlomethods

A python implementation - Monte Carlo Methods

nlp-spam-detector

spam detector on text messages dataset

partofspeechtagging

Part of Speech Tagging Use several techniques, including table lookups, n-grams, and hidden Markov models, to tag parts of speech in sentences, and compare their performance.