Classifying Objects as New or Learned with Convolutional Networks and SGD By Kevin Xiong and Evan Phibbs Mentored by Yufei Wang.

Slides:



Advertisements
Similar presentations
Road-Sign Detection and Recognition Based on Support Vector Machines Saturnino, Sergio et al. Yunjia Man ECG 782 Dr. Brendan.
Advertisements

Navneet Goyal, BITS-Pilani Perceptrons. Labeled data is called Linearly Separable Data (LSD) if there is a linear decision boundary separating the classes.
Support Vector Machines
CSCI 347 / CS 4206: Data Mining Module 07: Implementations Topic 03: Linear Models.
Designing Facial Animation For Speaking Persian Language Hadi Rahimzadeh June 2005.
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Classification Neural Networks 1
Properties of Machine Learning Applications for Use in Metamorphic Testing Chris Murphy, Gail Kaiser, Lifeng Hu, Leon Wu Columbia University.
A neural approach to extract foreground from human movement images S.Conforto, M.Schmid, A.Neri, T.D’Alessio Compute Method and Programs in Biomedicine.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Real-Time Face Detection and Tracking Using Multiple Cameras RIT Computer Engineering Senior Design Project John RuppertJustin HnatowJared Holsopple This.
Knowledge Systems Lab JN 8/24/2015 A Method for Temporal Hand Gesture Recognition Joshua R. New Knowledge Systems Laboratory Jacksonville State University.
West Virginia University
Presented by: Kamakhaya Argulewar Guided by: Prof. Shweta V. Jain
Image Recognition using Hierarchical Temporal Memory Radoslav Škoviera Ústav merania SAV Fakulta matematiky, fyziky a informatiky UK.
Human Gesture Recognition Using Kinect Camera Presented by Carolina Vettorazzo and Diego Santo Orasa Patsadu, Chakarida Nukoolkit and Bunthit Watanapa.
A Method for Hand Gesture Recognition Jaya Shukla Department of Computer Science Shiv Nadar University Gautam Budh Nagar, India Ashutosh Dwivedi.
The Perceptron. Perceptron Pattern Classification One of the purposes that neural networks are used for is pattern classification. Once the neural network.
Human Action Recognition from RGB-D Videos Oliver MacNeely YSP 2015.
By: Jared Meyer A Neural Network Approach to Classifying Cartoons Based on Color ECE 539 Final Project.
Non-Bayes classifiers. Linear discriminants, neural networks.
Figure ground segregation in video via averaging and color distribution Introduction to Computational and Biological Vision 2013 Dror Zenati.
Neural Text Categorizer for Exclusive Text Categorization Journal of Information Processing Systems, Vol.4, No.2, June 2008 Taeho Jo* 報告者 : 林昱志.
CSSE463: Image Recognition Day 14 Lab due Weds, 3:25. Lab due Weds, 3:25. My solutions assume that you don't threshold the shapes.ppt image. My solutions.
Vehicle Detection in Aerial Surveillance Using Dynamic Bayesian Networks Hsu-Yung Cheng, Member, IEEE, Chih-Chia Weng, and Yi-Ying Chen IEEE TRANSACTIONS.
Support-Vector Networks C Cortes and V Vapnik (Tue) Computational Models of Intelligence Joon Shik Kim.
Machine Learning: A Brief Introduction Fu Chang Institute of Information Science Academia Sinica ext. 1819
Object Recognition Tutorial Beatrice van Eden - Part time PhD Student at the University of the Witwatersrand. - Fulltime employee of the Council for Scientific.
Neural Networks Lecture 11: Learning in recurrent networks Geoffrey Hinton.
1 An introduction to support vector machine (SVM) Advisor : Dr.Hsu Graduate : Ching –Wen Hong.
SUPPORT VECTOR MACHINES Presented by: Naman Fatehpuria Sumana Venkatesh.
Rich feature hierarchies for accurate object detection and semantic segmentation 2014 IEEE Conference on Computer Vision and Pattern Recognition Ross Girshick,
Feasibility of Using Machine Learning Algorithms to Determine Future Price Points of Stocks By: Alexander Dumont.
Lecture 4b Data augmentation for CNN training
Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces Speaker: Po-Kai Shen Advisor: Tsai-Rong Chang Date: 2010/6/14.
Leaves Recognition By Zakir Mohammed Indiana State University Computer Science.
Facial Detection via Convolutional Neural Network Nathan Schneider.
Big data classification using neural network
3D Puppetry: A Kinect-based Interface for 3D Animation
Demo.
DeepCount Mark Lenson.
Jure Zbontar, Yann LeCun
Basic machine learning background with Python scikit-learn
Neural networks (3) Regularization Autoencoder
Lecture 5 Smaller Network: CNN
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Presenter: Hajar Emami
Calculate HOC on Depth and HOG on RGB and concatenate them
Classification Neural Networks 1
Counting in Dense Crowds using Deep Learning
RGB-D Image for Scene Recognition by Jiaqi Guo
Deep Learning Hierarchical Representations for Image Steganalysis
Introduction to Deep Learning with Keras
Smart Robots, Drones, IoT
network of simple neuron-like computing elements
CSC 578 Neural Networks and Deep Learning
[Figure taken from googleblog
Creating Data Representations
Image Classification Painting and handwriting identification
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
Image Compression Using An Adaptation of the ART Algorithm
Other Classification Models: Support Vector Machine (SVM)
A Novel Smoke Detection Method Using Support Vector Machine
CSC321: Neural Networks Lecture 11: Learning in recurrent networks
CIS 519 Recitation 11/15/18.
CSC 578 Neural Networks and Deep Learning
Sign Language Recognition With Unsupervised Feature Learning
Presentation transcript:

Classifying Objects as New or Learned with Convolutional Networks and SGD By Kevin Xiong and Evan Phibbs Mentored by Yufei Wang

Introduction The turtlebot runs on Robotic Operating System (ROS). ROS allows us to interface with the turtlebot’s motors and Xbox kinect’s camera and depth data.

Goal Our goal was for the turtlebot to be placed anywhere in the room, move around the room to find objects around it, recognize each object as known or new and learn the object if it was new, as an attempt in open-ended learning.

Libraries We wrote our program entirely in python using two libraries: Caffe: A convolutional neural network library Sklearn: a general-purpose machine learning library, which includes a linear svm

Methods The robot captures depth data and rgb data from the turtlebot’s kinect. a binary mask is created from the depth data such that each 1 corresponds to an object pixel and each 0 to a background pixel in order to reduce the effect of the background on classification rgb data is multiplied by the mask and set as input into the CNN

Methods (continued) The convolutional network’s last hidden layer activations are used as input into an svm classifier The distances to the separating hyperplanes of each input into the svm are used as inputs into another svm classifier to determine whether an object is new or known.

Methods (continued) rgb depth mask rgb mask linear svm classifie r clas s decision_function method (distance to each hyperplane) new or old linear svm classifie r eighth layer activations (4096d vector) output Caffe convolutional network

Hurdles We encountered many limitations while using the turtlebot The turtlebot’s movements are not accurate The turtlebot can only rotate, move forward, or move backward. Kinect has very noisy depth data and is not aligned with camera rgb data

Results We tested on 4 types of tea, 2 types of cubes, a bottle, magic eight ball, and a stuffed animal cat.

Video Demonstration

Improvements Our program could be improved with the following: a more robust way of circling the objects an algorithm for moving about a room to ensure no objects are left undiscovered Combining depth data and object partitioning algorithms in order to create a finer, more accurate mask

Improvements (continued) relying solely on object partitioning in order to recognize known objects and remove them from the scene, leaving only new objects to be focused on and trained using an object mask such that background pixels are set to random color noise