Cell Tracking via Proposal Generation & Selection

Size: px
Start display at page:

Download "Cell Tracking via Proposal Generation & Selection"

Transcription

1 Cell Tracking via Proposal Generation & Selection Saad Ullah Akram, Juho Kannala, Lauri Eklund and Janne Heikkilä 2

2 Overview Introduction Importance Challenges: detection & tracking Current state of cell tracking field Our method Cell proposal generation (CPN) Proposal graph Cell tracking via proposal selection Summary

3 Overview Introduction Importance Challenges: detection & tracking Current state of cell tracking field 4

4 Cell Tracking Process of: Locating a moving cell over time & Detecting cellular events (division, death, entry, exit) : highlights links between parent & daughter cells Time Lineage of a cell saad.akram@oulu.fi 5

5 Applications Understanding dynamic cellular behavior Spread of diseases (e.g. cancer) Effectiveness/safety of a drug Organ/embryo development Gene profiling saad.akram@oulu.fi 6

6 Automation Huge datasets 1,000s of D images/day 10,000s cells in each image > 10 TBs of image data/day Subtle patterns Accurate/objective/repeatable Video from: F. Amat et al., Fast, accurate reconstruction of cell lineages from large-scale fluorescence microscopy data., Nat. Methods, saad.akram@oulu.fi 7

7 Challenges: Tracking Difficult to model motion Similar cell appearances and shapes Similar shapes & appearances 8

8 Challenges: Tracking Low frame rate Large movements Large shape and appearance changes Large movement Difficult to detect cell division Parent cells in last frame before division 9

9 DIC Microscopy Phase Contrast Bright Field Challenges: Detection Detection failures account for most tracking errors Large variation in cell shapes & appearances Microscopy modality Labeled structure Resolution Cell density Fluorescence Dyes & Proteins Image from: E. Meijering, Cell Segmentation: 50 Years Down the Road, IEEE Signal Process. Mag.,

10 Current cell tracking methods Tracking by detection Detect cells in each frame Associate detections in nearby frames + Low frame rate/resolution Simple and modular Pros Tracking by model evolution Detect cells in 1 st frame and represent it using some model Segment current frame using the model from last frame Pros + Can handle noisy images ImageJ (TrackMate, MTrack2), CellProfiler (TrackObjects), etc saad.akram@oulu.fi 11

11 Limitations of current cell tracking methods Cell detection methods assume Cell appearances High intensity near the center Characteristic intensity profile at cell boundaries Cell shapes Round or elliptical shapes Cell size within some narrow range Assumptions are often not satisfied for new sequences Lack robustness Require tuning multiple parameters 12

12 Overview Our method Cell proposal generation (CPN) Proposal graph Cell tracking via proposal selection 1

13 Tracking by proposal selection 1. Generate cell proposals Use CNNs to learn the cell shapes and appearances 2. Link cell proposals using edges (represent cellular events). Select subset of cell proposals & their associations (provides cell tracks) 14

14 Cell proposals/candidates Cell detection can benefit from Temporal information Machine learning to decide what a cell looks like A cell proposal is a candidate segmentation of a cell Enables representation of multiple segmentation hypothesis in ambiguous regions Image Cell Detection Cell Proposals: 2 Cell Proposals: Cell Proposals: 4 saad.akram@oulu.fi 15

15 ROIPooling bbox score Candidate Bounding Boxes Cell proposal network (CPN) Bounding box network Segmentation network k 2k Nx k NMS NMS Proposals saad.akram@oulu.fi 16 1 NMS Proposal Masks Fig: CPN: Convolutional, max-pooling, fully connected, and deconvolutional layers are shown. Proposed bounding boxes and segmentation masks after non-maxima suppression (NMS) are shown for a selected area from Fluo-N2DL-HeLa dataset.

16 Time Tracking graph (g): Ground truth Cell tracks can be represented using a graph S Nodes represent cells D 1 Special nodes (S & T): Initiate/terminate cell lineage trees D 2 D Edges represent cell events Cell entering field of view Cell exiting field of view Cell division (mitosis) Cell moving a) D 4 T D 5 b) saad.akram@oulu.fi 17

17 Time Graphical model (G) A graphical model (G) is used to reason about which cell tracks should be selected Nodes represent cell proposal probabilities Black edges represent proposal constraints Special nodes (S & T): Initiate/terminate cell lineage tress Only few edges of each type are shown to avoid clutter Edge weights represent cellular event probabilities Cell entering field of view Cell exiting field of view Mitosis Cell moving a) S T b) saad.akram@oulu.fi 18

18 Time Proposal selection Each sub-graph of our model (G) represents a tracking hypothesis Optimal tracks can be obtained by finding the sub-graph with the highest probability S a) 0.07 T 0.0 b) c) saad.akram@oulu.fi 19

19 Results Same model structure is used for all datasets 4 datasets from ISBI Cell Tracking Challenge [1] TRA: Tracking score (0-1 (perfect)) penalizes errors in the tracks SEG: Segmentation score Instance level intersection over union overlap. Video [1] Method TRA SEG CPN Fluo-N2DL-HeLa-02 EPFL [] 0.97 KTH [4] CPN Fluo-N2DH-GOWT1-02 HEID [2] 0.95 EPFL [] 0.95 PhC-C2DH-U7-02 CPN U-Net [5] PhC-C2DL-PSC-01 CPN [1] M. Maška et al., A Benchmark for Comparison of Cell Tracking Algorithms, Bioinformatics, [2] M. Schiegg, et al., Graphical Model for Joint Segmentation and Tracking of Multiple Dividing Cells, Bioinformatics, [] E. Turetken, et al., Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences, in T-MI, [4] K. E. G. Magnusson, et al., A Batch Algorithm using Iterative Application of the Viterbi Algorithm to Track Cells and Construct Cell Lineages, in ISBI, [5] O. Ronneberger, et al., U-Net: Convolutional Networks for Biomedical Image Segmentation, in MICCAI, saad.akram@oulu.fi 20

20 Time Fluo-N2DL-HeLa-02 21

21 Time PhC-C2DH-U

22 Time PhC-C2DL-PSC-01 2

23 Overview Summary 24

24 Summary + (Potentially) can be applied to other sequences Has better performance than existing methods Requires annotated data Our tracking method More Information: Paper: Code: saad.akram@oulu.fi 25

25 Thanks. Questions? 26

Cell Tracking via Proposal Generation and Selection

Cell Tracking via Proposal Generation and Selection V1.01 1 Cell Tracking via Proposal Generation and Selection Saad Ullah Akram, Juho Kannala, Lauri Eklund, and Janne Heikkilä arxiv:1705.03386v1 [cs.cv] 9 May 2017 Abstract Microscopy imaging plays a vital

More information

Cell Segmentation Proposal Network For Microscopy Image Analysis

Cell Segmentation Proposal Network For Microscopy Image Analysis Cell Segmentation Proposal Network For Microscopy Image Analysis Saad Ullah Akram 1,2, Juho Kannala 3, Lauri Eklund 2,4, and Janne Heikkilä 1 1 Center for Machine Vision and Signal Analysis, 2 Biocenter

More information

JOINT CELL SEGMENTATION AND TRACKING USING CELL PROPOSALS

JOINT CELL SEGMENTATION AND TRACKING USING CELL PROPOSALS JOINT CELL SEGMENTATION AND TRACKING USING CELL PROPOSALS Saad Ullah Akram 1,2, Juho Kannala 3, Lauri Eklund 2,4, and Janne Heikkilä 1 1 Center for Machine Vision Research, 2 Biocenter Oulu, 4 Oulu Center

More information

Cell Segmentation and Tracking in Phase Contrast Images using Graph Cut with Asymmetric Boundary Costs

Cell Segmentation and Tracking in Phase Contrast Images using Graph Cut with Asymmetric Boundary Costs Cell Segmentation and Tracking in Phase Contrast Images using Graph Cut with Asymmetric Boundary Costs Robert Bensch and Olaf Ronneberger Computer Science Department and BIOSS Centre for Biological Signalling

More information

IMPROVING THE ROBUSTNESS OF CONVOLUTIONAL NETWORKS TO APPEARANCE VARIABILITY IN BIOMEDICAL IMAGES

IMPROVING THE ROBUSTNESS OF CONVOLUTIONAL NETWORKS TO APPEARANCE VARIABILITY IN BIOMEDICAL IMAGES 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) April 4-7, 2018, Washington, D.C., USA IMPROVING THE ROBUSTNESS OF CONVOLUTIONAL NETWORKS TO APPEARANCE VARIABILITY IN BIOMEDICAL

More information

Cell Lineage Tracing in Lens-free Microscopy Videos

Cell Lineage Tracing in Lens-free Microscopy Videos Cell Lineage Tracing in Lens-free Microscopy Videos Markus Rempfler 1,2, Sanjeev Kumar 2, Valentin Stierle 3, Philipp Paulitschke 3, Bjoern Andres 4, and Bjoern H. Menze 1,2 1 Institute for Advanced Study,

More information

A Model Based Neuron Detection Approach Using Sparse Location Priors

A Model Based Neuron Detection Approach Using Sparse Location Priors A Model Based Neuron Detection Approach Using Sparse Location Priors Electronic Imaging, Burlingame, CA 30 th January 2017 Soumendu Majee 1 Dong Hye Ye 1 Gregery T. Buzzard 2 Charles A. Bouman 1 1 Department

More information

An objective comparison of cell-tracking algorithms

An objective comparison of cell-tracking algorithms An objective comparison of cell-tracking algorithms Vladimír Ulman 1,24,25, Martin Maška 1,25, Klas E G Magnusson 2, Olaf Ronneberger 3,24, Carsten Haubold 4, Nathalie Harder 5,24, Pavel Matula 1, Petr

More information

RELIABLE CELL TRACKING BY GLOBAL DATA ASSOCIATION. Ryoma Bise, Zhaozheng Yin, and Takeo Kanade. Carnegie Mellon University, Pittsburgh, PA, USA.

RELIABLE CELL TRACKING BY GLOBAL DATA ASSOCIATION. Ryoma Bise, Zhaozheng Yin, and Takeo Kanade. Carnegie Mellon University, Pittsburgh, PA, USA. RELIABLE CELL TRACKING BY GLOBAL DATA ASSOCIATION Ryoma Bise, Zhaozheng Yin, and Takeo Kanade Carnegie Mellon University, Pittsburgh, PA, USA. ABSTRACT Automated cell tracking in populations is important

More information

Analysis of High-throughput Microscopy Videos: Catching Up with Cell Dynamics

Analysis of High-throughput Microscopy Videos: Catching Up with Cell Dynamics Analysis of High-throughput Microscopy Videos: Catching Up with Cell Dynamics Paper ID #159 Anonymous Abstract. We present a novel framework for high-throughput cell lineage analysis in time-lapse microscopy

More information

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation Object detection using Region Proposals (RCNN) Ernest Cheung COMP790-125 Presentation 1 2 Problem to solve Object detection Input: Image Output: Bounding box of the object 3 Object detection using CNN

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha

More information

Chapter 3. Automated Segmentation of the First Mitotic Spindle in Differential Interference Contrast Microcopy Images of C.

Chapter 3. Automated Segmentation of the First Mitotic Spindle in Differential Interference Contrast Microcopy Images of C. Chapter 3 Automated Segmentation of the First Mitotic Spindle in Differential Interference Contrast Microcopy Images of C. elegans Embryos Abstract Differential interference contrast (DIC) microscopy is

More information

A web interface for the quantification of microtubule dynamics

A web interface for the quantification of microtubule dynamics A web interface for the quantification of microtubule dynamics Koon Yin Kong, Georgia Institute of Technology Adam Marcus, Emory University Paraskevi Giaanakakou, Emory University May D. Wang, Georgia

More information

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun Presented by Tushar Bansal Objective 1. Get bounding box for all objects

More information

FiloQuant manual V1.0 Table of Contents

FiloQuant manual V1.0 Table of Contents FiloQuant manual V1.0 Table of Contents 1) FiloQuant aims and distribution license...2 2) Installation...3 3) FiloQuant, step-by-step instructions (single images)...4 1: Choose the region of interest to

More information

RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES. Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA

RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES. Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA RESTORING ARTIFACT-FREE MICROSCOPY IMAGE SEQUENCES Zhaozheng Yin Takeo Kanade Robotics Institute Carnegie Mellon University 5000 Forbes Ave, Pittsburgh, PA 15213, USA ABSTRACT Phase contrast and differential

More information

Cell Image Analysis: Algorithms, System and Applications

Cell Image Analysis: Algorithms, System and Applications Cell Image Analysis: Algorithms, System and Applications Takeo Kanade 1, Zhaozheng Yin 1, Ryoma Bise 1, Seungil Huh 1, Sungeun Eom 1, Michael F. Sandbothe 1 and Mei Chen 2 1 Carnegie Mellon University,

More information

Tracking of Virus Particles in Time-Lapse Fluorescence Microscopy Image Sequences

Tracking of Virus Particles in Time-Lapse Fluorescence Microscopy Image Sequences Tracking of Virus Particles in Time-Lapse Fluorescence Microscopy Image Sequences W. J. Godinez 1, M. Lampe 2, S. Wörz 1, B. Müller 2, R. Eils 1 and K. Rohr 1 1 University of Heidelberg, IPMB, and DKFZ

More information

MICROTUBULE FILAMENT TRACING AND ESTIMATION. Rohan Chabukswar. Department of Electrical and Computer Engineering Carnegie Mellon University

MICROTUBULE FILAMENT TRACING AND ESTIMATION. Rohan Chabukswar. Department of Electrical and Computer Engineering Carnegie Mellon University MICROTUBULE FILAMENT TRACING AND ESTIMATION Rohan Chabukswar Department of Electrical and Computer Engineering Carnegie Mellon University ABSTRACT The project explores preprocessing of images to facilitate

More information

Object Detection on Self-Driving Cars in China. Lingyun Li

Object Detection on Self-Driving Cars in China. Lingyun Li Object Detection on Self-Driving Cars in China Lingyun Li Introduction Motivation: Perception is the key of self-driving cars Data set: 10000 images with annotation 2000 images without annotation (not

More information

Fast and accurate automated cell boundary determination for fluorescence microscopy

Fast and accurate automated cell boundary determination for fluorescence microscopy Fast and accurate automated cell boundary determination for fluorescence microscopy Stephen Hugo Arce, Pei-Hsun Wu &, and Yiider Tseng Department of Chemical Engineering, University of Florida and National

More information

BioImaging facility update: from multi-photon in vivo imaging to highcontent high-throughput image-based screening. Alex Laude The BioImaging Unit

BioImaging facility update: from multi-photon in vivo imaging to highcontent high-throughput image-based screening. Alex Laude The BioImaging Unit BioImaging facility update: from multi-photon in vivo imaging to highcontent high-throughput image-based screening Alex Laude The BioImaging Unit Multi-dimensional, multi-modal imaging at the sub-cellular

More information

Multi-channel Deep Transfer Learning for Nuclei Segmentation in Glioblastoma Cell Tissue Images

Multi-channel Deep Transfer Learning for Nuclei Segmentation in Glioblastoma Cell Tissue Images Multi-channel Deep Transfer Learning for Nuclei Segmentation in Glioblastoma Cell Tissue Images Thomas Wollmann 1, Julia Ivanova 1, Manuel Gunkel 2, Inn Chung 3, Holger Erfle 2, Karsten Rippe 3, Karl Rohr

More information

A Three-color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking

A Three-color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking A Three-color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking Jierong Cheng, Wei Xiong, Ying Gu, Shue-Ching Chia, Yue Wang, and Joo-Hwee Lim Institute for Infocomm

More information

Cell Detection with Star-convex Polygons

Cell Detection with Star-convex Polygons Cell Detection with Star-convex Polygons Uwe Schmidt 1,, Martin Weigert 1,, Coleman Broaddus 1, and Gene Myers 1,2 1 Max Planck Institute of Molecular Cell Biology and Genetics, Dresden, Germany Center

More information

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Shaoqing Ren Kaiming He Ross Girshick Jian Sun Present by: Yixin Yang Mingdong Wang 1 Object Detection 2 1 Applications Basic

More information

Segmentation and descriptors for cellular immunofluoresence images

Segmentation and descriptors for cellular immunofluoresence images Christopher Probert cprobert@stanford.edu CS231A Project Report Segmentation and descriptors for cellular immunofluoresence images 1: Introduction Figure 1: Example immunoflouresence images of human cancer

More information

Restoring the Invisible Details in Differential Interference Contrast Microscopy Images

Restoring the Invisible Details in Differential Interference Contrast Microscopy Images Restoring the Invisible Details in Differential Interference Contrast Microscopy Images Wenchao Jiang and Zhaozheng Yin Department of Computer Science, Missouri University of Science and Technology, wjm84@mst.edu,

More information

Deconvolution Networks

Deconvolution Networks Deconvolution Networks Johan Brynolfsson Mathematical Statistics Centre for Mathematical Sciences Lund University December 6th 2016 1 / 27 Deconvolution Neural Networks 2 / 27 Image Deconvolution True

More information

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs Supplementary Material Peak memory usage, GB 10 1 0.1 0.01 OGN Quadratic Dense Cubic Iteration time, s 10

More information

An Objective Comparison of Cell Tracking Algorithms

An Objective Comparison of Cell Tracking Algorithms An Objective Comparison of Cell Tracking Algorithms Vladimír Ulman 1 **, Martin Maška 1**, Klas E. G. Magnusson 2, Olaf Ronneberger 3, Carsten Haubold 4, Nathalie Harder 5, Pavel Matula 1, Petr Matula

More information

LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015

LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015 LEARNING TO SEGMENT MOVING OBJECTS IN VIDEOS FRAGKIADAKI ET AL. 2015 Darshan Thaker Oct 4, 2017 Problem Statement Moving object segmentation in videos Applications: security tracking, pedestrian detection,

More information

DEFECT INSPECTION FROM SCRATCH TO PRODUCTION. Andrew Liu, Ryan Shen Deep Learning Solution Architect

DEFECT INSPECTION FROM SCRATCH TO PRODUCTION. Andrew Liu, Ryan Shen Deep Learning Solution Architect DEFECT INSPECTION FROM SCRATCH TO PRODUCTION Andrew Liu, Ryan Shen Deep Learning Solution Architect Defect Inspection and its challenges AGENDA NGC Docker images Model set up - Unet Data preparation -

More information

Fully Unsupervised Symmetry-Based Mitosis Detection in Time-Lapse Cell Microscopy

Fully Unsupervised Symmetry-Based Mitosis Detection in Time-Lapse Cell Microscopy Bioimage informatics Fully Unsupervised Symmetry-Based Mitosis Detection in Time-Lapse Cell Microscopy Topaz Gilad 1, Jose Reyes 2, Jia-Yun Chen 2, Galit Lahav 2 and Tammy Riklin Raviv 1, 1 Department

More information

Review: Identification of cell types from single-cell transcriptom. method

Review: Identification of cell types from single-cell transcriptom. method Review: Identification of cell types from single-cell transcriptomes using a novel clustering method University of North Carolina at Charlotte October 12, 2015 Brief overview Identify clusters by merging

More information

Image Segmentation. Shengnan Wang

Image Segmentation. Shengnan Wang Image Segmentation Shengnan Wang shengnan@cs.wisc.edu Contents I. Introduction to Segmentation II. Mean Shift Theory 1. What is Mean Shift? 2. Density Estimation Methods 3. Deriving the Mean Shift 4. Mean

More information

Deformable Part Models

Deformable Part Models CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones

More information

JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA

JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS. Zhao Chen Machine Learning Intern, NVIDIA JOINT DETECTION AND SEGMENTATION WITH DEEP HIERARCHICAL NETWORKS Zhao Chen Machine Learning Intern, NVIDIA ABOUT ME 5th year PhD student in physics @ Stanford by day, deep learning computer vision scientist

More information

Floor Plan Optimization through Evolutionary Simulation

Floor Plan Optimization through Evolutionary Simulation Floor Plan Optimization through Evolutionary Simulation Stephen Holman, Kevin Kerr, Nicholas Perseo Background: Evolutionary computation (EC) is an umbrella term for a range of problem-solving techniques

More information

CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep

CS395T paper review. Indoor Segmentation and Support Inference from RGBD Images. Chao Jia Sep CS395T paper review Indoor Segmentation and Support Inference from RGBD Images Chao Jia Sep 28 2012 Introduction What do we want -- Indoor scene parsing Segmentation and labeling Support relationships

More information

arxiv: v1 [cs.cv] 31 Mar 2016

arxiv: v1 [cs.cv] 31 Mar 2016 Object Boundary Guided Semantic Segmentation Qin Huang, Chunyang Xia, Wenchao Zheng, Yuhang Song, Hao Xu and C.-C. Jay Kuo arxiv:1603.09742v1 [cs.cv] 31 Mar 2016 University of Southern California Abstract.

More information

Cellular Image Segmentation using N-agent Cooperative Game Theory

Cellular Image Segmentation using N-agent Cooperative Game Theory Cellular Image Segmentation using N-agent Cooperative Game Theory by Ian B. Dimock A research paper presented to the University of Waterloo in partial fulfillment of the requirement for the degree of Master

More information

Lecture 7: Semantic Segmentation

Lecture 7: Semantic Segmentation Semantic Segmentation CSED703R: Deep Learning for Visual Recognition (207F) Segmenting images based on its semantic notion Lecture 7: Semantic Segmentation Bohyung Han Computer Vision Lab. bhhanpostech.ac.kr

More information

Modeling and Propagating CNNs in a Tree Structure for Visual Tracking

Modeling and Propagating CNNs in a Tree Structure for Visual Tracking The Visual Object Tracking Challenge Workshop 2016 Modeling and Propagating CNNs in a Tree Structure for Visual Tracking Hyeonseob Nam* Mooyeol Baek* Bohyung Han Dept. of Computer Science and Engineering

More information

Mask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi

Mask R-CNN. By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Mask R-CNN By Kaiming He, Georgia Gkioxari, Piotr Dollar and Ross Girshick Presented By Aditya Sanghi Types of Computer Vision Tasks http://cs231n.stanford.edu/ Semantic vs Instance Segmentation Image

More information

Detecting and Tracking Cells using Network Flow Programming

Detecting and Tracking Cells using Network Flow Programming Detecting and Tracking Cells using Network Flow Programming Engin Türetken 1,2 Xinchao Wang 1 Carlos Becker 1 Pascal Fua 1 1 Computer Vision Laboratory (EPFL), CH-1015 Lausanne, Switzerland 2 Swiss Center

More information

Reliably Tracking Partially Overlapping Neural Stem Cells in DIC Microscopy Image Sequences

Reliably Tracking Partially Overlapping Neural Stem Cells in DIC Microscopy Image Sequences 67 Neural Stem Cells in DIC Microscopy Image Sequences Ryoma Bise 1,2, Kang Li 3, Sungeun Eom 2, Takeo Kanade 2 1 Dai Nippon Printing Co.,Ltd., Media Research Center, Tokyo, Japan. 2 Carnegie Mellon University,

More information

Tracking People. Tracking People: Context

Tracking People. Tracking People: Context Tracking People A presentation of Deva Ramanan s Finding and Tracking People from the Bottom Up and Strike a Pose: Tracking People by Finding Stylized Poses Tracking People: Context Motion Capture Surveillance

More information

Globally Optimal Cell Tracking using Integer Programming

Globally Optimal Cell Tracking using Integer Programming Globally Optimal Cell Tracking using Integer Programming Engin Türetken CSEM, Switzerland engin.tueretken@alumni.epfl.ch Xinchao Wang CVLab, EPFL, Switzerland xinchao.wang@epfl.ch Carsten Haubold HCI,

More information

A Visual Navigation System for Querying Neural Stem Cell Imaging Data

A Visual Navigation System for Querying Neural Stem Cell Imaging Data A Visual Navigation System for Querying Neural Stem Cell Imaging Data Ishwar Kulkarni 1 Shanaz Y. Mistry 1 Brian Cummings 2 M. Gopi 1 1 Department of Computer Science, 2 Department of Anatomy and Neurobiology

More information

Learning to Segment Object Candidates

Learning to Segment Object Candidates Learning to Segment Object Candidates Pedro Pinheiro, Ronan Collobert and Piotr Dollar Presented by - Sivaraman, Kalpathy Sitaraman, M.S. in Computer Science, University of Virginia Facebook Artificial

More information

Microscopy Cell Counting with Fully Convolutional Regression Networks

Microscopy Cell Counting with Fully Convolutional Regression Networks Microscopy Cell Counting with Fully Convolutional Regression Networks Weidi Xie, J. Alison Noble, Andrew Zisserman Department of Engineering Science, University of Oxford,UK Abstract. This paper concerns

More information

Learning to Count Cells: Applications to Lens-free Imaging of Large Fields

Learning to Count Cells: Applications to Lens-free Imaging of Large Fields 1 Learning to Count Cells: Applications to Lens-free Imaging of Large Fields G. Flaccavento 1,2, V. Lempitsky 3, I. Pope 1,4, P.R. Barber 1, A. Zisserman 3, J.A. Noble 2, B. Vojnovic 1 1 Gray Institute

More information

Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network. Nathan Sun CIS601

Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network. Nathan Sun CIS601 Disguised Face Identification (DFI) with Facial KeyPoints using Spatial Fusion Convolutional Network Nathan Sun CIS601 Introduction Face ID is complicated by alterations to an individual s appearance Beard,

More information

Neuron Crawler: An Automatic Tracing Algorithm for Very Large Neuron Images

Neuron Crawler: An Automatic Tracing Algorithm for Very Large Neuron Images Neuron Crawler: An Automatic Tracing Algorithm for Very Large Neuron Images Zhi Zhou, Staci A. Sorensen, and Hanchuan Peng* Allen Institute for Brain Science, Seattle, WA 98103. * Corresponding author.

More information

Cell Tracking using Convolutional Neural Networks

Cell Tracking using Convolutional Neural Networks Cell Tracking using Convolutional Neural Networks Anton Jackson-Smith Stanford acjs@stanford.edu Abstract Automated cell segmentation and tracking is an ongoing challenge in biology, with better technology

More information

Understanding Tracking and StroMotion of Soccer Ball

Understanding Tracking and StroMotion of Soccer Ball Understanding Tracking and StroMotion of Soccer Ball Nhat H. Nguyen Master Student 205 Witherspoon Hall Charlotte, NC 28223 704 656 2021 rich.uncc@gmail.com ABSTRACT Soccer requires rapid ball movements.

More information

Segmentation of Cells from Spinning Disk Confocal Images Using a Multi-stage Approach

Segmentation of Cells from Spinning Disk Confocal Images Using a Multi-stage Approach Segmentation of Cells from Spinning Disk Confocal Images Using a Multi-stage Approach Saad Ullah Akram 1,2, Juho Kannala 1, Mika Kaakinen 2,3, Lauri Eklund 2,3, and Janne Heikkilä 1 1 Center for Machine

More information

Interactive Tracking of Cells in Microscopy Image Sequences

Interactive Tracking of Cells in Microscopy Image Sequences Interactive Tracking of Cells in Microscopy Image Sequences M. Gentil, M. Sameki, D. Gurari, E. Saraee, E. Hasenberg, J. Y. Wong, and M. Betke Boston University, USA Abstract. Analysis of the morphological

More information

Foundations of Machine Learning CentraleSupélec Fall Clustering Chloé-Agathe Azencot

Foundations of Machine Learning CentraleSupélec Fall Clustering Chloé-Agathe Azencot Foundations of Machine Learning CentraleSupélec Fall 2017 12. Clustering Chloé-Agathe Azencot Centre for Computational Biology, Mines ParisTech chloe-agathe.azencott@mines-paristech.fr Learning objectives

More information

Efficient Segmentation-Aided Text Detection For Intelligent Robots

Efficient Segmentation-Aided Text Detection For Intelligent Robots Efficient Segmentation-Aided Text Detection For Intelligent Robots Junting Zhang, Yuewei Na, Siyang Li, C.-C. Jay Kuo University of Southern California Outline Problem Definition and Motivation Related

More information

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin

More information

Instance-aware Semantic Segmentation via Multi-task Network Cascades

Instance-aware Semantic Segmentation via Multi-task Network Cascades Instance-aware Semantic Segmentation via Multi-task Network Cascades Jifeng Dai, Kaiming He, Jian Sun Microsoft research 2016 Yotam Gil Amit Nativ Agenda Introduction Highlights Implementation Further

More information

Biomedical Image Analysis. Mathematical Morphology

Biomedical Image Analysis. Mathematical Morphology Biomedical Image Analysis Mathematical Morphology Contents: Foundation of Mathematical Morphology Structuring Elements Applications BMIA 15 V. Roth & P. Cattin 265 Foundations of Mathematical Morphology

More information

Cellular Tracking and Mitosis Detection in Dense In-vitro Cellular Data

Cellular Tracking and Mitosis Detection in Dense In-vitro Cellular Data Thesis submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Cellular Tracking and Mitosis Detection in Dense In-vitro Cellular Data By Ketheesan Thirusittampalam

More information

arxiv: v1 [cs.cv] 4 Apr 2019

arxiv: v1 [cs.cv] 4 Apr 2019 mproved nference via Deep nput Transfer Saied Asgari Taghanaki, Kumar Abhishek, and Ghassan Hamarneh School of Computing Science, Simon Fraser University, Canada {sasgarit, kabhishe, hamarneh}@sfu.ca arxiv:194.237v1

More information

Classification of objects from Video Data (Group 30)

Classification of objects from Video Data (Group 30) Classification of objects from Video Data (Group 30) Sheallika Singh 12665 Vibhuti Mahajan 12792 Aahitagni Mukherjee 12001 M Arvind 12385 1 Motivation Video surveillance has been employed for a long time

More information

Joint Vanishing Point Extraction and Tracking. 9. June 2015 CVPR 2015 Till Kroeger, Dengxin Dai, Luc Van Gool, Computer Vision ETH Zürich

Joint Vanishing Point Extraction and Tracking. 9. June 2015 CVPR 2015 Till Kroeger, Dengxin Dai, Luc Van Gool, Computer Vision ETH Zürich Joint Vanishing Point Extraction and Tracking 9. June 2015 CVPR 2015 Till Kroeger, Dengxin Dai, Luc Van Gool, Computer Vision Lab @ ETH Zürich Definition: Vanishing Point = Intersection of 2D line segments,

More information

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task Kyunghee Kim Stanford University 353 Serra Mall Stanford, CA 94305 kyunghee.kim@stanford.edu Abstract We use a

More information

TEXT SEGMENTATION ON PHOTOREALISTIC IMAGES

TEXT SEGMENTATION ON PHOTOREALISTIC IMAGES TEXT SEGMENTATION ON PHOTOREALISTIC IMAGES Valery Grishkin a, Alexander Ebral b, Nikolai Stepenko c, Jean Sene d Saint Petersburg State University, 7 9 Universitetskaya nab., Saint Petersburg, 199034,

More information

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma Mask R-CNN Background Related Work Architecture Experiment Mask R-CNN Background Related Work Architecture Experiment Background From left

More information

Deep Face Recognition. Nathan Sun

Deep Face Recognition. Nathan Sun Deep Face Recognition Nathan Sun Why Facial Recognition? Picture ID or video tracking Higher Security for Facial Recognition Software Immensely useful to police in tracking suspects Your face will be an

More information

Detection of Sub-resolution Dots in Microscopy Images

Detection of Sub-resolution Dots in Microscopy Images Detection of Sub-resolution Dots in Microscopy Images Karel Štěpka, 2012 Centre for Biomedical Image Analysis, FI MU supervisor: prof. RNDr. Michal Kozubek, Ph.D. Outline Introduction Existing approaches

More information

Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences

Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences IEEE TRANSACTIONS ON MEDICAL IMAGING 1 Network Flow Integer Programming to Track Elliptical Cells in Time-Lapse Sequences Engin Türetken, inchao Wang, Carlos J. Becker, Carsten Haubold, and Pascal Fua,

More information

Automatically Improving 3D Neuron Segmentations for Expansion Microscopy Connectomics. by Albert Gerovitch

Automatically Improving 3D Neuron Segmentations for Expansion Microscopy Connectomics. by Albert Gerovitch Automatically Improving 3D Neuron Segmentations for Expansion Microscopy Connectomics by Albert Gerovitch 1 Abstract Understanding the geometry of neurons and their connections is key to comprehending

More information

Ensemble registration: Combining groupwise registration and segmentation

Ensemble registration: Combining groupwise registration and segmentation PURWANI, COOTES, TWINING: ENSEMBLE REGISTRATION 1 Ensemble registration: Combining groupwise registration and segmentation Sri Purwani 1,2 sri.purwani@postgrad.manchester.ac.uk Tim Cootes 1 t.cootes@manchester.ac.uk

More information

Digital Volume Correlation for Materials Characterization

Digital Volume Correlation for Materials Characterization 19 th World Conference on Non-Destructive Testing 2016 Digital Volume Correlation for Materials Characterization Enrico QUINTANA, Phillip REU, Edward JIMENEZ, Kyle THOMPSON, Sharlotte KRAMER Sandia National

More information

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07.

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07. NIH Public Access Author Manuscript Published in final edited form as: Proc Soc Photo Opt Instrum Eng. 2014 March 21; 9034: 903442. doi:10.1117/12.2042915. MRI Brain Tumor Segmentation and Necrosis Detection

More information

Actin Filament Segmentation using Spatiotemporal Active-Surface and Active-Contour Models

Actin Filament Segmentation using Spatiotemporal Active-Surface and Active-Contour Models Actin Filament Segmentation using Spatiotemporal Active-Surface and Active-Contour Models Hongsheng Li 1, Tian Shen 1, Dimitrios Vavylonis 2, and Xiaolei Huang 1 1 Department of Computer Science & Engineering,

More information

Spatio-temporal Analysis of Unstained Cells In-vitro

Spatio-temporal Analysis of Unstained Cells In-vitro Spatio-temporal Analysis of Unstained Cells In-vitro Nico Scherf 1,2, Jens-Peer Kuska 3, Ulf-Dietrich Braumann 2, Katja Franke 4, Tilo Pompe 4, Ingo Röder 1 1 Inst. f. Medizinische Informatik, Statistik

More information

Automated Video Analysis of Crowd Behavior

Automated Video Analysis of Crowd Behavior Automated Video Analysis of Crowd Behavior Robert Collins CSE Department Mar 30, 2009 Computational Science Seminar Series, Spring 2009. We Are... Lab for Perception, Action and Cognition Research Interest:

More information

ECS 289H: Visual Recognition Fall Yong Jae Lee Department of Computer Science

ECS 289H: Visual Recognition Fall Yong Jae Lee Department of Computer Science ECS 289H: Visual Recognition Fall 2014 Yong Jae Lee Department of Computer Science Plan for today Questions? Research overview Standard supervised visual learning building Category models Annotators tree

More information

Black-Box Hyperparameter Optimization for Nuclei Segmentation in Prostate Tissue Images

Black-Box Hyperparameter Optimization for Nuclei Segmentation in Prostate Tissue Images Black-Box Hyperparameter Optimization for Nuclei Segmentation in Prostate Tissue Images Thomas Wollmann 1, Patrick Bernhard 1,ManuelGunkel 2, Delia M. Braun 3, Jan Meiners 4, Ronald Simon 4, Guido Sauter

More information

Office of Graduate Studies

Office of Graduate Studies Office of Graduate Studies Dissertation / Thesis Approval Form This form is for use by all doctoral and master s students with a dissertation/thesis requirement. Please print clearly as the library will

More information

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields Authors: Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh Presented by: Suraj Kesavan, Priscilla Jennifer ECS 289G: Visual Recognition

More information

Nuclei Segmentation of Whole Slide Images in Digital Pathology

Nuclei Segmentation of Whole Slide Images in Digital Pathology Nuclei Segmentation of Whole Slide Images in Digital Pathology Dennis Ai Department of Electrical Engineering Stanford University Stanford, CA dennisai@stanford.edu Abstract Pathology is the study of the

More information

A Statistical Thresholding Method for Cell Tracking. Nezamoddin N. Kachouie 1, Paul Fieguth 1 John Ramunas 2 and Eric Jervis 2

A Statistical Thresholding Method for Cell Tracking. Nezamoddin N. Kachouie 1, Paul Fieguth 1 John Ramunas 2 and Eric Jervis 2 2006 IEEE International Symposium on Signal Processing and Information Technology A Statistical Thresholding Method for Cell Tracking Nezamoddin N. Kachouie 1, Paul Fieguth 1 John Ramunas 2 and Eric Jervis

More information

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University. Visualizing and Understanding Convolutional Networks Christopher Pennsylvania State University February 23, 2015 Some Slide Information taken from Pierre Sermanet (Google) presentation on and Computer

More information

Using Machine Learning for Classification of Cancer Cells

Using Machine Learning for Classification of Cancer Cells Using Machine Learning for Classification of Cancer Cells Camille Biscarrat University of California, Berkeley I Introduction Cell screening is a commonly used technique in the development of new drugs.

More information

Introduction to GE Microarray data analysis Practical Course MolBio 2012

Introduction to GE Microarray data analysis Practical Course MolBio 2012 Introduction to GE Microarray data analysis Practical Course MolBio 2012 Claudia Pommerenke Nov-2012 Transkriptomanalyselabor TAL Microarray and Deep Sequencing Core Facility Göttingen University Medical

More information

CS 221: Object Recognition and Tracking

CS 221: Object Recognition and Tracking CS 221: Object Recognition and Tracking Sandeep Sripada(ssandeep), Venu Gopal Kasturi(venuk) & Gautam Kumar Parai(gkparai) 1 Introduction In this project, we implemented an object recognition and tracking

More information

Multi-Plane Tomographic Phase Retrieval for 4D Cell Microscopy. Emrah Bostan Computational Imaging Lab UC Berkeley

Multi-Plane Tomographic Phase Retrieval for 4D Cell Microscopy. Emrah Bostan Computational Imaging Lab UC Berkeley Multi-Plane Tomographic Phase Retrieval for 4D Cell Microscopy Emrah Bostan Computational Imaging Lab UC Berkeley IMA Workshop Series: Phaseless Imaging in Theory and Practice University of Minnesota,

More information

Probabilistic Tracking of Virus Particles in Fluorescence Microscopy Image Sequences

Probabilistic Tracking of Virus Particles in Fluorescence Microscopy Image Sequences Probabilistic Tracking of Virus Particles in Fluorescence Microscopy Image Sequences W. J. Godinez 1,2, M. Lampe 3, S. Wörz 1,2, B. Müller 3, R. Eils 1,2, K. Rohr 1,2 1 BIOQUANT, IPMB, University of Heidelberg,

More information

Model-Based Segmentation and Colocalization Quantification in 3D Microscopy Images

Model-Based Segmentation and Colocalization Quantification in 3D Microscopy Images Model-Based Segmentation and Colocalization Quantification in 3D Microscopy Images Stefan Wörz 1, Petra Sander 2, Martin Pfannmöller 1, Ralf J. Rieker 3,4, Stefan Joos 2, Gunhild Mechtersheimer 3, Petra

More information

PROCESS > SPATIAL FILTERS

PROCESS > SPATIAL FILTERS 83 Spatial Filters There are 19 different spatial filters that can be applied to a data set. These are described in the table below. A filter can be applied to the entire volume or to selected objects

More information

Dynamic Routing Between Capsules

Dynamic Routing Between Capsules Report Explainable Machine Learning Dynamic Routing Between Capsules Author: Michael Dorkenwald Supervisor: Dr. Ullrich Köthe 28. Juni 2018 Inhaltsverzeichnis 1 Introduction 2 2 Motivation 2 3 CapusleNet

More information

Automated Cell Volume Estimation in Time-Lapse Microscopy Images

Automated Cell Volume Estimation in Time-Lapse Microscopy Images Automated Cell Volume Estimation in Time-Lapse Microscopy Images Amr El-Labban 1, Andrew Zisserman 1, Yusuke Toyoda 2, and Anthony Hyman 2 1 Department of Engineering Science, University of Oxford, UK

More information

Epithelial rosette detection in microscopic images

Epithelial rosette detection in microscopic images Epithelial rosette detection in microscopic images Kun Liu,3, Sandra Ernst 2,3, Virginie Lecaudey 2,3 and Olaf Ronneberger,3 Department of Computer Science 2 Department of Developmental Biology 3 BIOSS

More information

Peripheral drift illusion

Peripheral drift illusion Peripheral drift illusion Does it work on other animals? Computer Vision Motion and Optical Flow Many slides adapted from J. Hays, S. Seitz, R. Szeliski, M. Pollefeys, K. Grauman and others Video A video

More information