Udemy

Platform

English

Language

Data Science

Category

Siam Mask Object Tracking and Segmentation in OpenCV Python

Implement Real-Time Object Tracking and Segmentation using OpenCV Python

3.50 (1 reviews)

Students

1 hour

Content

Jun 2021

Last Update
Regular Price


What you will learn

Object Tracking with Segmentation

Fundamentals of Siam Mask

How to set-up your programming environment

How to work with your own Dataset

Train Siam Mask For your own Applications

How to test if Siam Mask is working


Description

What Is Siam Mask

In this course you will learn how to implement both real-time object tracking and semi-supervised video object segmentation with a single simple approach. SiamMask, improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting the loss with a binary segmentation task.

Once trained, SiamMask solely relies on a single bounding-box initialization and operates online, producing class-agnostic(any class will work) object segmentation masks and rotated bounding boxes at 35 frames per second.

Despite its simplicity, versatility and fast speed, our strategy allows us to establish a new state-of-the-art among real-time trackers on VOT-2018 dataset, while at the same time demonstrating competitive performance and the best speed for the semi-supervised video object segmentation task on DAVIS-2016 and DAVIS-2017

Applications of Siam Mask

  • Automatic Data Annotation - Regardless of Class

  • Rotoscoping

  • Robotics

  • Object Detection and targeting

  • Virtual Background without Green Screen

What you will Learn?

You will learn the fundamentals of Siam Mask and how it can be used for fast online object tracking and segmentation. You will first learn about the origins of Siam Mask, how it was developed as well its amazing performance on real world tests. Next we do a paper review to understand more about the architecture of Siamese Networks with regards to computer vision.

Thereafter, we move on to the implementation of Siam Mask by setting up the environment for development so that you can run Siam Mask on your own PC or Laptop. Once that is working, we will show you how to train Siam Mask for your own custom applications.

Once trained, you will need a method in which to test your new model so that you can apply it for real world applications.

Why Should I Take this Course?

You should take this course, because Siam Mask is a State of Art Model that has robust accuracy and performance and can be used in a wide variety of applications.


Screenshots

Siam Mask Object Tracking and Segmentation in OpenCV Python
Siam Mask Object Tracking and Segmentation in OpenCV Python
Siam Mask Object Tracking and Segmentation in OpenCV Python
Siam Mask Object Tracking and Segmentation in OpenCV Python

Content

Introduction

Object Tracking Introduction

Single and Multi-Object Video Object Tracking

Object Segmentation

Siam Mask Object Segmentation Tracking

Siam Mask Course Overview

Paper Review

How does Siam Mask Work Intro

Fully Convolutional Siamese Network

SiamFC and Siam RPN

Siam Mask

Implementation Details

Siam Mask Performance

Results of Siam Mask

Important Links

Environmental Setup

Environmental Setup Intro

What you will Need

Setup and GitHub Code

Anaconda Setup

Setup Python Environment

3_6 Running the Demo

3_7 Demo Analysis

3_8 Key Take-away

Working with Your Own Dataset

4_1 Using your Own Dataset Intro

4_2 Siam Mask Execution Commands

4_3 Converting the Dataset into Images

4_4 Running the Demo on your own Dataset

4_5 Activity - Test it on your own video

Training Dataset Processing

5_1 Training Datasets Overview

5_2 YouTube VOS Dataset

5_3 COCO Dataset

5_4 ImageNet Datasets

5_5 YouTube VOS Training Dataset Process

5_6 Step 1 - Using the Correct Directory

5_7 Step 2 - Downloading the Raw Image Dataset

5_8 Annotation Metafile Format Review

5_9 Dataset Post Processing

5_10 Step 3 - Crop and Generate Data Info

5_11 Convert Raw Data to Summarised Training format

5_12 How to Repeat for Other Datasets

5_13 Activity - Try Out your Own Datasets

Training Siam Mask

6_1 Intro to Siam Mask Training

6_2 Why Use Test Data

6_3 Step 0 - Downloading Test Data

6_4 Step 1 - Download the Pre-trained Model

6_5 Step 2 - Training Siam Mask Base Model

6_6 Post-Training Checkpoints

6_7 Overview of Checkpoint Testing

6_8 Activity - Train you own Dataset

Testing Siam Mask

7_1 Testing SiamMask Intro

7_2 Various Options for Testing SiamMask

7_3 Option 1 - Testing Checkpoints on VOT

7_4 Option 2 - Best Model for Hyperparametric Search

7_5 Option 3 - Tracking on your Own Dataset

7_6 Siam Mask Custom Model Testing Summary

Error Handling and Troubleshooting

A1 - Error_Handling_-_jitdebug

A2 - Error_Handling_-_CUDA

A3 - Error_Handling_-_NoneType

A4 - Error_Handling_-_checkpoint_e9

A5 - Error_Handling_-_jq-_command_not_found

A6 - Error_Handling_-_NAN_FPS

BONUS SECTION

Learn More from Augmented Startups


4150804

Udemy ID

6/28/2021

Course created date

7/2/2021

Course Indexed date
Bot
Course Submitted by