Training Date : Coming soon
Time : 4 days (24 hours)
Duration : 09:00 – 16:00
Instructor : Tapanan Yeophantong
Affiliation :
Director, Intelligent Systems Laboratory
Vincent Mary School of Science and Technology
Assumption University
Pre-requisite(s) : Fundamentals of Machine Learning (or equivalent)
Description :
A practical training workshop on the principles and practices in developing computer vision applications,
using opencv frameworks and machine/deep learning tools. Topics include an overview for computer
vision tasks and pipelines, computer vision frameworks and tools, object detection and localisation, object
recognition, and motion analysis techniques for tracking objects in video streams.
Lesson Plan
- Lesson 1 Basics of Computer Vision (6 hours)
1.1. Computer Vision Tasks & Pipelines
1.2. Overview of OpenCV Framework & Libraries
1.3. Image Preprocessing Techniques
1.4. Metrics for Performance Evaluation
- Lesson 2 Object Detection, Identification and Tracking (6 hours)
2.1. Overview of Object Recognition Tasks
2.2. Object Detection Using Cascade Classifiers
2.3. Object recognition using ML techniques
2.4. Object Tracking Using Kalman Filter
- Lesson 3 Object Recognition Using Deep Learning (6 hours)
3.1. Overview of Tensorflow
3.2. R-CNN & SSD Architectures
3.3. YOLO Architectures
3.4. Tensorflow Models for Computer Vision
- Lesson 4 Feature Embedding and Transfer Learning (6 hours)
4.1. Importance of feature extraction
4.2. Feature Extraction & Template Matching
4.3. Obtaining Feature Embeddings from Deep Learning Models
4.4. Advanced Network Training Using Transfer Learning
0.00 average based on 0 ratings
