Computer Vision

Semantic Segmentation Overview

What is Semantic Segmentation? Image segmentation is a computer vision task in which we label specific regions of an image according to what’s being shown. The goal of semantic image segmentation is to label each pixel of an image with a corresponding class of what is being represented.

2020-12-19

Segmentation

2020-12-19

Annotation Conversion: COCO JSON to YOLO Txt

Bounding box formats comparison and conversion In COCO Json, the format of bounding box is: "bbox": [ <absolute_x_top_left>, <absolute_y_top_left>, <absolute_width>, <absolute_height> ] However, the annotation is different in YOLO. For each .

2020-12-02

COCO JSON Format for Object Detection

The COCO dataset is formatted in JSON and is a collection of “info”, “licenses”, “images”, “annotations”, “categories” (in most cases), and “segment info” (in one case). { "info": {...}, "licenses": [.

2020-12-02

Face Detection: Neural-Network-Based

Motivation Idea: Use a search-window to scan over an image Train a classifier to decide whether the search windows contains a face or not? Detection Simple neuron model Topologies Parameters Adjustable Parameters are

2020-11-13

Evaluation Metrics for Object Detection

Precision & Recall Confusion matrix: Precision: measures how accurate is your predictions. i.e. the percentage of your predictions are correct. $$ \text{precision} = \frac{TP}{TP + FP} $$ Recall: measures how good you find all the positives.

2020-11-12

Object Detection

2020-11-12

Face Detection: Color-Based

TL;DR Different color spaces and classifiers can be used Models: histograms, Gaussian Models, Mixture of Gaussians Model Histogram-backprojection / Histogram matching Bayes classifier Discriminative Classifiers (ANN, SVM) Bayesian classifier and ANN seem to work well

2020-11-06

Pattern Recognition

Why pattern recognition and what is it? What is machine learning? Motivation: Some problems are very hard to solve by writing a computer program by hand Learn common patterns based on either a priori knowledge or

2020-11-06

Computer Vision for Human-Computer Interaction

Name Computer Vision for Human-Computer Interaction Semester WS 20/21 Language English, German Lecturer(s) Prof. Dr.-Ing. Rainer Stiefelhagen Dr.-Ing. Muhammad Saquib Sarfraz Credits 6 Homepages https://cvhci.anthropomatik.kit.edu/600_1979.php

2020-11-06