Index

A

• activation / Convolutional Neural Networks
• Anaconda
  • installing / Installing Anaconda
  • URL / Installing Anaconda
• applications
  • drones / Applications
  • image editing / Applications
  • satellites or space vehicles / Applications
  • Augmented Reality (AR) / Applications
• Augmented Reality (AR) / Applications

B

• Bayes theorem / Bayes theorem
• Bernoulli distribution / Bernoulli distribution
• Binomial distribution / Binomial distribution

C

• camera intrinsic matrix / Image formation
• challenges, segmentation
  • noisy boundaries / Challenges in segmentation 
  • clustered scene / Challenges in segmentation 
• challenges, tracking
  • about / Tracking
  • object occlusion / Challenges in tracking
  • fast movement / Challenges in tracking
  • change of shape / Challenges in tracking
  • false positives / Challenges in tracking
• CIFAR-10 / CIFAR-10
• classifier parameters
  • reference / Methods for object detection
• CMake
  • installation link / OpenCV build from source
• CNN architectures
  • about / Popular CNN architectures
  • VGGNet / VGGNet
  • inception models / Inception models
  • ResNet model / ResNet model
• COCO
  • about / MSCOCO
  • URL / MSCOCO
  • RGB-D dataset / TUM RGB-D dataset
• computer vision
  • about / What constitutes computer vision?
  • image classification / Computer vision is everywhere
  • object detection / Computer vision is everywhere
  • image geometry / Computer vision is everywhere
  • image segmentation / Computer vision is everywhere
  • image generation / Computer vision is everywhere
  • image transformation / Computer vision is everywhere
• conditional distribution / Conditional distribution
• convolution / The convolution layer
• Convolutional Neural Networks (CNNs)
  • about / Convolutional Neural Networks
  • convolution layer / The convolution layer
  • activation layer / The activation layer
  • pooling layer / The pooling layer
  • fully connected layer / The fully connected layer
  • Batch Normalization / Batch Normalization
  • dropout / Dropout
  • using / CNN in practice 
  • fashion-MNIST classifier training code / Fashion-MNIST classifier training code
  • analyzing / Analysis of CNNs 
  • transfer learning / Transfer learning
• curse of dimensionality / Dimensionality's curse

D

• datasets
  • about / Datasets
  • ImageNet / ImageNet
  • MNIST / MNIST
  • CIFAR-10 / CIFAR-10
  • Pascal VOC / Pascal VOC
  • MSCOCO / MSCOCO
  • requisites / Datasets and libraries required
  • download link / Dataset and libraries
• deep learning-based object detection
  • about / Deep learning-based object detection
  • two-stage detectors / Deep learning-based object detection, Two-stage detectors
  • one-stage detectors / Deep learning-based object detection, One-stage detectors
  • faster R-CNN with ResNet-101 / Demo – Faster R-CNN with ResNet-101
• deep SORT
  • reference / Deep SORT
• Directed Acyclic Graph (DAG) / A simple neural network

E

• eigen value / Computing eigen values and eigen vectors
• eigen vectors / Computing eigen values and eigen vectors
• Epipolar Geometry / Image formation
• Euclidean coordinate system / Image formation

F

• Faster R-CNN / Deep learning-based object detection
• Fast Fourier Transform (FFT) / MOSSE tracker
• feature
  • use cases / Features use cases 
  • datasets and libraries / Datasets and libraries
  • importance / Why are features important?
  • Harris corner detection / Harris Corner Detection
• feedforward networks / A simple neural network
• filters
  • about / Introduction to filters, The convolution layer
  • linear filters / Linear filters
  • non-linear filters / Non-linear filters 
  • image gradients / Image gradients
• freezing a model / Transfer learning
• fully convolutional network (FCN) / CNNs for segmentation
• fundamental matrix / Image formation

G

• Gaussian distribution / Gaussian distribution
• Gaussian filter / Smoothing a photo 
• gradient descent / A simple neural network

H

• Hessian matrix / Hessian matrix

I

• image
  • manipulation / Image manipulation
  • gradients / Image gradients
  • transformation / Transformation of an image
  • translation / Translation
  • rotation / Rotation 
  • affine transform / Affine transform 
  • formation / Image formation
  • aligning / Aligning images 
• image color conversions
  • grayscale / Image color conversions
  • HSV and HLS / Image color conversions
  • LAB color space / Image color conversions
• ImageNet / ImageNet
• Imagenet Large Scale Visual Recognition Challenge (ILSVRC) / VGGNet
• image operations
  • about / Getting started
  • image, reading / Reading an image 
  • image color, conversions / Image color conversions
• image pyramids / Image pyramids
• Inertial Measurement Units (IMU) / Applications
• input
  • preprocessing / Preprocessing
• input processing
  • normalization / Normalization
  • noise / Noise
• Inverse Fast Fourier Transform (IFFT) / MOSSE tracker

J

• Joint distribution / Joint distribution
• Jupyter notebook / Jupyter notebook

K

• Keras / Keras for deep learning 
• kernel / 2D linear filters

L

• learning
  • overview / A rolling-ball view of learning
• libraries
  • installing / Libraries and installation
  • Anaconda, installing / Installing Anaconda
  • OpenCV, installing / Installing OpenCV
  • TensorFlow / TensorFlow for deep learning
  • keras / Keras for deep learning 
  • requisites / Datasets and libraries required
• linear algebra
  • about / Linear algebra
  • vectors / Vectors
• linear filter
  • about / Linear filters
  • 2D Linear Filters / 2D linear filters
  • box filters / Box filters
  • linear filters, properties / Properties of linear filters
• loop closure / Visual SLAM

M

• machine learning
  • about / What is machine learning?
  • techniques / Kinds of machine learning techniques
• machine learning techniques
  • supervised learning / Supervised learning
  • unsupervised learning / Unsupervised learning
• marginal distribution / Marginal distribution
• Matplotlib / Matplotlib
• matrices
  • about / Matrices
  • operations / Operations on matrices
  • properties / Matrix properties
• matrices, operations
  • addition / Addition
  • subtraction / Subtraction
  • multiplication / Matrix multiplication
• matrix properties
  • transpose / Transpose
  • identity matrix / Identity matrix
  • diagonal matrix / Diagonal matrix
  • symmetric matrix / Symmetric matrix
  • trace of matrix / Trace of a matrix
  • determinant / Determinant
  • norm of matrix / Norm of a matrix
  • inverse of matrix / Getting the inverse of a matrix 
  • orthogonality / Orthogonality
• mean / Gaussian distribution
• Minimum Output Sum of Squared Error (MOSSE)
  • reference / MOSSE tracker
• MNIST / MNIST
• model's performance evaluation
  • about / Evaluation
  • precision value / Precision
  • recall / Recall
  • F-measure / F-measure
• Multiple Object Tracking (MOT) problem / Deep SORT

N

• neural networks
  • about / Introduction to neural networks, A simple neural network
  • convolution operation / Revisiting the convolution operation
• non-linear filters
  • about / Non-linear filters 
  • photo, smoothing / Smoothing a photo 
  • histogram, equalization / Histogram equalization
  • median filter / Median filter 
• non-maximal suppression / One-stage detectors
• NumPy / NumPy

O

• object detection
  • about / Introduction to object detection
  • challenges / Challenges in object detection
  • libraries / Dataset and libraries used
  • dataset / Dataset and libraries used
  • methods / Methods for object detection
  • deep learning-based object detection / Deep learning-based object detection
• one-stage detectors
  • about / One-stage detectors, Demo
  • demo / Demo
• OpenCV
  • URL / Installing OpenCV
  • installing / Installing OpenCV
  • Anaconda, used for installation / OpenCV Anaconda installation 
  • building, from source / OpenCV build from source
  • about / Opencv FAQs
• ORB SLAM2
  • reference / Visual SLAM
• oriented BRIEF (ORB) / Aligning images 

P

• Pascal VOC
  • about / Pascal VOC
  • URL / Pascal VOC
• pixels / Image manipulation, Why are features important?
• Poisson distribution / Poisson distribution
• postprocessing / Postprocessing
• Probability Density Function (PDF) / What are random variables?
• probability distributions
  • Bernoulli distribution / Bernoulli distribution
  • Binomial distribution / Binomial distribution
  • Poisson distribution / Poisson distribution
  • uniform distribution / Uniform distribution
  • Gaussian distribution / Gaussian distribution
  • Joint distribution / Joint distribution
  • Marginal distribution / Marginal distribution
  • conditional distribution / Conditional distribution
• Probability Mass Function (PMF) / What are random variables?
• probability theory / Introduction to probability theory

R

• random variables
  • about / What are random variables?
  • expectation / Expectation
  • variance / Variance
  • probability distributions / Probability distributions
  • Bayes theorem / Bayes theorem
• receptive field / The convolution layer
• Region of Interests (ROI) / Two-stage detectors
• Region Proposal Network (RPN) / Two-stage detectors
• RGB-D dataset
  • URL / TUM RGB-D dataset

S

• SciPy / SciPy
• segmentation
  • about / Segmentation
  • challenges / Challenges in segmentation 
  • CNNs / CNNs for segmentation
  • FCN, implementing / Implementation of FCN
• Simple Online and Realtime Tracking / Deep SORT
• Single Shot Multibox Detector (SSD) / Deep learning-based object detection, One-stage detectors
• Singular Value Decomposition (SVD) / Singular Value Decomposition
• supervised learning
  • about / Supervised learning
  • classification / Classification
  • regression / Regression

T

• TensorFlow / TensorFlow for deep learning
• tracking
  • about / Tracking
  • challenges / Challenges in tracking
  • object tracking, methods / Methods for object tracking
  • MOSSE tracker / MOSSE tracker
  • deep SORT / Deep SORT
• tracking by detection / Methods for object tracking
• training / A simple neural network
• transfer learning / Transfer learning

U

• Uniform distribution / Uniform distribution
• unsupervised learning / Unsupervised learning

V

• variance / Gaussian distribution
• vectors
  • addition / Addition
  • subtraction / Subtraction
  • multiplication / Vector multiplication
  • norm / Vector norm
  • orthogonality / Orthogonality
• Visual Odometry (VO)
  • about / Visual odometry
  • challenges / Visual odometry
  • process / Visual odometry
• Visual Simultaneous Localization and Mapping (vSLAM) / Dataset and libraries, Visual SLAM

W

• weights / Convolutional Neural Networks
• window / Harris Corner Detection