Skip to content

Implementing Neural Networks for Computer Vision in autonomous vehicles and robotics for classification, pattern recognition, control. Using Python, numpy, tensorflow. From basics to complex project

License

Notifications You must be signed in to change notification settings

sichkar-valentyn/Neural_Networks_for_Computer_Vision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural Networks for Computer Vision

Implementing Neural Networks for Computer Vision in Autonomous Vehicles and Robotics, for Object Detection and Object Tracking, Object Classification, Pattern Recognition, Robotics Control. From Very Beginning to Complex and Huge Project.
DOI

Reference to:

Valentyn N Sichkar. Neural Networks for computer vision in autonomous vehicles and robotics // GitHub platform. DOI: 10.5281/zenodo.1317904

Structure of repository




The main aim of the repository is to study and to develope complex project on Computer Vision in autonomous vehicles and robotics through basics in Neural Networks to advanced learning. Here is brief description of repository, its stages of development, animated figures with empirical results. To get full content scroll down or click here to reach the content.


  • Example #1 - simple convolving of input image with three different filters for edge detection.
    Simple Convolution

  • Example #2 - more complex Convolving of input image with following architecture:
    Input ---> Conv --> ReLU --> Pool ---> Conv --> ReLU --> Pool ---> Conv --> ReLU --> Pool


Conv --> ReLU --> Pool


🚩 Concept Map of the Course Concept Map of the Course

👉 Join the Course https://www.udemy.com/course/training-yolo-v3-for-objects-detection-with-custom-data/


  • Example #4 - image Classification with CNN and CIFAR-10 datasets in pure numpy, algorithm and file structure:
    Image_Classification_File_Structure.png

  • Example #5 - training of Model #1 for CIFAR-10 Image Classification:
    Training Model 1

  • Example #6 - Initialized Filters and Trained Filters for ConvNet Layer for CIFAR-10 Image Classification task:
    Filters Cifar10

  • Example #7 - training of Model #1 for MNIST Digits Classification:
    Training Model 1

  • Example #8 - Initialized Filters and Trained Filters for ConvNet Layer for MNIST Digits Classification:
    Filters Cifar10

  • Example #9 - Histogram of 43 classes for training dataset with their number of examples for Traffic Signs Classification before and after Equalization by adding transformated images from original dataset:
    Histogram of 43 classes with their number of examples

  • Example #10 - Prepared and preprocessed data for Traffic Sign Classification (RGB, Gray, Local Histogram Equalization):
    Preprocessed_examples

  • Example #11 - Implementing Traffic Sign Classification with Convolutional Neural Network.
    • Left: Original frame with Detected Sign.
    • Upper Right: cut frame with Detected Sign.
    • Lower Right: classified frame by ConvNet according to the Detected Sign.
      Traffic_Sign_Classification_Small_Small.gif

  • Example #12 - Enhancing image by CLAHE (Contrast Limited Adaptive Histogram Equalization) Algorithm for RGB images with OpenCV:
    clahe_enhancing.png

  • Example #13 - Accuracy for training CNN with different datasets for Traffic Sign Classification is shown on the figure below:
    Accuracy_of_different_datasets_of_Model_1_TS.png

Theory and experimental results (it'll send you to appropriate page):




Codes (it'll send you to appropriate file):



MIT License

Copyright (c) 2018-2019 Valentyn N Sichkar

github.com/sichkar-valentyn

Reference to:

Valentyn N Sichkar. Neural Networks for computer vision in autonomous vehicles and robotics // GitHub platform. DOI: 10.5281/zenodo.1317904