View on GitHub

Neural Networks for Computer Vision

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

by Valentyn Sichkar Academia.edu YouTube

Neural Networks for Computer Vision

Implementing Neural Networks for Computer Vision in Autonomous Vehicles and Robotics for Objects Detection and Tracking, Objects Classification, Pattern Recognition, Robotics Control. From very beginning to Complex Project.

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

Related works
Description
Content
- Codes
- Theory and experimental results

Sichkar V.N. Comparison analysis of knowledge based systems for navigation of mobile robot and collision avoidance with obstacles in unknown environment. St. Petersburg State Polytechnical University Journal. Computer Science. Telecommunications and Control Systems, 2018, Vol. 11, No. 2, Pp. 64–73. DOI: 10.18721/JCSTCS.11206 (Full-text available also here ResearchGate.net/profile/Valentyn_Sichkar)
The study on Image Processing in Python is put in separate repository and is available here: Image processing in Python
The study of Semantic Web languages OWL and RDF for Knowledge representation of Alarm-Warning System is put in separate repository and is available here: Knowledge Base Represented by Semantic Web Language
The research results for Neural Network Knowledge Based system for the tasks of collision avoidance is put in separate repository and is available here: Matlab implementation of Neural Networks
The research on Machine Learning algorithms and techniques in Python is put in separate repository and is available here: Machine Learning in Python

Description

The aim of the repository is to study and create 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.

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

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

Conv --> ReLU --> Pool

Example #3 - video introduction into Convolutional NN with Python from scratch:

Example #4 - image classification with CNN and CIFAR-10 datasets in pure numpy, algorithm and file structure:

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

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

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

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

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:

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

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.