colinshane Goto Github PK

dvs-feature-extraction

Dynamic Vision Sensor (DVS) data is an alternative to classical vision paradigms and offers many advantages over frame based processing. Further work is needed to create techniques capable of harnessing the full potential of DVS data. This repository holds some work using evolutionary algorithms to generate kernels specialised to DVS data. These kernels can then be used as low level feature detectors for input into neural networks.

dvs-multi-cue-pedestrian-detection

Multi-Cue Event Information Fusion for Pedestrian Detection with Neuromorphic Vision Sensors

dvs-truenorth

Telluride neuromorphic project on event-based image classification

dvscalibration

Matlab functions to help with DVS calibration using the Caltech Camera Calibration Toolbox (from http://www.vision.caltech.edu/bouguetj/calib_doc/ )

dvs_reconstruction

Calculate full image from event based camera (dynamic vision sensor)

emp

event-based stereo matching algorithm

ev-flownet

Code for the paper "EV-FlowNet: Self-Supervised Optical Flow for Event-based Cameras"

event-based_vision_resources

event-driven

neuromorphic development on the iCub robot

event-flow

This repository is an implementation of motion flow computation from DVS events following the method of "Event-Based Visual Flow" (https://ieeexplore.ieee.org/document/6589170)

eventbasedvisualodometry

Implementation of Event-Based Visual Odometry algorithm - Group project for 16-720 Computer Vision / 16-833 SLAM

eventrecognitioncnn

Event recognition based on object and scene recognition CNN models. Used Keras framework (TF) + Python for deep learning, Flask for API and Angular for Web App

event_feature_tracking

This repo contains MATLAB implementations of the event-based feature tracking methods described in "Event-based Feature Tracking with Probabilistic Data Association" and "Event-based Visual Inertial Odometry".

evolvingann

Spiking Artificial Neural Network With Reward Driven Hebbian Learning

fast

FAST corner detector by Edward Rosten

forecasting-lstm-wta

Combines the variational inference winner-take-all spiking neural network model (VIWTA SNN) with a standard vanilla LSTM built using the Keras Python package to predict time series steps and sequences.

freeproxy

The best tutorial that help you build VPN, in simple, safe and free ways.

gotgithub

GotGitHub: an open source E-book about GitHub in Chinese

hands_on_ml_with_sklearn_and_tf

OReilly Hands On Machine Learning with Scikit Learn and TensorFlow (Sklearn与TensorFlow机器学习实用指南)

har-dvs

This project is a part of our work, "Dynamic Vision Sensors for Human Activity Recognition"

hardware-accelerated-snn

Architecture for Spiking Neural Network

hbpprak_perception

helllo-world

it's my first day in github. hello, the whole new world

hfirst

A Matlab implementation of the spiking HFIRST model for recognition

hmm-stdp

STDP installs in winner-take-all circuits an online approximation to hidden Markov model learning

hrr-scaling

Python/CUDA code to create a spiking neural network that can encode and traverse the Wordnet lexical database.

ijcnn2016

Diverse, Noisy and Parallel: a New Spiking Neural Network Approach for Humanoid Robot Control

integernet

introduction-to-spiking-neural-network

introduction_to_ml_with_python

Notebooks and code for the book "Introduction to Machine Learning with Python"