Search Results for "computer vision"

Metalhead.jl provides standard machine learning vision models for use with Flux.jl. The architectures in this package make use of pure Flux layers, and they represent the best practices for creating modules like residual blocks, inception blocks, etc. in Flux. Metalhead also provides some building blocks for more complex models in the Layers module.

...Transformations are designed to be light-weight and efficient enough for, e.g., real-time graphical applications, while support for both explicit and automatic differentiation makes it easy to perform optimization and therefore ideal for computer vision applications such as SLAM (simultaneous localization and mapping).

...From loading datasets and creating data preprocessing pipelines to training, FastAI.jl takes the boilerplate out of deep learning projects. It equips you with reusable components for every part of your project while remaining customizable at every layer. FastAI.jl comes with support for common computer vision and tabular data learning tasks, with more to come.

Flux3D.jl is a 3D vision library, written completely in Julia. This package utilizes Flux.jl and Zygote.jl as its building blocks for training 3D vision models and for supporting differentiation. This package also have support of CUDA GPU acceleration with CUDA.jl.

OpenFace is an advanced facial behavior analysis toolkit intended for computer vision and machine learning researchers, those in the affective computing community, and those who are simply interested in creating interactive applications based on facial behavior analysis. The OpenFace toolkit is capable of performing several complex facial analysis tasks, including facial landmark detection, eye-gaze estimation, head pose estimation and facial action unit recognition.

Overhead Imagery Research Data Set (OIRDS) - an annotated data library & tools to aid in the development of computer vision algorithms

The Java parallel to the popular Intel computer vision library, OpenCV. OpenJCV = Open Java Computer Vision

This Java native library wraps OpenCV (Computer Vision Lib.) function cvMatchTemplate and implements methods for utilities result visualization. It allows efficient images template matching using Normalized Cross-Correlation (NCC) and others algorithms.

A C++ library of high level motion analysis/computer vision functions, coupled with GUIs that allow easy configuration and use. Current development focuses on color tracking, multiple camera calibration and triangulation, and 3D tracking algorithms.

i3D-converter creates a 3D representation from a couple of images (or a pair of stereo images). This program also performs other Computer Vision operations such as, edge and corner detection, image filtering, getting geometric shapes,...

C++ library that implements basic data structures and algorithms for computer vision and image processing applications

A software to implement the existing stereo matching algorithms in computer vision, including the easiest SSD, and the newest algorithms.