IAM

Meet me at CVPR'18: Tuesday, June 19th, I will be presenting our work on weakly-supervised 3D shape completion.

TAG»OPENCV«

ARTICLE

Compiling OpenCV 2.4.x with CUDA 9

Currently, both OpenCV 2 and OpenCV 3 seem to have some minor issues with CUDA 9. However, CUDA 9 is required for the latest generation of NVidia graphics cards. In this article, based on this StackOverflow question, I want to discuss a very simple patch to get OpenCV 2 running with CUDA 9.

More ...

29thJANUARY2017

PROJECT

Revised C++ implementations of two popular superpixel algorithms, SEEDS and FH, which are shown to outperform the original implementations.

More ...

05thDECEMBER2016

PROJECT

A comprehensive comparison and evaluation of 28 superpixel algorithms on 5 different datasets; published in CVIU and GCPR.

More ...

ARTICLE

Running OpenCV and Google GLog with CMake on Travis CI

Running C++ projects on Travis CI may be challenging depending on the libraries used. Here I briefly describe how to run OpenCV and Google GLog on Travis CI.

More ...

07thJUNE2016

PROJECT

Efficient C++ implementation for hierarchical graph-based image segmentation.

More ...

09thMAY2016

PROJECT

Efficient C++ implementation of iPiano, a proximal algorithm with inertial force for non-convex and non-smooth optimization; including applications to image segmentation.

More ...

ARTICLE

Fast, Multi-Label Connected Components in MatLab

This article presents a MatLab MEX wrapper for a fast, multi-label connected components implementation in C++ originally written by Ali Rahimi.

More ...

ARTICLE

Optical Flow I/O with OpenCV

This article presents an OpenCV wrapper for the Flow I/O code provided by the Sintel dataset [2].

More ...

ARTICLE

Efficient Hierarchical Graph-Based Video Segmentation: An Implementation

This article presents an efficient implementation of the hierarchical graph-based video segmentation algorithm proposed by Grundmann et al. [1]. The implementation is available on GitHub.

More ...

ARTICLE

Efficient High-Quality Superpixels: SEEDS Revised

SEEDS Revised is a new implementation of the superpixel algorithm SEEDS [1] used for evaluation in my bachelor thesis “Superpixel Segmentation using Depth Information”. This article introduces the basic concepts of SEEDS as well as the usage of SEEDS Revised.

More ...