##Convolutional Neural Networks for Visual Tracking
The main goal of our GSoC project was an implementation of GOTURN tracker in OpenCV library.
Original paper is located here: http://davheld.github.io/GOTURN/GOTURN.pdf
Short GOTURN tracker overview: http://davheld.github.io/GOTURN/GOTURN.html
Our implementation of GOTURN comes in two parts:
- GOTURN tracker imlementation in OpenCV Tracking API. Pretrained GOTURN model is required.
- GOTURN tracker training toolkit, for pretraining GOTURN with custom parameters.
Also we uploaded a pretrained (according to the original paper) GOTURN model to opencv_extra repository, so anyone can use it straightly without time-consuming pretraining procedure.
##OpenMax layer implementation for tinyDNN
OpenMax layer implementation for tinyDNN has started as additional activity during the last week of GSoC. Current implementation includes only a utility function for Mean Activation Vector with the following MR EVT calibration using Weibull fiting in libMR.
For complete OpenMax implementation two are still need to be done:
- Function for calculation Weibull fiting for all classes in particular dataset
- Actual OpenMax layer implementation (now there is empty OpenMax layer skeleton) to calculate a final OpenMax score
##List of all commits during GSoC 2016:
- [GOTURN Tracker in OpenCV Tracking API]
(https://github.com/opencv/opencv_contrib/compare/master…Auron-X:GOTURN_Tracker@%7B2016-08-23%7D) - [GOTURN Training Toolkit]
(https://github.com/Auron-X/GOTURN_Training_Toolkit/commits) - [GOTURN Trained Model in OpenCV_Extra]
(https://github.com/opencv/opencv_extra/compare/master…Auron-X:GOTURN_Tracker@%7B2016-08-24%7D) - [OpenMax layer implementation for tinyDNN]
(https://github.com/tiny-dnn/tiny-dnn/compare/master…Auron-X:tinyDNN_OpenMax@%7B2016-08-23%7D)