BigSnarf blog

Infosec FTW

Monthly Archives: March 2017

Predicting deep into the future with segmentation

Screen Shot 2017-03-24 at 9.04.14 AM

Click to access 1703.07684.pdf

https://github.com/MarvinTeichmann/MultiNet

Click to access 1612.07695.pdf

https://github.com/e-lab/ENet-training

Self driving car LIDAR and camera download

Screen Shot 2017-03-23 at 11.06.36 PM

Self Driving Car Operating System

Screen Shot 2017-03-20 at 6.20.31 PMScreen Shot 2017-03-20 at 6.18.10 PMScreen Shot 2017-03-20 at 6.03.27 PM

TACC Traffic-Aware-Cruise-Control

tracking_white_van.gif

Screen Shot 2017-03-24 at 9.04.14 AM

russian_sdc

ff_autonomouscars3_f

901_Framegrab_Camera_sensor-e1441246576585

Traffic-Aware Cruise Control uses a camera

Mounted on the windshield behind the interior rear view mirror and a radar sensor in the
center of the front grill to detect whether there is a vehicle in front of you in the same
lane. If the area in front of car is clear, Traffic-Aware Cruise Control is designed to
drive consistently at a set speed.
When a vehicle is detected, Traffic-Aware Cruise Control is designed to slow down the car if
needed to maintain a selected time-based distance from the vehicle in front, up to the
set speed. Traffic-Aware Cruise Control does not eliminate the need to watch the road in
front of you and to apply the brakes if needed.
Traffic-Aware Cruise Control makes it easy to maintain a consistent time-based distance
from a vehicle travelling in front of you in the same lane. Traffic-Aware Cruise Control is
primarily intended for driving on dry, straight roads, such as highways and freeways. It
should not be used on city streets.

GOTURN tracking

ezgif-2-95cb54bb47ezgif-2-0f24362942

Hand annotating first image on Kitti Sequence 21

Screen Shot 2017-03-17 at 4.06.52 PM

http://davheld.github.io/GOTURN/GOTURN.html

https://github.com/davheld/GOTURN

Click to access GOTURN.pdf

https://github.com/Auron-X/GOTURN_Training_Toolkit

https://handong1587.github.io/deep_learning/2015/10/09/tracking.html

https://github.com/Guanghan/ROLO

http://guanghan.info/projects/ROLO/

Click to access 1703.01289.pdf

##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:

  1. GOTURN tracker imlementation in OpenCV Tracking API. Pretrained GOTURN model is required.
  2. 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:

  1. Function for calculation Weibull fiting for all classes in particular dataset
  2. Actual OpenMax layer implementation (now there is empty OpenMax layer skeleton) to calculate a final OpenMax score

##List of all commits during GSoC 2016:

##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:

  1. GOTURN tracker imlementation in OpenCV Tracking API. Pretrained GOTURN model is required.
  2. 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:

  1. Function for calculation Weibull fiting for all classes in particular dataset
  2. Actual OpenMax layer implementation (now there is empty OpenMax layer skeleton) to calculate a final OpenMax score

##List of all commits during GSoC 2016:

 

 

Ego-motion

Optical Flow experiments

Filtering noise with Kalman Filters

The workhorse of robotics is Kalman Filters

kalman2kalman1

http://greg.czerniak.info/guides/kalman1/

Training Neural Networks for classification using the Extended Kalman Filter: A comparative study (effen paywalled)

Click to access kalman_V2.pdf

https://github.com/iqans/opencv-python/blob/master/kalman.py

https://arxiv.org/abs/1703.02310

Screen Shot 2017-03-30 at 10.40.15 PM.png