Browsing All Posts filed under »Research«

Optimal Triangulation for Tuning Keypoint Co-ordinates

October 11, 2017

0

Given a set of correct keypoint matches and a fundamental matrix, to optimize the coordinates of these key points such that they satisfy the epipolar constraint. A point (x,y) on the left image (pose: [I|0]) and (x’,y’) on the right image (pose: [R|t]). These points are undistorted and in normalized image coordinates. Having known the pose […]

Image Keypoint Descriptors and Matching

August 17, 2017

0

[GitHub] Extracting keypoints from images, usually, corner points etc is usually the first step for geometric methods in computer vision. A typical workflow is: keypoints are extracted from images (SIFT, SURF, ORB etc.). At these keypoints descriptors are extracted (SURF, ORB etc). Usually a 32D vector at each keypoint. The nearest neighbor search is performed to […]

HowTo – Pose Graph Bundle Adjustment

April 29, 2017

0

SLAM (Simultaneous Localization and Mapping) is one of the important practical areas in computer vision / robotics / image based modelling community. A SLAM system typically consists of a) odometry estimator (relative pose estimator), b) Bundle adjustment module, c) sensor fusion module (for visual-inertial system), d) mapping module. While there are several excellent resources, refer […]

Generating randoms from a specified CDF

March 9, 2017

0

This post deals with generating random numbers given a CDF (Cumulative distribution function). CDF may be specified as an analytical function or as a table of values. We also assume that we have a source of pseudo-random uniformly distributed numbers. Probability Integral Transform At the core of this issue is the ‘Probability Integral Transform’.  It states that, […]

NetVLAD – Supervised Place Recognition

February 15, 2017

0

Download PPT – Google Docs Vector of locally aggregated descriptors (VLAD) [1] is a simple and popular technique for computing a fingerprint of an image for place recognition. It basically forms say K=64 clusters of SIFT like descriptors (descriptors at SIFT feature points). Then, for every descriptor subtracts it from cluster center and adds it up. […]

Recurrent Neural Net: Memo

January 11, 2017

0

RNN (Recurrent Neural nets) are used to model sequences. Unlike the usual feedforward nets which are stateless in terms on inputs, RNNs have memory. In particular, its inputs are the output of previous step and also new observation in current step. The basic RNN are notoriously hard to train. LSTM (Long short term memory) networks […]

Generative Networks : Memo

January 11, 2017

0

Ian Goodfellow’s one of the popular works is the GAN (Generative Adversarial Networks). These networks basically can generate images (which look like real images). In the coming future, I wish to get into this a bit. Below could be a good start point : a) Tutorial by Goodfellow in NIPS2016 : [Arxiv] [Slides]