How to use Convolution Neural Network to predict SIFT features

A feature locator is essential in all CV domain. It's the basis of the germetric transformation, epipolar geometry, to 3D mesh reconstruction.

Many techniques - SIFT and other SLAM technologies, are available, but they require ideal environments to work in.

To address the short comings:

- sensitive to low texture environment
- sensitive to low light envonrment
- sensitive to high light environment (like outdoor day light with above 20k lux)
- and many other issues

I propose a CNN based neural network to detect 4 correspondences in an image A and an image B.

Since it is tricky to have a neural network to predict a 4x4 affine matrix of rotation and translation, I separated the translation vector from the rotation vector.

Basically, the ground truth data will be precalcalated with a generic SIFT with RANSAC to calculate the correspondences set P and P'.

The L2 (Eucledean) distance will be used between a predicted value. They are 4 points, so an averaged will be used to calculate the delta beteen a predict P' and P'

Using Theano, a neural network was created and trained over few weeks.

The prediction errors were within 25% of the ground truth.

Further work:

I didn't have the confidence value calculated, but would like to add that in the prediction graph. This means we should be using Cross Entropy instead Regression here.

Hardware:

- CPU:
- Intel(R) Core(TM)2Duo CPU E8500 @ 3.16GHz
- Memory:
- 2GB RAM
- GPU:
- GeForce GTX 285
- BLAS:
- Intel Math Kernel Library, version 10.2.4.032
- Compute:
- CPU: double precision
- GPU: single precisison

Comments

Anonymous said…

This comment has been removed by a blog administrator.

December 14, 2012 at 4:28:00 PM PST

How to project a camera plane A to a camera plane B

How to Create a holographic display and camcorder In the last part of the series "How to Create a Holographic Display and Camcorder", I talked about what the interest points, descriptors, and features to find the same object in two photos. In this part of the series, I'll talk about how to extract the depth of the object in two photos by calculating the disparity between the photos. In order to that, we need to construct a triangle mesh between correspondences. To construct a mesh, we will use Delaunnay triagulation. Delaunnay Triagulation - It minimizes angles of all triangles, while the sigma of triangles is maximized. The reason for the triangulation is to do a piece wise affine transformation for each triangle mapped from a projective plane A to a projective plane B. A projective plane A is of a camera projective view at time t, while a projective plane B is of a camera projective view at time t+1. (or, at t-1. It really doesn't matter)...

State of the Art SLAM techniques

Best Stereo SLAMs in 2017 are reviewed. Namely, (in arbitrary order) EKF-SLAM based, Keyframe based, Joint BA optimization based, RSLAM, S-PTAM, LSD-SLAM, Best RGB-D SLAMs in 2017 are also reviewed. KinectFusion, Kintinuouns, DVO-SLAM, ElasticFusion, RGB-D SLAM, See my keypoints of the best Stereo SLAMs. Stereo SLAM Conditionally Independent Divide and Conquer EKF-SLAM [5] operate in large environments than other approaches at that time uses both close and far points far points whose depth cannot be reliably estimated due to little disparity in the stereo camera uses an inverse depth parametrization [6] shows empirically points can be triangulated reliably, if their depth is less than about 40 times the stereo baseline. - Keyframe-based Stereo SLAM - uses BA optimization in a local area to archive scalability. ...

How to train a neural network to retrieve 3D maps from videos

This blog is about how to train a neural network to extract depth maps from videos of moving people captured with a monocular camera. Note: With a monocular camera, extracting the depth map of moving people is difficult. Difficulty is due to the motion blur and the rolling shutter of an image. However, we can overcome these limitations by predicting the depth maps by the model trained with a generated dataset using SfM and MVS from the normalized videos. This normalized dataset can be the basis of the training set for the neural network to automatically extract the accurate depth maps from a typical video footage, without any further assistance from a MVS. To start this project with a SfM and a MVS, we will use TUM Dataset. So, the basic idea is to use SfM and Multiview Stereo to estimate depth, while serves as supervision during training. The RGB-D SLAM reference implementation from these papers are used: - RGB-D Slam (Robotics OS) - Real-time 3D Visual SLAM ...

Artificial Intelligence and Machine Vision

Search This Blog