CVML Web-Lectures 5-6

LECTURE 5: Structure from Motion

Saturday 9^th May 2020, 11:00-11:45 EEST and repeated  20:00-20:45 EEST

Summary: Image-based 3D Shape Reconstruction, Stereo and multiview imaging principles. Feature extraction and matching. Triangulation and Bundle Adjustment. Mathematics of structure from motion. UAV image capturing. Optimal UAV flight trajectory/flight height/viewing angle/image overlap ratio. Pre/post-processing for 3D reconstruction: flat surface smoothing/mesh modification/isolated point removal.  Structure from motion applications: 3D face reconstruction from uncalibrated video. 3D landscape reconstruction. 3D building/monument reconstruction and modeling.

Sample lecture material

 – sample slides DOWNLOAD

Related Literature:

1. Pitas, “Computer vision”, Createspace/Amazon, in press.
2. R.Szelinski, “ Computer Vision ” , Springer 2011
3. Hartley R, Zisserman A. , “ Multiple view geometry in computer vision” . Cambridge university press; 2003.
4. Davies, E. Roy. “Computer vision: principles, algorithms, applications, learning ”. Academic Press, 2017

 

Lecture 6: 2D convolution and correlation

Saturday 9^th May 2020, 11:45-12:30 EEST and repeated 20:45-21:30 EEST

Summary: 2D convolutions play an extremely important role in machine learning, as they form the first layers of Convolutional Neural Networks (CNNs). They are also very important for computer vision (template matching through correlation, correlation trackers) and in image processing (image filtering/denoising/restoration). 3D convolutions are very important for machine learning (video analysis through CNNs) and for video filtering/denoising/restoration. 1D convolutions are extensively used in digital signal processing (filtering/denoising)  and analysis (also through CNNs)

Therefore, 2D convolution and correlation algorithms are very important both for machine learning and for signal/image/video processing and analysis. As their computational complexity is of the order O(N^4), their fast execution is a must.

This lecture will overview 1D/2D linear and cyclic convolution. Then it will present their fast execution through FFTs, resulting in algorithms having computational complexity of the order O(Nlog2N), O(N^2log2N) for 1D and 2D convolutions respectively. Parallel block-based 2D convolution/calculation methods will be overviewed.  The use of 2D convolutions in Convolutional Neural Networks will be presented.

 

Sample lecture material
 – sample slides DOWNLOAD

Related Literature

1. I. Pitas, Digital Image Processing Algorithms and Applications, J. Wiley, 2000.
2. I. Pitas, “Digital video processing and analysis ” , China Machine Press, 2017 (in Chinese).
3. I. Pitas, “Digital Video and Television ” , Createspace/Amazon, 2013.
4. I. Pitas, “Computer vision”, Createspace/Amazon, in press.