Download presentation
Presentation is loading. Please wait.
Published byNicholas Walters Modified over 9 years ago
1
UCF REU: Weeks 1 & 2
2
Gradient Code
4
Gradient
5
Direction of the Gradient: Calculating theta
6
Picking a threshold for the gradient map
7
Subtract the gradient from the original image display it Detailing on camera
8
Edge Detection
9
Sobel approximation to the derivative Filters Lapacian of Gaussian (LoG)
10
Canny Edge Detector Gaussian filter to smooth image 1 st derivative kernel to detect edges Non-maximal suppression
11
Median filter B = medfilt2(im) does a median filtering of the image im in two dimensions. Each output pixel contains the median value in the 3 x 3 neighborhood around the corresponding pixel in the input image. It pads the image with zeros on the edges, so the median values for points on the edge of the image may appear darker. Median filtering is most often used to reduce "salt and pepper" noise. A median filter is more effective than convolution when the goal is to simultaneously reduce noise and preserve edges.
12
Harris Corner Detector Shifting the window in any direction should yield a large change in appearance -aka what happens at a corner!
13
Code for Harris Corner
14
Optical Flow (Lucas Kanade with pyramids) Shows the vectors of motion.
15
Optical Flow (Liu) Found YouTube clip of Olympic diver: https://www.youtube.com/watch?v=djou2oLUeuo https://www.youtube.com/watch?v=djou2oLUeuo Clipped the video into a 3 second clip of just the action of diving Converted the clipped video into a sequence of jpg images Example:
16
Made a loop in demo flow to run through the sequence of diving images Took the optical flow images and converted them into an animated gif: Olympic Diver: http://makeagif.com/I27cPy
18
Scale Invariant Feature Transform (SIFT)
19
Code (for one image)
20
Code to collect all images Have to do these 2 pieces of code for every 15 categories
21
Input images Basic matching using SIFT points
22
Result
23
Code
24
Adaboost
25
SVM (Support Vector Machine) Pick classifier where the distance between the support vectors and the linear classifier is maximized.
26
Bag Of Words
27
Project Preference 1 Project: Multimodal data analysis for the detection of Attention Deficit Hyperactive Disorder Mentor: Soumyabrata Dey Began his reading most recent paper on the project Have taken discrete systems which has graph theory which will help because: looking at the brain as a series of nodes and edges
28
Project Preference 2 Project: Deep Tracker Mentor: Afshin Dehghan I know python Looked at papers on deep learning
29
Project Preference 3 Project: Action Recognition in Temporally Untrimmed videos Mentor: Amir R. Zamir Have a solid grasp of frame work Very interested in topic
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.