No self-introduction
Loading
Profile
Follow
codes (15)
Pedestrian detection in video
no vote
The goal of this project is to detect humans in real-time, with a high detection rate, and few false positives. The human detector achieves 20 fps speed and state-of-the-art detection accuracy, using only one processing thread without resorting to special hardwares like GPU. Contour is the most important information source for human detection, and the signs of comparisons among neighboring pixels are the key to encode contours.
domi858524 0 0
1
HOG+SVM for pedestrian detection
no vote
This C++ program demonstrates how to detect pedestrian on an image using the functions of OpenCV. The recognition is based on HOG and SVM.
domi858524 2 0
1
Determination of fundamental matrix by a set of po
no vote
The fundamental matrix can be determined by a set of point correspondences. This program demonstrates an example for this problem. The fundamental matrix is a relationship between any two images of the
same scene that constrains where the projection of points from the scene
can occur in both images.
domi858524 0 0
1
Double Pendulum Animation
no vote
Run the program by typing DoublePendulumAnimation at the Matlab prompt. Make sure that your current directory in Matlab is set to the directory containing DoublePendulumAnimation.m. To run the animation with the default parameters, simply click the Begin button to start the animation. You can experiment by changing the parameters and initial conditions and hitting the Begin button to see the motion of the double pendulum.
1)If the animation goes too slowly decrease the number of points.
2)If the animation is too fast or jerky increase the number of points.
3)Vary the time span to either increase or decrease the length of the animation.
domi858524 0 0
1
Pyramidal Implementation of the Lucas Kanade Featu
no vote
The program proposes a pyramidal implementation of the classical Lucas-Kanade algorithm. An iterative implementation of the Lucas-Kanade optical flow computation provides sufficient local tracking accuracy.
domi858524 0 0
1
Metropolis-Hastings algorithm
4.0
http://en.wikipedia.org/wiki/Metropolis-Hastings_algorithm
Metropolis-Hastings algorithm is a Markov chain Monte Carlo method for obtaining a sequence of random samples from a probability distribution for which direct sampling is difficult. The sequence can be used to
approximate the distribution.
The following code is a simple implementation of Metropolis-Hastings algorithm, these code is compiled under linux operation system. and can also be used in Windows OS.
The metropolis_demo.cpp is a demo for sampling a gaussian distribution.
Run metropoli
domi858524 5 0
1
Canny Edge Detector implemented in MATLAB
no vote
The Canny Edge Detector is implemented in MATLAB without using the functions of the image processing toolbox.
domi858524 0 0
1
Efficient LBP computation in MATLAB
4.0
This program computes the different types of an image's LBP-histogram. It introduces an efficient computation of LBP.
domi858524 0 0
1
Compute homography
4.0
This is the source code of computing Hormography Matrix of two images. Welcome to download and try. Thank you for your support!
domi858524 2 0
1
Visualize the HOG descriptor of an image
no vote
The OpenCV/C++ program computes and then visualizes the HOG descriptor of an image. The program takes a HOG descriptor and computes the gradient magnitude per cell by looping through all blocks and adding the gradient strengths for each of the cells per block to each individual cell and finally averages the gradient strengths.
domi858524 0 0
1
View More
Follows0
Fans0