kor01

import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np

# Read in the image
image = mpimg.imread('test.jpg')

# Grab the x and y size and make a copy of the image
ysize = image.shape[0]
xsize = image.shape[1]

kor01

purpose:

to give each cluster in segmentation output a label

s.t. the grounding geometric specification of semantic command can be extracted

kor01

DBSCAN: Density-Based Spatial Clustering of Application with Noise

Assummes: known distance boundary but not number of clusters

Also named as: Euclidean Clustering

two hyper parameters: 
maximum distance within cluster
minimum number of points in a cluster

kor01

human v.s. robots:

human 3D vision: stereo vision, prior geometry, motion filtering

robot 3D vision: (actively) measure the distance

sensor types:

active sensors: use an enery source to probe the environment

kor01

from the rotor center:

	the pitch surface in phase II and IV: up rotation produce up thrust on the body
    
    the pitch surface in phase I and III: up rotation produce down thrust on the body
    
	up rotation always produce down torque
    
    down rotation produce up torque

kor01

nosetests --logging-level=WARN -vs

kor01

import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
import cv2
import glob
import time
from sklearn.svm import SVC
from sklearn.preprocessing import StandardScaler
# NOTE: the next import is only valid 
# for scikit-learn version <= 0.17

kor01

# number of inner corners in x and y direction
nx = 8
ny = 6

#find chessboard corners
img = mpimg.imread(images[idx])

# Convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)

kor01

import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

# Read in and plot the image
image = mpimg.imread('Udacican.jpeg')
plt.imshow(image)

# Take histograms in R, G, and B

kor01

%% get size

d = size(a, 2)
e = size(a, 1)

%% drop singleton dimension
a = squeeze(b)

%% construct