def __init__(self, configuration):
# Images to be processed
self.bgr = np.empty(0)
self.hsv = np.empty(0)
self.edges = np.empty(0)
param_names = [
'hsv_white1',
'hsv_white2',
'hsv_yellow1',
'hsv_yellow2',
'hsv_red1',
'hsv_red2',
'hsv_red3',
'hsv_red4',
'hsv_green1',
'hsv_green2',
'hsv_blue1',
'hsv_blue2',
'hsv_no1',
'hsv_no2',
'dilation_kernel_size',
'canny_thresholds',
'hough_threshold',
'hough_min_line_length',
'hough_max_line_gap',
]
Configurable.__init__(self, param_names, configuration)
def __init__(self,configuration):
param_names = [
'mean_d_0',
'mean_phi_0',
'sigma_d_0',
'sigma_phi_0',
'delta_d',
'delta_phi',
'd_max',
'd_min',
'phi_max',
'phi_min',
'cov_v',
'linewidth_white',
'linewidth_yellow',
'lanewidth',
'min_max',
'sigma_d_mask',
'sigma_phi_mask',
]
configuration = copy.deepcopy(configuration)
Configurable.__init__(self,param_names,configuration)
self.d,self.phi = np.mgrid[self.d_min:self.d_max:self.delta_d,self.phi_min:self.phi_max:self.delta_phi]
self.belief=np.empty(self.d.shape)
self.mean_0 = [self.mean_d_0, self.mean_phi_0]
self.cov_0 = [ [self.sigma_d_0, 0], [0, self.sigma_phi_0] ]
self.cov_mask = [self.sigma_d_mask, self.sigma_phi_mask]
self.initialize()
def __init__(self, configuration):
# Images to be processed
self.bgr = np.empty(0)
self.hsv = np.empty(0)
self.edges = np.empty(0)
param_names = [
'hsv_white1',
'hsv_white2',
'hsv_yellow1',
'hsv_yellow2',
'hsv_red1',
'hsv_red2',
'hsv_red3',
'hsv_red4',
'hsv_blue1',
'hsv_blue2',
'dilation_kernel_size',
'canny_thresholds',
'hough_threshold',
'hough_min_line_length',
'hough_max_line_gap',
]
Configurable.__init__(self, param_names, configuration)
def __init__(self, configuration):
# Images to be processed
self.bgr = np.empty(0)
self.hsv = np.empty(0)
self.edges = np.empty(0)
param_names = [
'hsv_white1',
'hsv_white2',
'hsv_yellow1',
'hsv_yellow2',
'hsv_red1',
'hsv_red2',
'hsv_red3',
'hsv_red4',
<<<<<<< HEAD
'hsv_blue1',
'hsv_blue2',
=======
>>>>>>> 2d356ff5df7440b437fd8915a698c3f4ba9b0c0c
'dilation_kernel_size',
'canny_thresholds',
'hough_threshold',
'hough_min_line_length',
'hough_max_line_gap',
]
Configurable.__init__(self, param_names, configuration)
def __init__(self, configuration):
param_names = [
'mean_d_0',
'mean_phi_0',
'sigma_d_0',
'sigma_phi_0',
'delta_d',
'delta_phi',
'd_max',
'd_min',
'phi_max',
'phi_min',
'cov_v',
'linewidth_white',
'linewidth_yellow',
'lanewidth',
'min_max',
'sigma_d_mask',
'sigma_phi_mask',
'curvature_res',
'range_min',
'range_est',
'range_max',
'curvature_right',
'curvature_left',
]
configuration = copy.deepcopy(configuration)
Configurable.__init__(self, param_names, configuration)
self.d, self.phi = np.mgrid[self.d_min:self.d_max:self.delta_d,
self.phi_min:self.phi_max:self.delta_phi]
self.d_pcolor, self.phi_pcolor = \
np.mgrid[self.d_min:(self.d_max + self.delta_d):self.delta_d,
self.phi_min:(self.phi_max + self.delta_phi):self.delta_phi]
self.beliefArray = []
self.range_arr = np.zeros(self.curvature_res + 1)
for i in range(self.curvature_res + 1):
self.beliefArray.append(np.empty(self.d.shape))
self.mean_0 = [self.mean_d_0, self.mean_phi_0]
self.cov_0 = [[self.sigma_d_0, 0], [0, self.sigma_phi_0]]
self.cov_mask = [self.sigma_d_mask, self.sigma_phi_mask]
self.d_med_arr = []
self.phi_med_arr = []
self.median_filter_size = 5
self.initialize()
self.updateRangeArray(self.curvature_res)
# Additional variables
self.red_to_white = False
self.use_yellow = True
self.range_est_min = 0
self.filtered_segments = []
def __init__(self, configuration):
# Images to be processed
self.bgr = np.empty(0)
self.hsv = np.empty(0)
self.edges = np.empty(0)
param_names = [
'hsv_white1',
'hsv_white2',
'hsv_yellow1',
'hsv_yellow2',
'hsv_red1',
'hsv_red2',
'hsv_red3',
'hsv_red4',
'dilation_kernel_size',
'canny_thresholds',
'hough_threshold',
'hough_min_line_length',
'hough_max_line_gap',
]
configuration = copy.deepcopy(configuration)
Configurable.__init__(self, param_names, configuration)
self.dilation_kernel_size = 3
self.canny_thresholds = [80,200]
self.hough_threshold = 2
self.hough_min_line_length = 3
self.hough_max_line_gap = 1
self.hsv_white1 = [0,0,150]
self.hsv_white2 = [180,60,255]
self.hsv_yellow1 = [25,140,100]
self.hsv_yellow2 = [45,255,255]
self.hsv_red1 = [0,140,100]
self.hsv_red2 = [15,255,255]
self.hsv_red3 = [165,140,100]
self.hsv_red4 = [180,255,255]
def __init__(self, configuration):
# Images to be processed
self.bgr = np.empty(0)
self.hsv = np.empty(0)
self.edges = np.empty(0)
param_names = [
'hsv_white1',
'hsv_white2',
'hsv_yellow1',
'hsv_yellow2',
'hsv_red1',
'hsv_red2',
'hsv_red3',
'hsv_red4',
'dilation_kernel_size',
'canny_thresholds',
'sobel_threshold',
]
Configurable.__init__(self, param_names, configuration)
def __init__(self, configuration):
param_names = [
'mean_d_0',
'mean_phi_0',
'sigma_d_0',
'sigma_phi_0',
'delta_d',
'delta_phi',
'd_max',
'd_min',
'phi_max',
'phi_min',
'cov_v',
'linewidth_white',
'linewidth_yellow',
'lanewidth',
'min_max',
'sigma_d_mask',
'sigma_phi_mask',
'curvature_res',
'range_min',
'range_est',
'range_max',
'curvature_right',
'curvature_left',
]
configuration = copy.deepcopy(configuration)
Configurable.__init__(self, param_names, configuration)
self.d, self.phi = np.mgrid[self.d_min:self.d_max:self.delta_d,
self.phi_min:self.phi_max:self.delta_phi]
self.d_pcolor, self.phi_pcolor = \
np.mgrid[self.d_min:(self.d_max + self.delta_d):self.delta_d,
self.phi_min:(self.phi_max + self.delta_phi):self.delta_phi]
self.beliefArray = []
self.range_arr = np.zeros(self.curvature_res + 1)
for i in range(self.curvature_res + 1):
self.beliefArray.append(np.empty(self.d.shape))
self.mean_0 = [self.mean_d_0, self.mean_phi_0]
self.cov_0 = [[self.sigma_d_0, 0], [0, self.sigma_phi_0]]
self.cov_mask = [self.sigma_d_mask, self.sigma_phi_mask]
self.d_med_arr = []
self.phi_med_arr = []
self.median_filter_size = 5
self.default_delta_d = self.delta_d
self.default_delta_phi = self.delta_phi
self.update_matrix(1) #1 is initial value matrix_mash_size
self.initialize()
self.updateRangeArray(self.curvature_res)
# Additional variables
self.red_to_white = False
self.is_dynamic = True
self.range_est_min = 0
self.filtered_segments = []
# The dynamic color can be used to change which color
# the Duckiebot observes during lane following, instead of yellow
self.dynamic_color = YELLOW
self.dynamic_color_sub = rospy.Subscriber('/parking/lane_color',
String,
self.updateDynamicColor,
queue_size=1)