Classes | Namespaces | Functions | Variables
slam_evaluation.py File Reference

Go to the source code of this file.

Classes

class  slam_evaluation.Error

Namespaces

namespace  slam_evaluation

Functions

def slam_evaluation.apply_tf_to_matrix
def slam_evaluation.apply_tf_to_vector
def slam_evaluation.calc_dist
def slam_evaluation.calc_dist_xyz
def slam_evaluation.calc_errors
def slam_evaluation.calc_time_vector
def slam_evaluation.quaternion_from_rpy
def slam_evaluation.rebase
def slam_evaluation.sigmoid
def slam_evaluation.to_transform
def slam_evaluation.toRSTtable
def slam_evaluation.trajectory_distances

Variables

list slam_evaluation.angles = [-6, 6, -4, 4, -12, 12]
tuple slam_evaluation.args = parser.parse_args()
tuple slam_evaluation.ax0 = Axes3D(fig0)
tuple slam_evaluation.ax1 = fig1.gca()
tuple slam_evaluation.ax2 = fig2.gca()
tuple slam_evaluation.ax3 = fig3.gca()
tuple slam_evaluation.ax4 = fig4.gca()
tuple slam_evaluation.ax5 = fig5.gca()
list slam_evaluation.colors = ['g','r','b']
tuple slam_evaluation.edges = pylab.loadtxt(args.graph_edges_file, delimiter=',', usecols=(3,4,5,10,11,12))
tuple slam_evaluation.f = open(args.ground_truth_file)
tuple slam_evaluation.fig0 = pylab.figure()
tuple slam_evaluation.fig1 = pylab.figure()
tuple slam_evaluation.fig2 = pylab.figure()
tuple slam_evaluation.fig3 = pylab.figure()
tuple slam_evaluation.fig4 = pylab.figure()
tuple slam_evaluation.fig5 = pylab.figure()
tuple slam_evaluation.first_gt_coincidence = to_transform(gt_rebased[0,:])
tuple slam_evaluation.first_vertice = to_transform(vertices[0,:])
dictionary slam_evaluation.font
tuple slam_evaluation.gt = pylab.loadtxt(args.ground_truth_file, delimiter=',', comments='%', usecols=(0,5,6,7,8,9,10,11))
tuple slam_evaluation.gt_corrected = apply_tf_to_vector(tf_correction, gt_moved)
tuple slam_evaluation.gt_dist = trajectory_distances(gt_rb_corrected)
tuple slam_evaluation.gt_moved = apply_tf_to_matrix(tf_delta, gt)
tuple slam_evaluation.gt_rb_corrected = apply_tf_to_vector(tf_correction, gt_rb_moved)
tuple slam_evaluation.gt_rb_moved = apply_tf_to_matrix(tf_delta, gt_rebased)
tuple slam_evaluation.gt_rebased = rebase(vertices, gt)
list slam_evaluation.header = [ "Input", "Data Points", "Traj. Distance (m)", "Trans. MAE (m)"]
string slam_evaluation.help = 'file with ground truth'
tuple slam_evaluation.lines = f.readlines()
float slam_evaluation.linewidth = 3.0
tuple slam_evaluation.odom = pylab.loadtxt(args.visual_odometry_file, delimiter=',', comments='%', usecols=(0,5,6,7,8,9,10,11))
tuple slam_evaluation.odom_corrected = apply_tf_to_vector(tf_correction, odom_moved)
tuple slam_evaluation.odom_dist = trajectory_distances(odom_rb_corrected)
tuple slam_evaluation.odom_errors = calc_errors(gt_rb_corrected, odom_rb_corrected)
tuple slam_evaluation.odom_mae = np.average(np.abs(odom_errors), 0)
tuple slam_evaluation.odom_moved = apply_tf_to_matrix(tf_delta, odom)
tuple slam_evaluation.odom_rb_corrected = apply_tf_to_vector(tf_correction, odom_rb_moved)
tuple slam_evaluation.odom_rb_moved = apply_tf_to_matrix(tf_delta, odom_rebased)
tuple slam_evaluation.odom_rebased = rebase(vertices, odom)
tuple slam_evaluation.orb = pylab.loadtxt(args.orb_file, delimiter=',', usecols=(0,2,3,4,5,6,7,8))
tuple slam_evaluation.orb_corrected = apply_tf_to_vector(tf_correction, orb_moved)
tuple slam_evaluation.orb_dist = trajectory_distances(orb_rb_corrected)
tuple slam_evaluation.orb_errors = calc_errors(gt_rb_corrected, orb_rb_corrected)
tuple slam_evaluation.orb_mae = np.average(np.abs(orb_errors), 0)
tuple slam_evaluation.orb_moved = apply_tf_to_matrix(tf_delta, orb)
tuple slam_evaluation.orb_rb_corrected = apply_tf_to_vector(tf_correction, orb_rb_moved)
tuple slam_evaluation.orb_rb_moved = apply_tf_to_matrix(tf_delta, orb_rebased)
tuple slam_evaluation.orb_rebased = rebase(vertices, orb)
tuple slam_evaluation.p = optimize.brute(sigmoid, rranges, args=(vertices, gt_rebased))
tuple slam_evaluation.Param = collections.namedtuple('Param','roll pitch yaw')
tuple slam_evaluation.parser
tuple slam_evaluation.q = quaternion_from_rpy(roll, pitch, yaw)
list slam_evaluation.rows = []
tuple slam_evaluation.rranges = ((angles[0]*np.pi/180, angles[1]*np.pi/180, 0.04), (angles[2]*np.pi/180, angles[3]*np.pi/180, 0.02), (angles[4]*np.pi/180, angles[5]*np.pi/180, 0.04))
list slam_evaluation.size = lines[1]
tuple slam_evaluation.tf_correction = to_transform([0.0, 0.0, 0.0, 0.0, q[0], q[1], q[2], q[3]])
tuple slam_evaluation.tf_delta = tf.concatenate_matrices(tf.inverse_matrix(first_gt_coincidence), first_vertice)
tuple slam_evaluation.time = calc_time_vector(gt_rb_corrected)
list slam_evaluation.vect = []
tuple slam_evaluation.vertices = pylab.loadtxt(args.graph_vertices_file, delimiter=',', usecols=(0,2,3,4,5,6,7,8))
tuple slam_evaluation.vertices_dist = trajectory_distances(vertices)
tuple slam_evaluation.vertices_errors = calc_errors(gt_rb_corrected, vertices)
tuple slam_evaluation.vertices_mae = np.average(np.abs(vertices_errors), 0)


stereo_slam
Author(s): Pep Lluis Negre
autogenerated on Thu Jul 14 2016 04:09:13