What are segments? about 3rscan HOT 5 CLOSED

file = open('labels.instances.annotated.ply', 'rb')
plydata = PlyData.read(file)
labels = plydata['vertex']['objectId']

 "segGroups": [
    {
      "id": 42,
      "objectId": 42,
      "label": "box",
  ...
    {
      "id": 34,
      "objectId": 34,
      "label": "chair",

with open('semseg.json', 'r') as read_file:
  data = json.load(read_file)
  for segGroups in data['segGroups']:
      print(segGroups["objectId"], segGroups["label"])

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 21 18:11:45 2020

@author: bayraktare
"""
import json, glob, csv, sys,os, argparse, meshio
import numpy as np

def get_intrinsic_color(fn):
    k = open(fn, 'r')
    kk = k.readlines()
#    print(kk)
    K = []    
    for i in range(len(kk)):
       K.append(kk[i].split(' '))
    
    mt = np.asarray(K[7][2:-1], dtype='float')    
    mat = np.reshape(mt,(4,4))
    wi = int(K[2][2][:-1]) # colorwidth
    hi = int(K[3][2][:-1]) # colorheight
    return (mat,wi,hi)

def get_pose(fn):
  return np.loadtxt(open(fn, "rb"), delimiter=" ")

def get_full_pc(fn):
  #return np.loadtxt(open(fn, "rb"), delimiter=" ")
  return np.genfromtxt(open(fn, "rb"), delimiter=" ")

def frame_num_from_name(filename):# when name is .../frame-000000.pose.txt
  return int(filename.split('/')[-1].split('-')[1].split('.')[0])

def getOcclusion(camref, behind, full_pc2d, pc3di, bbx):
  (oid,l,x1,y1,x2,y2)=bbx
  inter=5 # resolution of the grid
  d=0.1# distance beyond we consider that a point does not belong anymore to an object
  xs=range(int(x1),int(x2),int((x2-x1)/inter))
  ys=range(int(y1),int(y2),int((y2-y1)/inter))
  occlus_count=0
  obj_idx=np.zeros((1, len(behind)), dtype=bool)
  obj_idx[[0],[pc3di]]=True
  oclus=0
  outsideobject=0
  for i in range(len(xs)-1):
    for j in range(len(ys)-1):
      all_idx=np.logical_and( xs[i]<full_pc2d[0] , full_pc2d[0]<xs[i+1])
      all_idx=np.logical_and(all_idx, ys[j]<full_pc2d[1])
      all_idx=np.logical_and( all_idx, full_pc2d[1]<ys[j+1])
      all_idx=np.logical_and(all_idx, np.logical_not(behind) ) # Collecting point cloud inside this rectangle and not begind the camera
      o_idx=np.logical_and( all_idx, obj_idx) # selecting the 2D points which are inside the rectangle and belong to the object
      all_idx=np.logical_and(all_idx,np.logical_not(obj_idx))# removing the points linked to the object
      if not o_idx.any() or not all_idx.any():
        if not o_idx.any():
          outsideobject+=1 # this part of the bounding box does not contain object points, so we don't count it
        continue # no object points for this rectangle, or no point who does not belong to the object
      o_depth=np.min(np.linalg.norm(camref[0:3,o_idx[0,:]],axis=0))/3 #mean depth of the object for this rectangle
      if sum((o_depth-np.linalg.norm(camref[0:3,all_idx[0,:]],axis=0)/3)>d)>0:# if any point not from the object is in front (i.e. has a lower depth) of the object and make an occlusion ...
        oclus+=1 # ... we count this part as occluded
  if ((len(xs)-1)*(len(ys)-1)-outsideobject)==0:
    print('something is wrong: no points projected on the bbx')
    return 1
  return float(oclus)/((len(xs)-1)*(len(ys)-1)-outsideobject)

# main code
input_sequences = glob.glob('/home/.../3rscan/sequence/*')
scene_list = [i.split('/')[-1] for i in input_sequences]
datadir = '/home/.../3rscan/sequence' 
outdir = '/home/.../3rscan/2dgtwithbboxes' 
# CONVERT PLY TO XYZ
for ply in input_ply:
    if os.path.isfile(ply.split('ply')[0]+'xyz'):
        print('file exists, skipping', ply.split('ply')[0]+'xyz')
        continue
    d = meshio.read(ply)
    np.savetxt(ply.split('ply')[0]+'xyz', d.points, fmt='%1.6f')
c = 0
for scene in scene_list:
    if os.path.isfile(outdir+'/'+scene+'.2dgt'): #seq.split('/')[-1]+'.2dgt'):
        print('file exists, skipping', scene)  #seq.split('/')[-1])
        continue
 # read *.semseg.json
    ag_f = datadir+'/'+scene+'/semseg.json' # seq+'/semseg.json' 
    if not os.path.isfile(ag_f):
        print('no *semseg.json file found for the scene', ag_f)
        continue
    fp = open(ag_f)
    aggreg = json.load(fp)
    fp.close()
    
    objs = {} # will contain the objects for this scene
    seg_f = datadir+'/'+scene+'/mesh.refined.0.010000.segs.json' # seq+'/mesh.refined.0.010000.segs.json'
    if not os.path.isfile(seg_f):
        print('no mesh.refined.0.010000.segs.json file found for the scene', seg_f)
        continue
    f = open(seg_f)
    segs = json.load(f)
    f.close

     # read *.xyz and append them into 3D point cloud 
    xyz_f = datadir+'/'+scene+'/labels.instances.annotated.xyz' # seq+'/labels.instances.annotated.xyz'
    if not os.path.isfile(xyz_f):
        print('no XYZ file found for the scene', xyz_f)
        continue
    pc3d=get_full_pc(xyz_f) #getting the full 3D point cloud
    for po in aggreg['segGroups']: # for each object in the json file
        objs[po['objectId']]=[ po['label']]# {0: 'window'}
        pc3di=[]
        for segid in po['segments']:#for each segment of the object o
            pc3di+=[x for (x,y) in enumerate(segs['segIndices']) if y==segid ] # collecting the 3D points associated to the segment segid
        objs[po['objectId']].append(pc3di)
    print('Loading 3D point cloud done, number of objects:', len(objs.keys()))
    (m_calibrationColorIntrinsic,wi,hi)=get_intrinsic_color(datadir+'/'+scene+'/sequence/_info.txt') # seq+'/sequence/_info.txt')#getting intrinsic parameter
    print('done1')
    obj_by_img={}# dictionnary that will contain the bounding boxes of the objects appearing in each image.
    for pose in glob.glob(datadir+'/'+scene+'/sequence/*pose.txt'):
        cam2world=get_pose(pose)# getting the inverse of the extrinsic parameters from the frame_0XXXX.pose.txt
        if np.logical_not(np.isfinite(cam2world)).any() or  np.isnan(cam2world).any() or cam2world.shape[0]==0:
            print('erroneous camera value, skipping', cam2world)
            continue #the values of the camera pose are wrong, so we skip
            
        world2cam=np.linalg.inv(cam2world)#getting the actual parameters
        obj_by_img[frame_num_from_name(pose)]=[pose.split('/')[-1].split('.')[0],[]] # will contain a list with two elements the name of the  frame and the list of objects bbxs 
        camref=np.dot(world2cam,np.vstack((pc3d.transpose(),np.ones((1,pc3d.shape[0])))))
        behind=camref[2]<=0 # boolean array which is true for the points which are behind the camera
        full_pc2d=np.dot(m_calibrationColorIntrinsic, camref)
        full_pc2d=np.divide(full_pc2d,np.tile(full_pc2d[2],(4,1))) #normalising the homogeneous point: [x y 1]
        for oid, (l, pc3di) in objs.items():
            if behind[pc3di].any():# if any of the object point is behind the camera, we skip
                continue
            rows=np.array( [len(pc3di)*[0], len(pc3di)*[1]] )
            cols=np.array([pc3di,pc3di])
            pc2d=full_pc2d[rows,cols]   # get the points related to the objects, from the indices
            (x1,y1,x2,y2)=(min(pc2d[0]),min(pc2d[1]),max(pc2d[0]),max(pc2d[1])) # getting the bounding box coordinate
            if x1<0 or y1<0 or wi<x2 or hi<y2 or int(x2-x1)<5 or int(y2-y1)<5: # I don't keep it if the bounding box is outside the image or if the object is small on the image
                continue
            
            o=getOcclusion(camref, behind, full_pc2d, pc3di, (oid,l,x1,y1,x2,y2))  
            obj_by_img[frame_num_from_name(pose)][1].append([oid,l,o,x1,y1,x2,y2]) #note here I am saving only the bounding box coordinate. You might want to add the full 2D point cloud
                
    print('Sampiyon Besiktas', c)
    c += 1
#    import pdb; pdb.set_trace()
    fw=open(outdir+'/'+scene+'.2dgt','w')# writting the results
    for (fnum,v) in obj_by_img.items():
        if len(v)==1:
            continue
        fn = v[0]
        for detection in v[1]:
#            detection[1] = detection[1].encode('utf8')
#            fw.write(' '.join([fn]+[str(x).replace(' ','_') for x in detection ])+'\n')
            print('%s %d %s %1.3f %1.6f %1.6f %1.6f %1.6f' % ('frame-'+'%0.6d'% (fnum), int(detection[0]), str(detection[1]), float(detection[2]), float(detection[3]), 
                                                           float(detection[4]), float(detection[5]), float(detection[6])),file=fw)