def track_and_label_objects(video_info):
previous_frame= None
previous_num_obj=-1
cropped_img_array=[]
tracked_video=[]
for frame_info in video_info:
print "Tracking Frame Nr: %d"%frame_info.frame
print len(frame_info.rects)
current_frame = frame.Frame_Info()
current_frame=frame_info.duplicate()
current_frame.rects=[]
print len(frame_info.rects)
if previous_frame is not None:
print "Previous Frame obj:%d"%previous_num_obj
for rect in frame_info.rects:
print "Entered into the rect check"
max_rect=None
max_iou=0
current_rect= Rectangle_Multiclass()
trackID=-1
if previous_num_obj >0: ### If i come here means that there's the same number of object between the previous and the current frame
print "Entered into the rect check with :%d objects"%previous_num_obj
id_rect=0
max_id=0
for prev_rect in previous_frame.rects:
print "Entered"
if rect.iou(prev_rect)>max_iou:
max_iou=rect.iou(prev_rect)
max_id=id_rect
id_rect=id_rect+1
print "Lenght previous rects array: %d"%len(previous_frame.rects)
print "max_rect track ID: %d"%previous_frame.rects[max_id].trackID
print "max_rect label: %s"%previous_frame.rects[max_id].label
current_rect.load_labeled_rect(previous_frame.rects[max_id].trackID, previous_frame.rects[max_id].true_confidence, previous_frame.rects[max_id].label_confidence, previous_frame.rects[max_id].x1,previous_frame.rects[max_id].y1,previous_frame.rects[max_id].x2 ,previous_frame.rects[max_id].y2, previous_frame.rects[max_id].label, previous_frame.rects[max_id].label_chall, previous_frame.rects[max_id].label_code)
current_frame.append_labeled_rect(current_rect)
rect.load_label(previous_frame.rects[max_id].trackID,previous_frame.rects[max_id].label_confidence, previous_frame.rects[max_id].label, previous_frame.rects[max_id].label_chall, previous_frame.rects[max_id].label_code)
previous_frame.rects.pop(max_id)
previous_num_obj=previous_num_obj-1
else:
### If i come here means that there's more objects in the current frame respect to che previous
if previous_num_obj == 0:
trackID = len(frame_info.rects)
previous_num_obj = -1
current_rect= Rectangle_Multiclass()
img= Image.open(frame_info.filename)
cor = (rect.x1,rect.y1,rect.x2 ,rect.y2)
cropped_img=img.crop(cor)
cropped_img_name="cropped_frame_%d.JPEG"%(frame_info.frame)
cropped_img.save(cropped_img_name)
cropped_img_array.append(cropped_img_name)
label, confidence = Utils_Imagenet.run_inception_once(cropped_img_name)
rect.load_label(trackID,confidence, vid_classes.code_to_class_string(label), vid_classes.code_to_code_chall(vid_classes), label)
current_rect.load_labeled_rect(trackID, rect.true_confidence, confidence, rect.x1,rect.y1,rect.x2 ,rect.y2, vid_classes.code_to_class_string(label), vid_classes.code_to_code_chall(vid_classes), label)
print "current_rect track ID: %d"%current_rect.trackID
print "current_rect label: %s"%current_rect.label
current_frame.append_labeled_rect(current_rect)
else:
trackID=1
for rect in frame_info.rects:
current_rect= Rectangle_Multiclass()
img= Image.open(frame_info.filename)
cor = (rect.x1,rect.y1,rect.x2 ,rect.y2)
cropped_img=img.crop(cor)
cropped_img_name="cropped_frame_%d.JPEG"%(frame_info.frame)
cropped_img.save(cropped_img_name)
cropped_img_array.append(cropped_img_name)
label, confidence = Utils_Imagenet.run_inception_once(cropped_img_name)
rect.load_label(trackID,confidence, vid_classes.code_to_class_string(label), vid_classes.code_to_code_chall(vid_classes), label)
current_rect.load_labeled_rect(trackID, rect.true_confidence, confidence, rect.x1,rect.y1,rect.x2 ,rect.y2, vid_classes.code_to_class_string(label), vid_classes.code_to_code_chall(vid_classes), label)
current_frame.append_labeled_rect(current_rect)
trackID=trackID+1
previous_num_obj=len(frame_info.rects)
previous_frame=frame_info.duplicate()
previous_frame.duplicate_rects(frame_info.rects)
print previous_frame
print "Previous Frame obj:%d"%previous_num_obj
print "prev_rect 0 track ID: %d"%previous_frame.rects[0].trackID
print "prev_rect 0 label: %s"%previous_frame.rects[0].label
tracked_video.insert(len(tracked_video), current_frame)
return tracked_video
def parse_XML_to_multiclass_txt(bb_XML_file_list, path_val_folder,
path_dataset):
count_rect = 0
count_img = 0
progress = progressbar.ProgressBar(widgets=[
progressbar.Bar('=', '[', ']'), ' ',
progressbar.Percentage(), ' ',
progressbar.ETA()
])
print "Start Processing & Building the MultiClass Dataset... May take a while..."
path_mltcl_bb_file = path_dataset + '/' + string_mltcl_bb_file # Create this file in .dataset/airplane/airplane_bb_mltcl_file_list.txt
path_mltcl_class_code_file = path_dataset + '/' + string_mltcl_class_code_file
path_mltcl_class_name_file = path_dataset + '/' + string_mltcl_class_name_file
path_mltcl_chall_code_file = path_dataset + '/' + string_mltcl_chall_code_file
for file_name in progress(bb_XML_file_list):
with open(file_name, 'rt') as f:
tree = ElementTree.parse(f)
for obj in tree.findall('object'):
name = obj.find('name').text
class_code = name
name = vid_classes.code_to_class_string(name)
if name in ["nothing"]:
continue
else:
path_orig_file = path_val_folder
jump = 0
image_multi_class = Frame_Info()
image_multi_class.dataset_path = path_val_folder
rectangle_multi = Rectangle_Multiclass()
#xmin x1 letf
#ymin y1 bottom
#xmax x2 right
#ymax y2 top
for node in tree.iter():
tag = str(node.tag)
if tag in ["folder"]:
path_orig_file = path_orig_file + '/' + str(
node.text)
image_multi_class.folder = str(node.text)
if tag in ["filename"]:
image_multi_class.filename = str(
node.text) + '.PNG'
path_orig_file = path_orig_file + '/' + str(
node.text) + '.JPEG'
if tag in ["width"]:
image_multi_class.width = int(node.text)
if tag in ["height"]:
image_multi_class.height = int(node.text)
if tag in ["trackid"]:
image_multi_class.frame = int(
os.path.basename(file_name).replace(
'.xml', ''))
if tag in ['name']:
if str(
vid_classes.code_to_class_string(
str(node.text))) in ["nothing"]:
jump = 1
else:
jump = 0
print str(node.text)
rectangle_multi.label_chall = int(
vid_classes.code_to_code_chall(
str(node.text)))
rectangle_multi.label_code = str(node.text)
rectangle_multi.label = vid_classes.code_to_class_string(
str(node.text))
if tag in ["xmax"]:
if jump == 0:
rectangle_multi.x2 = float(
utils_image.transform_point(
image_multi_class.width,
image_multi_class.height, width,
height, float(node.text), True))
if tag in ["xmin"]:
if jump == 0:
rectangle_multi.x1 = float(
utils_image.transform_point(
image_multi_class.width,
image_multi_class.height, width,
height, float(node.text), True))
if tag in ["ymin"]:
if jump == 0:
rectangle_multi.y2 = float(
utils_image.transform_point(
image_multi_class.width,
image_multi_class.height, width,
height, float(node.text), False))
if tag in ["ymax"]:
if jump == 0:
rectangle_multi.y1 = float(
utils_image.transform_point(
image_multi_class.width,
image_multi_class.height, width,
height, float(node.text), False))
image_multi_class.append_rect(rectangle_multi)
count_rect = count_rect + 1
if jump == 0:
count_img = count_img + 1
out_stream = open(path_mltcl_bb_file, "a")
out_stream.write(image_multi_class.get_info_string() +
os.linesep)
out_stream = open(path_mltcl_class_code_file, "a")
out_stream.write(image_multi_class.get_rects_code() +
os.linesep)
out_stream = open(path_mltcl_class_name_file, "a")
out_stream.write(image_multi_class.get_rects_labels() +
os.linesep)
out_stream = open(path_mltcl_chall_code_file, "a")
out_stream.write(image_multi_class.get_rects_chall() +
os.linesep)
break
out_stream = open('dataset/summary_multiclass.txt', "w")
out_stream.write("SUMMARY:" + os.linesep +
("Parsed: %d BB Files" % len(bb_XML_file_list)) +
os.linesep +
("Added: %d Object Rectangles" % count_rect) +
os.linesep + ("Added: %d Images" % count_img) +
os.linesep)
print "Ended with Success the Process"
print "SUMMARY:"
print "Parsed: %d BB Files" % len(bb_XML_file_list)
print "Added: %d Object Rectangles" % count_rect
print "Added: %d Images" % count_img
if count_img > 0:
print "Ratio BB_Files/Images: %.2f" % (float(count_img) /
float(len(bb_XML_file_list)))
out_stream.write(("Ratio BB_Files/Images: %.2f" %
(float(count_img) / float(len(bb_XML_file_list)))) +
os.linesep)
if count_rect > 0:
print "Ratio Images/Object_Rectangles: %.2f" % (float(count_img) /
float(count_rect))
out_stream.write(("Ratio Images/Object_Rectangles: %.2f" %
(float(count_img) / float(count_rect))) + os.linesep)
def track_and_label_objects(video_info):
previous_frame = None
previous_num_obj = -1
cropped_img_array = []
tracked_video = []
for frame_info in video_info:
print("Tracking Frame Nr: %d" % frame_info.frame)
print(len(frame_info.rects))
current_frame = frame.Frame_Info()
current_frame = frame_info.duplicate()
current_frame.rects = []
print(len(frame_info.rects))
if previous_frame is not None:
print("Previous Frame obj:%d" % previous_num_obj)
for rect in frame_info.rects:
print("Entered into the rect check")
max_rect = None
max_iou = 0
current_rect = Rectangle_Multiclass()
trackID = -1
if previous_num_obj > 0: ### If i come here means that there's the same number of object between the previous and the current frame
print("Entered into the rect check with :%d objects" %
previous_num_obj)
id_rect = 0
max_id = 0
for prev_rect in previous_frame.rects:
print("Entered")
if rect.iou(prev_rect) > max_iou:
max_iou = rect.iou(prev_rect)
max_id = id_rect
id_rect = id_rect + 1
print("Lenght previous rects array: %d" %
len(previous_frame.rects))
print("max_rect track ID: %d" %
previous_frame.rects[max_id].trackID)
print("max_rect label: %s" %
previous_frame.rects[max_id].label)
current_rect.load_labeled_rect(
previous_frame.rects[max_id].trackID,
previous_frame.rects[max_id].true_confidence,
previous_frame.rects[max_id].label_confidence,
previous_frame.rects[max_id].x1,
previous_frame.rects[max_id].y1,
previous_frame.rects[max_id].x2,
previous_frame.rects[max_id].y2,
previous_frame.rects[max_id].label,
previous_frame.rects[max_id].label_chall,
previous_frame.rects[max_id].label_code)
current_frame.append_labeled_rect(current_rect)
rect.load_label(
previous_frame.rects[max_id].trackID,
previous_frame.rects[max_id].label_confidence,
previous_frame.rects[max_id].label,
previous_frame.rects[max_id].label_chall,
previous_frame.rects[max_id].label_code)
previous_frame.rects.pop(max_id)
previous_num_obj = previous_num_obj - 1
else:
### If i come here means that there's more objects in the current frame respect to che previous
if previous_num_obj == 0:
trackID = len(frame_info.rects)
previous_num_obj = -1
current_rect = Rectangle_Multiclass()
img = Image.open(frame_info.filename)
cor = (rect.x1, rect.y1, rect.x2, rect.y2)
cropped_img = img.crop(cor)
cropped_img_name = "cropped_frame_%d.JPEG" % (
frame_info.frame)
cropped_img.save(cropped_img_name)
cropped_img_array.append(cropped_img_name)
label, confidence = Utils_Imagenet.run_inception_once(
cropped_img_name)
rect.load_label(
trackID, confidence,
vid_classes.code_to_class_string(label),
vid_classes.code_to_code_chall(vid_classes), label)
current_rect.load_labeled_rect(
trackID, rect.true_confidence, confidence, rect.x1,
rect.y1, rect.x2, rect.y2,
vid_classes.code_to_class_string(label),
vid_classes.code_to_code_chall(vid_classes), label)
print("current_rect track ID: %d" % current_rect.trackID)
print("current_rect label: %s" % current_rect.label)
current_frame.append_labeled_rect(current_rect)
else:
trackID = 1
for rect in frame_info.rects:
current_rect = Rectangle_Multiclass()
img = Image.open(frame_info.filename)
cor = (rect.x1, rect.y1, rect.x2, rect.y2)
cropped_img = img.crop(cor)
cropped_img_name = "cropped_frame_%d.JPEG" % (frame_info.frame)
cropped_img.save(cropped_img_name)
cropped_img_array.append(cropped_img_name)
label, confidence = Utils_Imagenet.run_inception_once(
cropped_img_name)
rect.load_label(trackID, confidence,
vid_classes.code_to_class_string(label),
vid_classes.code_to_code_chall(vid_classes),
label)
current_rect.load_labeled_rect(
trackID, rect.true_confidence, confidence, rect.x1,
rect.y1, rect.x2, rect.y2,
vid_classes.code_to_class_string(label),
vid_classes.code_to_code_chall(vid_classes), label)
current_frame.append_labeled_rect(current_rect)
trackID = trackID + 1
previous_num_obj = len(frame_info.rects)
previous_frame = frame_info.duplicate()
previous_frame.duplicate_rects(frame_info.rects)
print(previous_frame)
print("Previous Frame obj:%d" % previous_num_obj)
print("prev_rect 0 track ID: %d" % previous_frame.rects[0].trackID)
print("prev_rect 0 label: %s" % previous_frame.rects[0].label)
tracked_video.insert(len(tracked_video), current_frame)
return tracked_video
def parse_XML_to_multiclass_txt(bb_XML_file_list, path_val_folder, path_dataset):
count_rect=0
count_img=0
progress = progressbar.ProgressBar(widgets=[progressbar.Bar('=', '[', ']'), ' ',progressbar.Percentage(), ' ',progressbar.ETA()])
print "Start Processing & Building the MultiClass Dataset... May take a while..."
path_mltcl_bb_file=path_dataset+'/'+string_mltcl_bb_file # Create this file in .dataset/airplane/airplane_bb_mltcl_file_list.txt
path_mltcl_class_code_file=path_dataset+'/'+string_mltcl_class_code_file
path_mltcl_class_name_file=path_dataset+'/'+string_mltcl_class_name_file
path_mltcl_chall_code_file=path_dataset+'/'+string_mltcl_chall_code_file
for file_name in progress(bb_XML_file_list):
with open(file_name, 'rt') as f:
tree = ElementTree.parse(f)
for obj in tree.findall('object'):
name = obj.find('name').text
class_code= name
name = vid_classes.code_to_class_string(name)
if name in ["nothing"]:
continue
else:
path_orig_file=path_val_folder
jump=0
image_multi_class= Frame_Info()
image_multi_class.dataset_path= path_val_folder
rectangle_multi= Rectangle_Multiclass()
#xmin x1 letf
#ymin y1 bottom
#xmax x2 right
#ymax y2 top
for node in tree.iter():
tag=str(node.tag)
if tag in ["folder"]:
path_orig_file=path_orig_file+'/'+str(node.text)
image_multi_class.folder= str(node.text)
if tag in ["filename"]:
image_multi_class.filename=str(node.text)+'.PNG'
path_orig_file=path_orig_file+'/'+str(node.text)+'.JPEG'
if tag in ["width"]:
image_multi_class.width= int(node.text)
if tag in ["height"]:
image_multi_class.height= int(node.text)
if tag in ["trackid"]:
image_multi_class.frame= int(os.path.basename(file_name).replace('.xml', ''))
if tag in ['name']:
if str(vid_classes.code_to_class_string(str(node.text))) in ["nothing"]:
jump = 1
else :
jump=0
print str(node.text)
rectangle_multi.label_chall=int(vid_classes.code_to_code_chall(str(node.text)))
rectangle_multi.label_code=str(node.text)
rectangle_multi.label=vid_classes.code_to_class_string(str(node.text))
if tag in ["xmax"]:
if jump == 0:
rectangle_multi.x2=float(utils_image.transform_point(image_multi_class.width,image_multi_class.height,width, height,float(node.text), True))
if tag in ["xmin"]:
if jump == 0:
rectangle_multi.x1=float(utils_image.transform_point(image_multi_class.width,image_multi_class.height,width, height,float(node.text), True))
if tag in ["ymin"]:
if jump == 0:
rectangle_multi.y2=float(utils_image.transform_point(image_multi_class.width,image_multi_class.height,width, height,float(node.text), False))
if tag in ["ymax"]:
if jump == 0:
rectangle_multi.y1=float(utils_image.transform_point(image_multi_class.width,image_multi_class.height,width, height,float(node.text), False))
image_multi_class.append_rect(rectangle_multi)
count_rect=count_rect+1
if jump == 0:
count_img=count_img+1
out_stream = open(path_mltcl_bb_file, "a")
out_stream.write(image_multi_class.get_info_string()+ os.linesep)
out_stream = open(path_mltcl_class_code_file, "a")
out_stream.write(image_multi_class.get_rects_code()+ os.linesep)
out_stream = open(path_mltcl_class_name_file, "a")
out_stream.write(image_multi_class.get_rects_labels()+ os.linesep)
out_stream = open(path_mltcl_chall_code_file, "a")
out_stream.write(image_multi_class.get_rects_chall() + os.linesep)
break
out_stream = open('dataset/summary_multiclass.txt', "w")
out_stream.write( "SUMMARY:" + os.linesep+ ("Parsed: %d BB Files"%len(bb_XML_file_list)) + os.linesep+ ("Added: %d Object Rectangles"%count_rect) + os.linesep+("Added: %d Images"%count_img)+os.linesep)
print "Ended with Success the Process"
print "SUMMARY:"
print "Parsed: %d BB Files"%len(bb_XML_file_list)
print "Added: %d Object Rectangles"%count_rect
print "Added: %d Images"%count_img
if count_img>0:
print "Ratio BB_Files/Images: %.2f"%(float(count_img)/float(len(bb_XML_file_list)))
out_stream.write(("Ratio BB_Files/Images: %.2f"%(float(count_img)/float(len(bb_XML_file_list))))+os.linesep)
if count_rect>0:
print "Ratio Images/Object_Rectangles: %.2f"%(float(count_img)/float(count_rect))
out_stream.write(("Ratio Images/Object_Rectangles: %.2f"%(float(count_img)/float(count_rect)))+os.linesep)