161 lines
5.0 KiB
Python
161 lines
5.0 KiB
Python
import cv2 as cv
|
|
import argparse
|
|
import numpy as np
|
|
import os.path
|
|
import sys
|
|
import random
|
|
|
|
# Inicjalizacja parametrów
|
|
confThreshold = 0.5
|
|
maskThreshold = 0.3
|
|
|
|
args = parser.parse_args()
|
|
|
|
# Rysuje obrawmowanie zwierzęcia, koloruje i zaznacza maską
|
|
def drawBox(frame, classId, conf, left, top, right, bottom, classMask):
|
|
# obramowanie.
|
|
cv.rectangle(frame, (left, top), (right, bottom), (255, 178, 50), 3)
|
|
|
|
# etykieta obiektu
|
|
label = '%.2f' % conf
|
|
if classes:
|
|
assert(classId < len(classes))
|
|
label = '%s:%s' % (classes[classId], label)
|
|
|
|
# wyświetla etykietę
|
|
labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
|
|
top = max(top, labelSize[1])
|
|
cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
|
|
cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 1)
|
|
|
|
# zmiana rozmiaru maski i nałożenie na obiekt
|
|
classMask = cv.resize(classMask, (right - left + 1, bottom - top + 1))
|
|
mask = (classMask > maskThreshold)
|
|
roi = frame[top:bottom+1, left:right+1][mask]
|
|
|
|
colorIndex = random.randint(0, len(colors)-1)
|
|
color = colors[colorIndex]
|
|
|
|
frame[top:bottom+1, left:right+1][mask] = ([0.3*color[0], 0.3*color[1], 0.3*color[2]] + 0.7 * roi).astype(np.uint8)
|
|
|
|
# rysuje kontury na obrazie
|
|
mask = mask.astype(np.uint8)
|
|
im2, contours, hierarchy = cv.findContours(mask,cv.RETR_TREE,cv.CHAIN_APPROX_SIMPLE)
|
|
cv.drawContours(frame[top:bottom+1, left:right+1], contours, -1, color, 3, cv.LINE_8, hierarchy, 100)
|
|
|
|
# dla każdej ramki maskuje obraz
|
|
def postprocess(boxes, masks):
|
|
# N - liczba znalezionych obramowań
|
|
# C - liczba klas
|
|
# H,W- wysokość i szerokość
|
|
numClasses = masks.shape[1]
|
|
numDetections = boxes.shape[2]
|
|
|
|
frameH = frame.shape[0]
|
|
frameW = frame.shape[1]
|
|
|
|
for i in range(numDetections):
|
|
box = boxes[0, 0, i]
|
|
mask = masks[i]
|
|
score = box[2]
|
|
if score > confThreshold:
|
|
classId = int(box[1])
|
|
|
|
# zaznacza ramkę
|
|
left = int(frameW * box[3])
|
|
top = int(frameH * box[4])
|
|
right = int(frameW * box[5])
|
|
bottom = int(frameH * box[6])
|
|
|
|
left = max(0, min(left, frameW - 1))
|
|
top = max(0, min(top, frameH - 1))
|
|
right = max(0, min(right, frameW - 1))
|
|
bottom = max(0, min(bottom, frameH - 1))
|
|
|
|
# aktywacja maski
|
|
classMask = mask[classId]
|
|
|
|
# rysuje wszystko na obrazie
|
|
drawBox(frame, classId, score, left, top, right, bottom, classMask)
|
|
|
|
|
|
# załaduj nazwy
|
|
classesFile = "labels.names";
|
|
classes = None
|
|
with open(classesFile, 'rt') as f:
|
|
classes = f.read().rstrip('\n').split('\n')
|
|
|
|
# uruchomienie grafu tekstowego i modelu wagi
|
|
textGraph = "./mask.pbtxt";
|
|
modelWeights = "./mask/frozen_inference_graph.pb";
|
|
|
|
# Załadowanie z sieci
|
|
#net = cv.dnn.readNetFromTensorflow(modelWeights, textGraph);
|
|
#net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
|
|
#net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
|
|
|
|
# załadowanie klas
|
|
colorsFile = "colors.txt";
|
|
with open(colorsFile, 'rt') as f:
|
|
colorsStr = f.read().rstrip('\n').split('\n')
|
|
colors = [] #[0,0,0]
|
|
for i in range(len(colorsStr)):
|
|
rgb = colorsStr[i].split(' ')
|
|
color = np.array([float(rgb[0]), float(rgb[1]), float(rgb[2])])
|
|
colors.append(color)
|
|
|
|
winName = 'Animal finding program'
|
|
cv.namedWindow(winName, cv.WINDOW_NORMAL)
|
|
|
|
outputFile = "found_animal.avi"
|
|
if (args.image):
|
|
# Otrwiera pllik z obrazem
|
|
if not os.path.isfile(args.image):
|
|
print("Input image file ", args.image, " doesn't exist")
|
|
sys.exit(1)
|
|
cap = cv.VideoCapture(args.image)
|
|
outputFile = args.image[:-4]+'found_animal.jpg'
|
|
elif (args.video):
|
|
# Otwiera plik video
|
|
if not os.path.isfile(args.video):
|
|
print("Input video file ", args.video, " doesn't exist")
|
|
sys.exit(1)
|
|
cap = cv.VideoCapture(args.video)
|
|
outputFile = args.video[:-4]+'found_animal.avi'
|
|
|
|
|
|
# inicjalizacja zapisu video
|
|
if (not args.image):
|
|
vid_writer = cv.VideoWriter(outputFile, cv.VideoWriter_fourcc('M','J','P','G'), 28, (round(cap.get(cv.CAP_PROP_FRAME_WIDTH)),round(cap.get(cv.CAP_PROP_FRAME_HEIGHT))))
|
|
|
|
while cv.waitKey(1) < 0:
|
|
|
|
hasFrame, frame = cap.read()
|
|
|
|
# zamyka program, gdy skończy się film
|
|
if not hasFrame:
|
|
print("Processing Done.")
|
|
print("Output file saved ad: ", outputFile)
|
|
cv.waitKey(3000)
|
|
break
|
|
|
|
# Utworzenie boxa
|
|
blob = cv.dnn.blobFromImage(frame, swapRB=True, crop=False)
|
|
net.setInput(blob)
|
|
|
|
# Uruchomienie przekazanie, aby uzyskać dane wyjściowe
|
|
boxes, masks = net.forward(['detection_out_final', 'detection_masks'])
|
|
|
|
# Wyrzuca obramowanie i maskę dla każdego wykrytego obiektu
|
|
postprocess(boxes, masks)
|
|
|
|
# Zapisuje obraz z obramowaniami
|
|
if (args.image):
|
|
cv.imwrite(outputFile, frame.astype(np.uint8));
|
|
else:
|
|
vid_writer.write(frame.astype(np.uint8))
|
|
|
|
cv.imshow(winName, frame)
|
|
|
|
|