Mask R-CNN

# USAGE
# python mask_rcnn.py --mask-rcnn mask-rcnn-coco --image images/example_01.jpg
# python mask_rcnn.py --mask-rcnn mask-rcnn-coco --image images/example_03.jpg --visualize 1
 
# import the necessary packages
import numpy as np
import argparse
import random
import time
import cv2
import os
 
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
	help="path to input image")
ap.add_argument("-m", "--mask-rcnn", required=True,
	help="base path to mask-rcnn directory")
ap.add_argument("-v", "--visualize", type=int, default=0,
	help="whether or not we are going to visualize each instance")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
	help="minimum probability to filter weak detections")
ap.add_argument("-t", "--threshold", type=float, default=0.3,
	help="minimum threshold for pixel-wise mask segmentation")
args = vars(ap.parse_args())
 
# load the COCO class labels our Mask R-CNN was trained on
labelsPath = os.path.sep.join([args["mask_rcnn"],
	"object_detection_classes_coco.txt"])
LABELS = open(labelsPath).read().strip().split("\n")
 
# load the set of colors that will be used when visualizing a given
# instance segmentation
colorsPath = os.path.sep.join([args["mask_rcnn"], "colors.txt"])
COLORS = open(colorsPath).read().strip().split("\n")
COLORS = [np.array(c.split(",")).astype("int") for c in COLORS]
COLORS = np.array(COLORS, dtype="uint8")
 
# derive the paths to the Mask R-CNN weights and model configuration
weightsPath = os.path.sep.join([args["mask_rcnn"],
	"frozen_inference_graph.pb"])
configPath = os.path.sep.join([args["mask_rcnn"],
	"mask_rcnn_inception_v2_coco_2018_01_28.pbtxt"])
 
# load our Mask R-CNN trained on the COCO dataset (90 classes)
# from disk
print("[INFO] loading Mask R-CNN from disk...")
net = cv2.dnn.readNetFromTensorflow(weightsPath, configPath)
 
# load our input image and grab its spatial dimensions
image = cv2.imread(args["image"])
(H, W) = image.shape[:2]
 
# construct a blob from the input image and then perform a forward
# pass of the Mask R-CNN, giving us (1) the bounding box  coordinates
# of the objects in the image along with (2) the pixel-wise segmentation
# for each specific object
blob = cv2.dnn.blobFromImage(image, swapRB=True, crop=False)
net.setInput(blob)
start = time.time()
(boxes, masks) = net.forward(["detection_out_final", "detection_masks"])
end = time.time()
 
# show timing information and volume information on Mask R-CNN
print("[INFO] Mask R-CNN took {:.6f} seconds".format(end - start))
print("[INFO] boxes shape: {}".format(boxes.shape))
print("[INFO] masks shape: {}".format(masks.shape))
 
# loop over the number of detected objects
for i in range(0, boxes.shape[2]):
	# extract the class ID of the detection along with the confidence
	# (i.e., probability) associated with the prediction
	classID = int(boxes[0, 0, i, 1])
	confidence = boxes[0, 0, i, 2]
 
	# filter out weak predictions by ensuring the detected probability
	# is greater than the minimum probability
	if confidence > args["confidence"]:
		# clone our original image so we can draw on it
		clone = image.copy()
 
		# scale the bounding box coordinates back relative to the
		# size of the image and then compute the width and the height
		# of the bounding box
		box = boxes[0, 0, i, 3:7] * np.array([W, H, W, H])
		(startX, startY, endX, endY) = box.astype("int")
		boxW = endX - startX
		boxH = endY - startY
 
		# extract the pixel-wise segmentation for the object, resize
		# the mask such that it's the same dimensions of the bounding
		# box, and then finally threshold to create a *binary* mask
		mask = masks[i, classID]
		mask = cv2.resize(mask, (boxW, boxH),
			interpolation=cv2.INTER_NEAREST)
		mask = (mask > args["threshold"])
 
		# extract the ROI of the image
		roi = clone[startY:endY, startX:endX]
 
		# check to see if are going to visualize how to extract the
		# masked region itself
		if args["visualize"] > 0:
			# convert the mask from a boolean to an integer mask with
			# to values: 0 or 255, then apply the mask
			visMask = (mask * 255).astype("uint8")
			instance = cv2.bitwise_and(roi, roi, mask=visMask)
 
			# show the extracted ROI, the mask, along with the
			# segmented instance
			cv2.imshow("ROI", roi)
			cv2.imshow("Mask", visMask)
			cv2.imshow("Segmented", instance)
 
		# now, extract *only* the masked region of the ROI by passing
		# in the boolean mask array as our slice condition
		roi = roi[mask]
 
		# randomly select a color that will be used to visualize this
		# particular instance segmentation then create a transparent
		# overlay by blending the randomly selected color with the ROI
		color = random.choice(COLORS)
		blended = ((0.4 * color) + (0.6 * roi)).astype("uint8")
 
		# store the blended ROI in the original image
		clone[startY:endY, startX:endX][mask] = blended
 
		# draw the bounding box of the instance on the image
		color = [int(c) for c in color]
		cv2.rectangle(clone, (startX, startY), (endX, endY), color, 2)
 
		# draw the predicted label and associated probability of the
		# instance segmentation on the image
		text = "{}: {:.4f}".format(LABELS[classID], confidence)
		cv2.putText(clone, text, (startX, startY - 5),
			cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
 
		# show the output image
		cv2.imwrite("Output-%s.jpg" %(i), clone)
        #cv2.imshow("Output", clone)
		cv2.waitKey(0)
 

# USAGE
# python mask_rcnn_video.py --input videos/cats_and_dogs.mp4 --output output/cats_and_dogs_output.avi --mask-rcnn mask-rcnn-coco
 
# import the necessary packages
import numpy as np
import argparse
import imutils
import time
import cv2
import os
 
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", required=True,
	help="path to input video file")
ap.add_argument("-o", "--output", required=True,
	help="path to output video file")
ap.add_argument("-m", "--mask-rcnn", required=True,
	help="base path to mask-rcnn directory")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
	help="minimum probability to filter weak detections")
ap.add_argument("-t", "--threshold", type=float, default=0.3,
	help="minimum threshold for pixel-wise mask segmentation")
args = vars(ap.parse_args())
 
# load the COCO class labels our Mask R-CNN was trained on
labelsPath = os.path.sep.join([args["mask_rcnn"],
	"object_detection_classes_coco.txt"])
LABELS = open(labelsPath).read().strip().split("\n")
 
# initialize a list of colors to represent each possible class label
np.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3),
	dtype="uint8")
 
# derive the paths to the Mask R-CNN weights and model configuration
weightsPath = os.path.sep.join([args["mask_rcnn"],
	"frozen_inference_graph.pb"])
configPath = os.path.sep.join([args["mask_rcnn"],
	"mask_rcnn_inception_v2_coco_2018_01_28.pbtxt"])
 
# load our Mask R-CNN trained on the COCO dataset (90 classes)
# from disk
print("[INFO] loading Mask R-CNN from disk...")
net = cv2.dnn.readNetFromTensorflow(weightsPath, configPath)
 
# initialize the video stream and pointer to output video file
vs = cv2.VideoCapture(args["input"])
writer = None
 
# try to determine the total number of frames in the video file
try:
	prop = cv2.cv.CV_CAP_PROP_FRAME_COUNT if imutils.is_cv2() \
		else cv2.CAP_PROP_FRAME_COUNT
	total = int(vs.get(prop))
	print("[INFO] {} total frames in video".format(total))
 
# an error occurred while trying to determine the total
# number of frames in the video file
except:
	print("[INFO] could not determine # of frames in video")
	total = -1
 
# loop over frames from the video file stream
while True:
	# read the next frame from the file
	(grabbed, frame) = vs.read()
 
	# if the frame was not grabbed, then we have reached the end
	# of the stream
	if not grabbed:
		break
 
	# construct a blob from the input frame and then perform a
	# forward pass of the Mask R-CNN, giving us (1) the bounding box
	# coordinates of the objects in the image along with (2) the
	# pixel-wise segmentation for each specific object
	blob = cv2.dnn.blobFromImage(frame, swapRB=True, crop=False)
	net.setInput(blob)
	start = time.time()
	(boxes, masks) = net.forward(["detection_out_final",
		"detection_masks"])
	end = time.time()
 
	# loop over the number of detected objects
	for i in range(0, boxes.shape[2]):
		# extract the class ID of the detection along with the
		# confidence (i.e., probability) associated with the
		# prediction
		classID = int(boxes[0, 0, i, 1])
		confidence = boxes[0, 0, i, 2]
 
		# filter out weak predictions by ensuring the detected
		# probability is greater than the minimum probability
		if confidence > args["confidence"]:
			# scale the bounding box coordinates back relative to the
			# size of the frame and then compute the width and the
			# height of the bounding box
			(H, W) = frame.shape[:2]
			box = boxes[0, 0, i, 3:7] * np.array([W, H, W, H])
			(startX, startY, endX, endY) = box.astype("int")
			boxW = endX - startX
			boxH = endY - startY
 
			# extract the pixel-wise segmentation for the object,
			# resize the mask such that it's the same dimensions of
			# the bounding box, and then finally threshold to create
			# a *binary* mask
			mask = masks[i, classID]
			mask = cv2.resize(mask, (boxW, boxH),
				interpolation=cv2.INTER_NEAREST)
			mask = (mask > args["threshold"])
 
			# extract the ROI of the image but *only* extracted the
			# masked region of the ROI
			roi = frame[startY:endY, startX:endX][mask]
 
			# grab the color used to visualize this particular class,
			# then create a transparent overlay by blending the color
			# with the ROI
			color = COLORS[classID]
			blended = ((0.4 * color) + (0.6 * roi)).astype("uint8")
 
			# store the blended ROI in the original frame
			frame[startY:endY, startX:endX][mask] = blended
 
			# draw the bounding box of the instance on the frame
			color = [int(c) for c in color]
			cv2.rectangle(frame, (startX, startY), (endX, endY),
				color, 2)
 
			# draw the predicted label and associated probability of
			# the instance segmentation on the frame
			text = "{}: {:.4f}".format(LABELS[classID], confidence)
			cv2.putText(frame, text, (startX, startY - 5),
				cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
 
	# check if the video writer is None
	if writer is None:
		# initialize our video writer
		fourcc = cv2.VideoWriter_fourcc(*"MJPG")
		writer = cv2.VideoWriter(args["output"], fourcc, 30,
			(frame.shape[1], frame.shape[0]), True)
 
		# some information on processing single frame
		if total > 0:
			elap = (end - start)
			print("[INFO] single frame took {:.4f} seconds".format(elap))
			print("[INFO] estimated total time to finish: {:.4f}".format(
				elap * total))
 
	# write the output frame to disk
	writer.write(frame)
 
# release the file pointers
print("[INFO] cleaning up...")
writer.release()
vs.release()