yolo_click_crop2.py

# import the necessary packages
import numpy as np
import argparse
import time
import cv2
import os
from math import hypot

## FUNCTIONS

#CLICK CROP
refPt = []
cropping = False
def click_and_crop(event, x, y, flags, param):
	# grab references to the global variables
	global refPt, cropping
	# if the left mouse button was clicked, record the starting
	# (x, y) coordinates and indicate that cropping is being
	# performed
	if event == cv2.EVENT_LBUTTONDOWN:
		refPt = [(x, y)]
		cropping = True
	# check to see if the left mouse button was released
	elif event == cv2.EVENT_LBUTTONUP:
		# record the ending (x, y) coordinates and indicate that
		# the cropping operation is finished
		refPt.append((x, y))
		cropping = False
		# draw a rectangle around the region of interest
		cv2.rectangle(image, refPt[0], refPt[1], (0, 255, 0), 2)
		cv2.imshow("image", image)

def distance(p1,p2):
#"""Euclidean distance between two points."""
	xx1, yy1 = p1
	xx2, yy2 = p2
	return hypot(xx2 - xx1, yy2 - yy1)
##################################################################################################################

# 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("-y", "--yolo", required=True,
	help="base path to YOLO 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="threshold when applying non-maxima suppression")
args = vars(ap.parse_args())

# load the COCO class labels our YOLO model was trained on
labelsPath = os.path.sep.join([args["yolo"], "coco.names"])
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 YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])
# load our YOLO object detector trained on COCO dataset (80 classes)
print("[INFO] loading YOLO from disk...")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)

# load our input image and grab its spatial dimensions
image = cv2.imread(args["image"])
clone = image.copy()

(H, W) = image.shape[:2]
# determine only the *output* layer names that we need from YOLO
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# construct a blob from the input image and then perform a forward
# pass of the YOLO object detector, giving us our bounding boxes and
# associated probabilities
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416), swapRB=True, crop=False)
net.setInput(blob)
start = time.time()
layerOutputs = net.forward(ln)
end = time.time()
# show timing information on YOLO
print("[INFO] YOLO took {:.6f} seconds".format(end - start))


# initialize our lists of detected bounding boxes, confidences, and
# class IDs, respectively
boxes = []
confidences = []
classIDs = []
centers = []

# loop over each of the layer outputs
for output in layerOutputs:
	# loop over each of the detections
	for detection in output:
		# extract the class ID and confidence (i.e., probability) of
		# the current object detection
		scores = detection[5:]
		classID = np.argmax(scores)
		confidence = scores[classID]
		# 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 image, keeping in mind that YOLO actually
			# returns the center (x, y)-coordinates of the bounding
			# box followed by the boxes' width and height
			box = detection[0:4] * np.array([W, H, W, H])
			(centerX, centerY, width, height) = box.astype("int")
			# use the center (x, y)-coordinates to derive the top and
			# and left corner of the bounding box
			x = int(centerX - (width / 2))
			y = int(centerY - (height / 2))
			# update our list of bounding box coordinates, confidences,
			# and class IDs
			boxes.append([x, y, int(width), int(height)])
			centers.append((centerX, centerY))
			confidences.append(float(confidence))
			classIDs.append(classID)


# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],args["threshold"])


# ensure at least one detection exists
if len(idxs) > 0:
	# loop over the indexes we are keeping
	for i in idxs.flatten():
		# extract the bounding box coordinates
		(x, y) = (boxes[i][0], boxes[i][1])
		(w, h) = (boxes[i][2], boxes[i][3])
		# draw a bounding box rectangle and label on the image
		color = [int(c) for c in COLORS[classIDs[i]]]
		cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
		text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
		cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)



cv2.namedWindow("image")
cv2.setMouseCallback("image", click_and_crop)

# keep looping until double click
while True:
	# display the image and wait for a keypress
	cv2.imshow("image", image)
	key = cv2.waitKey(1) & 0xFF
    #Double Click Break
	if(len(refPt)>=2):
		break


# if there are two reference points, then crop the region of interest
# from the image and display it

if len(refPt) >= 2:
	roi = clone[refPt[0][1]:refPt[1][1], refPt[0][0]:refPt[1][0]]
	x = refPt[0][0]
	y = refPt[0][1]
	click_pos = (x, y)
	distance = [distance(click_pos, x) for x in centers]
	index = distance.index(min(distance))

	print(x, y)
	print(index)
	print(LABELS[classIDs[index]])
	print()

    #CROP
	x = boxes[index][0]
	y = boxes[index][1]
	w = boxes[index][2]
	h = boxes[index][3]

	EnlargeFactor = 1.1
	x1 = round(max(x+w/2-EnlargeFactor*w/2, 1))
	y1 = round(max(y+h/2-EnlargeFactor*h/2, 1))
	x2 = round(x1 + EnlargeFactor*w)
	y2 = round(y1 + EnlargeFactor*h)

	ret = [(x1,y1)]
	ret.append((x2, y2))
	roi = clone[ret[0][1]:ret[1][1], ret[0][0]:ret[1][0]]
	cv2.imshow("ROI", roi)
	cv2.imwrite("CroppedImage.png", roi)

	cv2.waitKey(0)


# close all open windows
cv2.destroyAllWindows()

#python yolo_click_crop2.py --image image_0.jpg --yolo yolo-coco
# python yolo_click_crop2.py --image image_0.jpg --yolo yolo-coco