我正在与很多人一起制作一个视频，其中很少有人穿着红色 T 恤。我使用人员检测和跟踪模型检测和跟踪了所有人员。如何区分穿红色的人和其他人。
我正在阅读 OpenCV 格式的帧。如果我知道坐标，假设 x,y 是颜色为红色的身体坐标。如何从 OpenCV 格式的坐标中获取颜色信息并检查是否在红色范围内？
我只需要突出显示其他人穿着红色的人的边界框。
谁能帮我找出解决方案。 谢谢！
【问题讨论】：
标签： python image opencv image-processing pixel
将颜色空间更改为 HSV 并找到颜色的 Hue 值范围的更好方法。
我们可以使用以下代码识别图像中的人体区域
import time
import cv2
import imutils
import numpy as np
from imutils.video import FPS
# import the necessary packages
from imutils.video import VideoStream
def get_centered_contours(mask):
# find contours
cntrs = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
sorted_contours = sorted(cntrs, key=cv2.contourArea, reverse=True)
filterd_contours = []
if sorted_contours != []:
for k in range(len(sorted_contours)):
if cv2.contourArea(sorted_contours[k]) < 1000.0:
filterd_contours = sorted_contours[0:k]
return filterd_contours
return filterd_contours
def check_red_colour_person(roi):
hsv = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
# define range of blue color in HSV
lower_red = np.array([0, 50, 50])
upper_red = np.array([10, 255, 255])
# Threshold the HSV image to get only blue colors
mask = cv2.inRange(hsv, lower_red, upper_red)
cnts = get_centered_contours(mask)
if cnts != []:
return True
else:
return False
# construct the argument parse and parse the arguments
prototxt = 'MobileNetSSD_deploy.prototxt.txt'
model = 'MobileNetSSD_deploy.caffemodel'
confidence_level = 0.8
# initialize the list of class labels MobileNet SSD was trained to
# detect, then generate a set of bounding box colors for each class
CLASSES = ["person"]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(prototxt, model)
# initialize the video stream, allow the cammera sensor to warmup,
# and initialize the FPS counter
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
time.sleep(2.0)
fps = FPS().start()
# loop over the frames from the video stream
while True:
try:
# grab the frame from the threaded video stream and resize it
# to have a maximum width of 400 pixels
frame = vs.read()
frame = imutils.resize(frame, width=400)
# grab the frame dimensions and convert it to a blob
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),
0.007843, (300, 300), 127.5)
# pass the blob through the network and obtain the detections and
# predictions
net.setInput(blob)
detections = net.forward()
# loop over the detections
for i in np.arange(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with
# the prediction
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the `confidence` is
# greater than the minimum confidence
if confidence > confidence_level:
# extract the index of the class label from the
# `detections`, then compute the (x, y)-coordinates of
# the bounding box for the object
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
roi = frame[startY:endY, startX:endX]
# cv2.imwrite('roi_{}_{}_{}_{}.png'.format(startX,startY,endX,endY),roi)
if check_red_colour_person(roi):
label = "{}: {:.2f}%".format(' Red T-shirt person',
confidence * 100)
cv2.imwrite(
'Red-T-shirt_guy_{}_{}_{}_{}.png'.format(startX, startY, endX,
endY), roi)
cv2.rectangle(frame, (startX, startY), (endX, endY),
(0, 0, 255), 2)
else:
cv2.rectangle(frame, (startX, startY), (endX, endY),
(255, 0, 0), 2)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(frame, label, (startX, y),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# update the FPS counter
fps.update()
except Exception as e:
print("Exception is occured")
continue
# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()
【讨论】：
您可以设置颜色边界
boundaries = [
([17, 15, 100], [50, 56, 200])]
所以这里是元组 ([17, 15, 100], [50, 56, 200])。
在这里，我们是说图像中所有具有 R >= 100、B >= 15 和 G >= 17 以及 R
你可以像下面这样实现：
for (lower, upper) in boundaries:
lower = np.array(lower, dtype = "uint8")
upper = np.array(upper, dtype = "uint8")
# find the colors within the specified boundaries and apply
# the mask
mask = cv2.inRange(image, lower, upper)
output = cv2.bitwise_and(image, image, mask = mask)
# show the images
cv2.imshow("images", np.hstack([image, output]))
【讨论】：