在屏幕而不是相机上显示蒙版对象检测

Question

所以我一直在关注this tutorial 以检测是否有人在相机上戴口罩，并使用以下代码在使用相机时让一切正常工作：

vs = cv2.VideoCapture(0)
while True:
   Frame = vs.read()

但是我希望它在显示屏而不是相机上找到检测结果，因此我将上面的代码更改为以下代码：

bounding_box = {'top': 0, 'left': 0, 'width': 1920, 'height': 1080}
sct = mss()
while True:
    sct_img = sct.grab(bounding_box)
    frame = np.array(sct_img)

我现在收到此错误

error: (-2:Unspecified error) 输入通道数应该是 3 的倍数，但在函数 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes' 中得到了 4

这里是完整的代码：

# import the necessary packages
import tensorflow as tf
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import imutils
import time
import cv2
import os
from mss import mss
from PIL import Image


def detect_and_predict_mask(frame, faceNet, maskNet):
    # grab the dimensions of the frame and then construct a blob
    # from it
    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(frame, 1.0, (224, 224),
                                 (104.0, 177.0, 123.0))


    # pass the blob through the network and obtain the face detections
    faceNet.setInput(blob)
    detections = faceNet.forward()

    # initialize our list of faces, their corresponding locations,
    # and the list of predictions from our face mask network
    faces = []
    locs = []
    preds = []

    # loop over the detections
    for i in range(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the detection
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the confidence is
        # greater than the minimum confidence
        if confidence > 0.5:
            # compute the (x, y)-coordinates of the bounding box for
            # the object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # ensure the bounding boxes fall within the dimensions of
            # the frame
            (startX, startY) = (max(0, startX), max(0, startY))
            (endX, endY) = (min(w - 1, endX), min(h - 1, endY))

            # extract the face ROI, convert it from BGR to RGB channel
            # ordering, resize it to 224x224, and preprocess it
            face = frame[startY:endY, startX:endX]
            face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
            face = cv2.resize(face, (224, 224))
            face = img_to_array(face)
            face = preprocess_input(face)

            # add the face and bounding boxes to their respective
            # lists
            faces.append(face)
            locs.append((startX, startY, endX, endY))

    # only make a predictions if at least one face was detected
    if len(faces) > 0:
    
        # for faster inference we'll make batch predictions on *all*
        # faces at the same time rather than one-by-one predictions
        # in the above `for` loop
        faces = np.array(faces, dtype="float32")
        preds = maskNet.predict(faces, batch_size=32)
        


    # return a 2-tuple of the face locations and their corresponding
    # locations
    return (locs, preds)


# load our serialized face detector model from disk
prototxtPath = r"face_detector\deploy.prototxt"
weightsPath = r"face_detector\res10_300x300_ssd_iter_140000.caffemodel"
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)
# load the face mask detector model from disk
maskNet = load_model("mask_detector.model")

# initialize the video stream
print("[INFO] starting video stream...")


bounding_box = {'top': 0, 'left': 0, 'width': 1920, 'height': 1080}

sct = mss()
# loop over the frames from the video stream
while True:
    sct_img = sct.grab(bounding_box)

    # grab the frame from the threaded video stream and resize it
    # to have a maximum width of 400 pixels
    frame = np.array(sct_img)
    #frame = imutils.resize(frame, width=1920, height=1080)

    # detect faces in the frame and determine if they are wearing a
    # face mask or not
    (locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)

    # loop over the detected face locations and their corresponding
    # locations
    for (box, pred) in zip(locs, preds):
        # unpack the bounding box and predictions
        (startX, startY, endX, endY) = box
        (mask, withoutMask) = pred

        # determine the class label and color we'll use to draw
        # the bounding box and text
        label = "Mask" if mask > withoutMask else "No Mask"
        color = (0, 255, 0) if label == "Mask" else (0, 0, 255)

        # include the probability in the label
        label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)

        # display the label and bounding box rectangle on the output
        # frame
        cv2.putText(frame, label, (startX, startY - 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
        cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)

    # show the output frame
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()

非常感谢您的帮助，因为我已经坚持了一周，并且在 google 中找到的针对此错误的解决方案对我没有帮助。

Answer 1

问题在于从 MSS 读取数据。 MSS 以 BGRA 形式（蓝色、绿色、红色、Alpha）返回原始像素。您可以从 here 阅读有关它的信息。您可以通过 cvtColor 转换为 BGR：

img=cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)