我正在研究基于 Yolo 的对象检测器，我想将它部署在视频/ipcamera 上。我使用 imutils.video 模块循环播放视频的所有帧。但结果只显示了对视频第一帧的检测。我想知道我的实现问题出在哪里，这是我的项目代码：
# import the necessary packages
from imutils.video import FPS
import numpy as np
import argparse
from sendsms import sendSMS
from datetime import datetime
import pytz
import cv2
import os
# it will get the time zone
# of the specified location
IST = pytz.timezone('Africa/Casablanca')
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-y", "--yolo", required=True,help="base path to YOLO directory")
ap.add_argument("-i", "--input", type=str, default="",help="path to (optional) input video file")
ap.add_argument("-o", "--output", type=str, default="",help="path to (optional) output video file")
ap.add_argument("-d", "--display", type=int, default=1,help="whether or not output frame should be displayed")
ap.add_argument("-c", "--confidence", type=float, default=0.3,help="minimum probability to filter weak detections")
ap.add_argument("-t", "--threshold", type=float, default=0.001,help="threshold when applying non-maxima suppression")
ap.add_argument("-u", "--use-gpu", type=bool, default=0,help="boolean indicating if CUDA GPU should be used")
args = vars(ap.parse_args())
# load the class labels our YOLO model was trained on
labelsPath = os.path.sep.join([args["yolo"], "obj.names"])
LABELS = open(labelsPath).read().strip().split("\n")
# initialize a list of colors to represent each possible class label(red and green)
COLORS = [[0,0,255],[0,255,0], [0,255,162],[0,162,255],[235,52,189],[195,235,52],[235,177,52],[235,134,52],[52,168,235],[52,168,235],[58,52,235],[70,102,11],[173,7,46],[64,11,24],[75,50,125],[50,54,125],[6,99,29],[2,245,27]]
# derive the paths to the YOLO weights and model configuration
weightsPath = os.path.sep.join([args["yolo"], "yolov4-tiny-custom_best.weights"])
configPath = os.path.sep.join([args["yolo"], "yolov4-tiny-custom.cfg"])
# load our YOLO object detector trained on mask dataset
print("[INFO] loading YOLO from disk...")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)
# determine only the *output* layer names that we need from YOLO
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# initialize the width and height of the frames in the video file
W = None
H = None
# initialize the video stream and pointer to output video file, then
# start the FPS timer
print("[INFO] accessing video stream...")
vs = WebcamVideoStream(src=0).start()
writer = None
fps = FPS.start()
# 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
# if the frame dimensions are empty, grab them
if W is None or H is None:
(H, W) = frame.shape[:2]
# construct a blob from the input frame and then perform a forward
# pass of the YOLO object detector, giving us our bounding boxes
# and associated probabilities
blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (864, 864),swapRB=True, crop=False)
net.setInput(blob)
layerOutputs = net.forward(ln)
# initialize our lists of detected bounding boxes, confidences,
# and class IDs, respectively
boxes = []
confidences = []
classIDs = []
# 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)])
confidences.append(float(confidence))
classIDs.append(classID)
# apply NMS to suppress weak, overlapping
# bounding boxes
idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],args["threshold"])
#Add top-border to frame to display stats
border_size=100
border_text_color=[255,255,255]
frame = cv2.copyMakeBorder(frame, border_size,0,0,0, cv2.BORDER_CONSTANT)
#calculate count values
filtered_classids=np.take(classIDs,idxs)
personne_count=(filtered_classids==0).sum()
casque_jaune_count=(filtered_classids==1).sum()
casque_rouge_count=(filtered_classids==2).sum()
casque_blue_count=(filtered_classids==3).sum()
casque_orange_count=(filtered_classids==4).sum()
gilet_rouge_count=(filtered_classids==5).sum()
gilet_jaune_count=(filtered_classids==6).sum()
camion_count=(filtered_classids==7).sum()
pelle_hydraulique_count=(filtered_classids==8).sum()
casque_blanc_count=(filtered_classids==9).sum()
fosse_count=(filtered_classids==10).sum()
moteur_count=(filtered_classids==11).sum()
voiture_count=(filtered_classids==12).sum()
tracteur_du_chantier_count=(filtered_classids==13).sum()
gros_du_chantier_count=(filtered_classids==14).sum()
lac_count=(filtered_classids==15).sum()
casque_noir_count=(filtered_classids==16).sum()
lunettes_count=(filtered_classids==17).sum()
casque_vert_count=(filtered_classids==18).sum()
casques_nombre=casque_jaune_count+casque_rouge_count+casque_blue_count+casque_orange_count+casque_blanc_count+casque_noir_count+casque_vert_count
gilets_nombre=gilet_rouge_count+gilet_jaune_count
employees_count=personne_count
employees_sans_casques=employees_count-casques_nombre
employees_avec_casques=casques_nombre
employees_sans_gilets=employees_count-gilets_nombre
employees_avec_gilets=gilets_nombre
#display count
text = "employees_sans_casques: {} employees_avec_casques: {} employees_sans_gilets: {} employees_avec_gilets: {}".format(employees_sans_casques, employees_avec_casques, employees_sans_gilets, employees_avec_gilets)
cv2.putText(frame,text, (1,int(border_size-30)), cv2.FONT_HERSHEY_SIMPLEX,0.5,border_text_color, 1)
#display status
text = "Status:"
cv2.putText(frame,text, (W-100, int(border_size-50)), cv2.FONT_HERSHEY_SIMPLEX,0.5,border_text_color, 2)
ratio=employees_sans_casques/(employees_avec_casques+employees_sans_casques+0.000001)
next_frame_towait=fps._numFrames+(5*25)
if ratio>=0.1 and employees_sans_casques>=3:
text = "Danger !"
cv2.putText(frame,text, (W-100, int(border_size-20)), cv2.FONT_HERSHEY_SIMPLEX,0.65,[26,13,247], 2)
elif ratio!=0 and np.isnan(ratio)!=True:
text = "Warning !"
cv2.putText(frame,text, (W-100, int(border_size-20)), cv2.FONT_HERSHEY_SIMPLEX,0.65,[0,255,255], 2)
else:
text = "Safe "
cv2.putText(frame,text, (W-100, int(border_size-20)), cv2.FONT_HERSHEY_SIMPLEX,0.65,[0,255,0], 2)
# 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]+border_size)
(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(frame, (x, y), (x + w, y + h), color, 1)
text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
cv2.putText(frame, text, (x, y-5), cv2.FONT_HERSHEY_SIMPLEX,0.5, color, 1)
# check to see if the output frame should be displayed to our
# screen
if args["display"] > 0:
# show the output frame
cv2.imshow("frame", frame)
key = cv2.waitKey(0) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# stop the timer and display FPS information
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))