我刚开始使用 YOLOv4 进行项目的实时对象检测应用程序。
我按照 darknet 网站上的步骤进行操作。为了使用网络摄像头进行实时检测,我运行了下面的代码
import cv2
import numpy as np
import time
# Load the YOLO model
net = cv2.dnn.readNet("./solarpanel/cfg/weights/yolov4-tiny-custom_last.weights",
"./solarpanel/cfg/yolov4-tiny-custom.cfg")
classes = []
with open("./solarpanel/cfg/obj.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
cap=None
font=None
starting_time = None
frame_id = 0
def loadWebCam():
global cap, font, starting_time, frame_id
# Load webcam
cap = cv2.VideoCapture(0)
font = cv2.FONT_HERSHEY_SIMPLEX
starting_time = time.time()
frame_id = 0
def unLoadWebCam():
global cap
cap.release()
cv2.destroyAllWindows()
def checkcellfailure():
global cap, font, starting_time, frame_id
loadWebCam()
class_ids = []
confidences = []
boxes = []
while True:
# Read webcam
_, frame = cap.read()
frame_id += 1
height, width, channels = frame.shape
# Detecting objects
blob = cv2.dnn.blobFromImage(frame,
0.00392, (416, 416), (0, 0, 0),
True,
crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
# Visualising data
class_ids = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.1:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.8, 0.3)
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
confidence = confidences[i]
color = colors[class_ids[i]]
cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
cv2.putText(frame, label + " " + str(round(confidence, 2)),
(x, y + 30), font, 3, color, 3)
elapsed_time = time.time() - starting_time
fps = frame_id / elapsed_time
cv2.putText(frame, "FPS: " + str(round(fps, 2)), (40, 670), font, .7,
(0, 255, 255), 1)
cv2.putText(frame, "press [esc] to exit", (40, 690), font, .45,
(0, 255, 255), 1)
cv2.imshow("Image", frame)
key = cv2.waitKey(1)
# print(confidences)
found=False
for conf in confidences:
if conf > 0.9:
found=True
if key == 27 or found:
print("cellfailure detected")
#print(" Global Location: %s" % vehicle.location.global_frame)
#print(" Global Location (relative altitude): %s" % vehicle.location.global_relative_frame)
#print(" Local Location: %s" % vehicle.location.local_frame)
#print("[button pressed] ///// [esc].")
#print("[feedback] ///// Videocapturing succesfully stopped")
break
#unLoadWebCam()
return confidences
这将打开一个新的相机窗口,用于检测类并关闭网络摄像头。(其中类我有 2 个类),但我只需要指定的类作为输出。
有人可以建议我正确的代码方式来打印指定的类作为输出并打印无人机的位置吗?
https://unitedcoders.world/blog/print_class_in_yolo.html 这是使用 ultraytics 在 yolo 中打印类名的简单代码