我已经检测到视频帧中的对象并对其进行了标记,并且还计算了帧中的对象总数,但我的问题是如何在通过如图所示的线后对对象进行计数。以及对象类别。
这是我的代码
在图像中,我已经计算了框架中的总对象,但我想在它们越线时计算它们。
import cv2
import numpy as np
net = cv2.dnn.readNet('yolov3.weights','yolov3.cfg')
classes = []
with open('coco.names','r') as f:
classes = f.read().splitlines()
# printing the data which is loaded from the names file
#print(classes)
cap = cv2.VideoCapture('video.mp4')
while True:
_,img = cap.read()
height, width, _ = img.shape
blob = cv2.dnn.blobFromImage(img, 1/255, (416 , 416), (0,0,0) ,swapRB=True,crop=False)
net.setInput(blob)
output_layer_names = net.getUnconnectedOutLayersNames()
layerOutput = net.forward(output_layer_names)
boxes = []
person =0
truck =0
car = 0
confidences = []
class_ids =[]
for output in layerOutput:
for detection in output:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
center_x = int(detection[0]*width)
center_y = int(detection[1]*height)
w = int(detection[2]*width)
h = int(detection[3]*height)
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,0.5,0.4)
font = cv2.QT_FONT_NORMAL
colors = np.random.uniform(0,255,size=(len(boxes),3))
for i in indexes.flatten():
labelsss = str(classes[class_ids[i]])
if(labelsss == 'person'):
person+=1
if(labelsss == 'car'):
car+=1
if(labelsss == 'truck'):
truck+=1
for i in indexes.flatten():
x,y,w,h = boxes[i]
label =str(classes[class_ids[i]])
confidence = str(round(confidences[i],1))
color = colors[i]
cv2.rectangle(img,(x,y),(x+w , y+h), color, 2)
cv2.line(img,(1000,250),(5,250),(0,0,0),2)
cv2.putText(img, label + " ", (x, y+20), font, 0.5, (255,255,255),2)
cv2.putText(img, 'Car'+ ":" + str(car), (20, 20), font, 0.8, (0,0,0),2)
cv2.putText(img, 'Person'+ ":" + str(person), (20, 50), font, 0.8, (0,0,0),2)
cv2.putText(img, 'Truck'+ ":" + str(truck), (20, 80), font, 0.8, (0,0,0),2)
cv2.imshow('Image',img)
key = cv2.waitKey(1)
if key == 10:
break
cap.release()
cv2.destroyAllWindows()
我实习期间就做了一个这样的项目。您可以在此处查看代码:https://github.com/sarimmehdi/nanonets_object_tracking/blob/master/test_on_video.py
简而言之:您应该绘制一个矩形(窄),并在穿过矩形时计算跟踪的 ID。如果矩形足够窄,也可以避免重新识别的问题。