Requirements:
- Python3
- OpenCV
- Classes Names [coco.names]
- Frozen inference graph [the weight ]
- The configuration file:
coco.names0.7KB
is a frozen graph that cannot be trained anymore, it defines the graph def and is actually a serialized graph
frozen_inference_graph.pb13133.3KB
ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt177.9KB
Detection on images :
import cv2
thres = 0.45 # Threshold to detect object
classNames= []
classFile = 'coco.names'
img ='' # Provide the image file here
with open(classFile, 'r') as infile:
data = infile.read()
classNames = data.splitlines()
configPath = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = 'frozen_inference_graph.pb'
net = cv2.dnn_DetectionModel(weightsPath,configPath)
net.setInputSize(320,320)
net.setInputScale(1.0/ 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)
classIds, confs, bbox = net.detect(img,confThreshold=thres)
print(classIds,bbox)
for classId, confidence,box in zip(classIds.flatten(),confs.flatten(),bbox):
cv2.rectangle(img,box,color=(4,0,221),thickness=2)
cv2.putText(img,classNames[classId-1].upper(),(box[0]+10,box[1]+30), cv2.FONT_HERSHEY_COMPLEX,1,(4,0,221),2)
cv2.imshow("Output",img)
cv2.waitkey(0)
Detect objects in video stream
import cv2
thres = 0.45 # Threshold to detect object
cap = cv2.VideoCapture(1)
cap.set(3,1280)
cap.set(4,720)
cap.set(10,70)
classNames= []
classFile = 'coco.names'
with open(classFile, 'r') as infile:
data = infile.read()
classNames = data.splitlines()
configPath = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = 'frozen_inference_graph.pb'
net = cv2.dnn_DetectionModel(weightsPath,configPath)
net.setInputSize(320,320)
net.setInputScale(1.0/ 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)
while True:
success,img = cap.read()
classIds, confs, bbox = net.detect(img,confThreshold=thres)
print(classIds,bbox)
if len(classIds) != 0:
for classId, confidence,box in zip(classIds.flatten(),confs.flatten(),bbox):
cv2.rectangle(img,box,color=(4,0,221),thickness=2)
cv2.putText(img,classNames[classId-1].upper(),(box[0]+10,box[1]+30),
cv2.FONT_HERSHEY_COMPLEX,1,(4,0,221),2)
cv2.putText(img,str(round(confidence*100,2)),(box[0]+200,box[1]+30),
cv2.FONT_HERSHEY_COMPLEX,1,(4,0,221),2)
cv2.imshow('Output',img)
cv2.waitKey(1)
Another code for video stream
import cv2
import numpy as np
thres = 0.45 # Threshold to detect object
nms_threshold = 0.2
cap = cv2.VideoCapture(1)
cap.set(3,1280)
cap.set(4,720)
cap.set(10,150)
classNames= []
classFile = 'coco.names'
with open(classFile, 'r') as infile:
data = infile.read()
classNames = data.splitlines()
#print(classNames)
configPath = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = 'frozen_inference_graph.pb'
net = cv2.dnn_DetectionModel(weightsPath,configPath)
net.setInputSize(320,320)
net.setInputScale(1.0/ 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)
while True:
success,img = cap.read()
classIds, confs, bbox = net.detect(img,confThreshold=thres)
bbox = list(bbox)
confs = list(np.array(confs).reshape(1,-1)[0])
confs = list(map(float,confs))
#print(type(confs[0]))
#print(confs)
indices = cv2.dnn.NMSBoxes(bbox,confs,thres,nms_threshold)
print(len(indices))
if len(indices) != 0:
print(indices[0])
for i in indices:
i = i
box = bbox[i]
x,y,w,h = box[0],box[1],box[2],box[3]
cv2.rectangle(img, (x,y),(x+w,h+y), color=(0, 255, 0), thickness=2)
cv2.putText(img,classNames[classIds[0]-1].upper(),(box[0]+10,box[1]+30),
cv2.FONT_HERSHEY_COMPLEX,1,(0,255,0),2)
cv2.imshow("Output",img)
cv2.waitKey(1)
objects detector.zip12159.5KB