Object detection

/ Computer Vision / By aicodeschool

Object Detection using SSD-MobileNetv3

import cv2
import matplotlib.pyplot as plt
classLabels = [] 
file_name = 'Labels.txt'
with open(file_name,'rt') as fpt:
    classLabels = fpt.read().rstrip('\n').split('\n')
    print(classLabels) ## Class labels

config_file = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
frozen_model = 'frozen_inference_graph.pb'

Reading the Model in Opencv

#model = cv2.dnn.readNetFromTensorflow(frozen_model,config_file)
model = cv2.dnn_DetectionModel(frozen_model,config_file)
model.setInputSize(320,320)
model.setInputScale(1.0/127.5) ## 255/2 = 127.5
model.setInputMean((127.5,127.5,127.5)) ## 
model.setInputSwapRB(True)
<dnn_Model 000001BDE265BA20>
#model.setInputSize(300,300)
#model.setInputScale(1.0/127.5) ## 255/2 = 127.5
#model.setInputMean((255,255,255)) ## 
#plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
img = cv2.imread('man-bmw.png')
img = cv2.imread('man_tuxedo_car_style_27329_1920x1080.jpg')
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))

ClassIndex, confidece, bbox = model.detect(img,confThreshold=0.5)
print(ClassIndex)
[[1]
 [3]]
 type(ClassIndex)
 numpy.ndarray
 id =(ClassIndex-1).flatten()
 print(id)
 [0 2]
 type(id.flatten())
 classLabels[ClassIndex.item()-1]

font_scale = 3
font = cv2.FONT_HERSHEY_PLAIN
for ClassInd, conf, boxes in zip(ClassIndex.flatten(), confidece.flatten(), bbox):
    #cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 0), 2)
    #cv2.putText(img, text, (text_offset_x, text_offset_y), font, fontScale=font_scale, color=(0, 0, 0), thickness=1)
    cv2.rectangle(img,boxes,(255, 0, 0), 2 )
    cv2.putText(img,classLabels[ClassInd-1],(boxes[0]+10,boxes[1]+40), font, fontScale=font_scale,color=(0, 255, 0), thickness=3 )

boxes[1]

294

import matplotlib.pyplot as plt
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))

print(len(classLabels))
80

Video Reading and Applying Object Detection

cap = cv2.VideoCapture("Record_2020_10_16_02_31_46_801.mp4")


# Check if the webcam is opened correctly
if not cap.isOpened():
    cap = cv2.VideoCapture(0)
if not cap.isOpened():
    raise IOError("Cannot open webcam")
font_scale = 3
font = cv2.FONT_HERSHEY_PLAIN

while True:
    ret,frame = cap.read()
   
    ClassIndex, confidece, bbox = model.detect(frame,confThreshold=0.55)
    
    print(ClassIndex)
    if (len(ClassIndex)!=0):
        for ClassInd, conf, boxes in zip(ClassIndex.flatten(), confidece.flatten(), bbox):
            if (ClassInd<=80):
                cv2.rectangle(frame,boxes,(255, 0, 0), 2 )
                cv2.putText(frame,classLabels[ClassInd-10],(boxes[0]+10,boxes[1]+40), font, fontScale=font_scale,color=(0, 255, 0), thickness=3 )
                
    cv2.imshow('Object Detection Tutorial',frame)

    if cv2.waitKey(2) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

For Webcame Demo

cap = cv2.VideoCapture(1)


# Check if the webcam is opened correctly
if not cap.isOpened():
    cap = cv2.VideoCapture(0)
if not cap.isOpened():
    raise IOError("Cannot open webcam")
font_scale = 3
font = cv2.FONT_HERSHEY_PLAIN

while True:
    ret,frame = cap.read()
   
    ClassIndex, confidece, bbox = model.detect(frame,confThreshold=0.55)
    
    print(ClassIndex)
    if (len(ClassIndex)!=0):
        for ClassInd, conf, boxes in zip(ClassIndex.flatten(), confidece.flatten(), bbox):
            if (ClassInd<=80):
                cv2.rectangle(frame,boxes,(255, 0, 0), 2 )
                cv2.putText(frame,classLabels[ClassInd-10],(boxes[0]+10,boxes[1]+40), font, fontScale=font_scale,color=(0, 255, 0), thickness=3 )
                
    cv2.imshow('Object Detection Tutorial',frame)

    if cv2.waitKey(2) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()