Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
WebCamObjectDetectionMobileNetSSD.py
# Bruno Capuano 2020
# display the camera feed using OpenCV
# display FPS
# load MobileNetSSD object detector trained with COCO Dataset (20 classes)
# analyze each camera frame using MobileNet
# enable disable obj detection pressing D key
import numpy as np
import time
import cv2
import os
def initMobileNetSSD():
global classesMobileNetSSD, colorsMobileNetSSD, net
classesMobileNetSSD = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
colorsMobileNetSSD = np.random.uniform(0, 255, size=(len(classesMobileNetSSD), 3))
net = cv2.dnn.readNetFromCaffe(prototxtFile, modelFile)
def analyzeFrame(frame, displayBoundingBox = True, displayClassName = True, displayConfidence = True):
global H, W
# init
if W is None or H is None:
(H, W) = frame.shape[:2]
if net is None:
initMobileNetSSD()
mobileNetSSDImgSize = (300, 300)
blob = cv2.dnn.blobFromImage(cv2.resize(frame, mobileNetSSDImgSize), 0.007843, mobileNetSSDImgSize, 127.5)
net.setInput(blob)
detections = net.forward()
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > confidenceDef:
idx = int(detections[0, 0, i, 1])
box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
(startX, startY, endX, endY) = box.astype("int")
if(displayBoundingBox):
cv2.rectangle(frame, (startX, startY), (endX, endY), colorsMobileNetSSD[idx], 2)
if(displayClassName and displayConfidence):
label = "{}: {:.2f}%".format(classesMobileNetSSD[idx], confidence * 100)
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(frame, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, colorsMobileNetSSD[idx], 2)
elif (displayClassName):
label = str(f"{classesMobileNetSSD[idx]}")
y = startY - 15 if startY - 15 > 15 else startY + 15
cv2.putText(frame, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, colorsMobileNetSSD[idx], 2)
# Camera Settings
camera_Width = 640 # 1024 # 1280 # 640
camera_Heigth = 480 # 780 # 960 # 480
frameSize = (camera_Width, camera_Heigth)
video_capture = cv2.VideoCapture(1)
time.sleep(2.0)
(W, H) = (None, None)
# MobileNetSSD Settings
confidenceDef = 0.5
thresholdDef = 0.3
prototxtFile = "MobileNetSSD_deploy.prototxt.txt"
modelFile = "MobileNetSSD_deploy.caffemodel"
net = (None)
classesMobileNetSSD = (None)
colorsMobileNetSSD = (None)
i = 0
detectionEnabled = False
while True:
i = i + 1
start_time = time.time()
ret, frameOrig = video_capture.read()
frame = cv2.resize(frameOrig, frameSize)
if(detectionEnabled):
analyzeFrame(frame)
if (time.time() - start_time ) > 0:
fpsInfo = "FPS: " + str(1.0 / (time.time() - start_time)) # FPS = 1 / time to process loop
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, fpsInfo, (10, 20), font, 0.4, (255, 255, 255), 1)
cv2.imshow('@elbruno - MobileNetSSD Object Detection', frame)
# key controller
key = cv2.waitKey(1) & 0xFF
if key == ord("d"):
if (detectionEnabled == True):
detectionEnabled = False
else:
detectionEnabled = True
if key == ord("q"):
break
video_capture.release()
cv2.destroyAllWindows()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.