利用Dragonbaord 410c開發(fā)板搭建具有運動追蹤功能攝像頭

很多時候我們不在家的時候，都希望能夠了解到家里的情況，這時候你可能想到需要一個web攝像頭來進(jìn)行監(jiān)控，但是作為一個410c開放愛好者，我們?nèi)ベI一個這樣的攝像頭就太浪費了，今天就帶大家一起來用手中的dragonbaord 410c開發(fā)板來實現(xiàn)一些個簡單的帶有運動追蹤功能的攝像頭，廢話不多說，接下來上干貨。

一、準(zhǔn)備工作

準(zhǔn)備一塊dragonboard 410c開發(fā)板、一個USB攝像頭、鼠標(biāo)、鍵盤當(dāng)然還有適配器和能夠接入網(wǎng)絡(luò)的wifi熱點。

這里鼠標(biāo)和鍵盤主要是用來進(jìn)行開發(fā)，如果你的dragonboard 410c開發(fā)板已經(jīng)安裝好了debain操作系統(tǒng)，這里我們接下來的工作將全部在dragonboard 410c開發(fā)板上完成，不需要PC機(jī)，具體環(huán)境搭建參考如下：

按照上述環(huán)境搭建后，就可以啟動你的dragonboard410c開發(fā)板了，這里首先我們不連接攝像頭，直接連接鼠標(biāo)，因為還需要配置你的dragonboard 410c開發(fā)板的網(wǎng)絡(luò)和在上面進(jìn)行編程，編號程序后運行程序的時候再講鼠標(biāo)拔掉，連接USB攝像頭。

二、代碼實現(xiàn)

整個開發(fā)過程中采用Python腳本語言來進(jìn)行設(shè)計，并且借助于opencvpython庫來進(jìn)行相關(guān)的圖形處理操作，廢話不多說，具體代碼如下：

#!/usr/bin/env python

import argparse

import datetime

import imutils

import time

import cv2

import numpy as np

ap = argparse.ArgumentParser()

ap.add_argument("-v","--video", help="path to the video file")

ap.add_argument("-a","--min-area", type=int, default=5000, help="minimum areasize")

args = vars(ap.parse_args())

?ifargs.get("video", None) is None:

???camera = cv2.VideoCapture(0)

???time.sleep(0.1)

?else:

???camera = cv2.VideoCapture(args["video"])

?framenext = None

firstFrame = None

i=0

while True:

???(grabbed, frame) = camera.read()

???text = "Unoccupied"

???if not grabbed:

???????break

???frame = imutils.resize(frame, width=500)

???framenext = frame

???gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

???#gray_pre = np.float32(gray)

???gray = cv2.GaussianBlur(gray, (21, 21), 0)

???if firstFrame is None:

???????firstFrame = gray

???????continue???????????

???frameDelta = cv2.absdiff(firstFrame, gray)

???thresh = cv2.threshold(frameDelta, 115, 255, cv2.THRESH_BINARY)[1]

???thresh = cv2.dilate(thresh, None, iterations=2)

???(cnts, _) = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,

???????cv2.CHAIN_APPROX_SIMPLE)

????for c in cnts:

???????# if the contour is too small, ignore it

???????if cv2.contourArea(c) < args["min_area"]:

???????????continue

????????# compute the bounding box for the contour? draw it on the frame

???????# and update the text

???????(x, y, w, h) = cv2.boundingRect(c)

???????cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)

???????text = "Occupied"

# caculation feature points

???graynext? =cv2.cvtColor(framenext, cv2.COLOR_BGR2GRAY)

???#graynext = np.float32(graynext);

???detector = cv2.xfeatures2d.SIFT_create()

???keypoints = detector.detect(gray,None)

???framenext=cv2.drawKeypoints(graynext,keypoints)

# draw the text and timestamp on the frame

???cv2.putText(frame, "Room Status: {}".format(text), (10, 20),

???????cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)

???cv2.putText(frame, datetime.datetime.now().strftime("%A %d %B %Y%I:%M:%S%p"),

???????(10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.35, (0, 0, 255),1)

???cv2.imshow("Security Feed", frame)

???cv2.imshow("Thresh", thresh)

???cv2.imshow("Frame Delta", frameDelta)

???cv2.imshow("keypoints",framenext)

???#key = cv2.waitKey(1) & 0xFF

???if cv2.waitKey(10) == 27:

???????break?

?????????????????? camera.release()

????cv2.destroyAllWindows()

???????? #Send the message via our own SMTP server (sendmail)

????sender = 'from@runoob.com'

????receivers = ['XXXXXXXXXX@thundersoft.com']

????text = MIMEText('Hello Qualcomm my name is NO1','plain','utf-8')

????image_url = "./detected_face.jpg"

?????image = MIMEImage(open(image_url,'rb').read())

????image.add_header('Content-ID','')

????message = MIMEMultipart('related')

????message['From'] = Header("workshop",'utf-8')

????message['To'] = Header("Test",'utf-8')

????subject = 'Python SMTP Test'

????message['Subject'] = Header(subject,'utf-8')

????message.attach(text)

????message.attach(image)

try:

???????? smtpObj=smtplib.SMTP('localhost')

???????? #smtpObj.set_debuglevel(1)

???????? smtpObj.sendmail(sender,receivers, message.as_string())

???????? smtpObj.quit()

???????? print"done!"

except smtplib.SMTPException:

?print "error:send failed"

三、測試

編寫好代碼后保存，然后使用Python monition_camera.py命令就可以運行上述代碼了，這里我們收到的郵件及附件效果如下，由于涉及到隱私具體的跟蹤人體目標(biāo)就不展示了，大家下載代碼實現(xiàn)即可以看到效果。