dlibのcorrelation_trackerがターゲットイメージを失った場所を検出するにはどうすればよいですか？

Question

マルチスレッドの顔tracking scriptにcorrelation_trackerを追加しました。奇妙なことに、一般的には画面上の顔を正確に追跡しますが、カメラの上に手を置くと、同じ座標が表示され続け、同じ領域が強調表示されます。追跡オブジェクトが実際に離れるときを検出する良い方法はありますか？それとも、これはしばらくの間、一層遅い検出器オブジェクトを処理する必要がありますか？

from __future__ import division 
import sys 
from time import time, sleep 
import threading 

import dlib 
#from skimage import io 


detector = dlib.get_frontal_face_detector() 
win = dlib.image_window() 

def adjustForOpenCV(image): 
    """ OpenCV use bgr not rgb. odd. """ 
    for row in image: 
     for px in row: 
      #rgb expected... but the array is bgr? 
      r = px[2] 
      px[2] = px[0] 
      px[0] = r 
    return image 

class webCamGrabber(threading.Thread): 
    def __init__(self): 
     threading.Thread.__init__(self) 
     #Lock for when you can read/write self.image: 
     #self.imageLock = threading.Lock() 
     self.image = False 

     from cv2 import VideoCapture, cv 
     from time import time 

     self.cam = VideoCapture(0) #set the port of the camera as before 
     #Doesn't seem to work: 
     self.cam.set(cv.CV_CAP_PROP_FRAME_WIDTH, 160) 
     self.cam.set(cv.CV_CAP_PROP_FRAME_WIDTH, 120) 
     #self.cam.set(cv.CV_CAP_PROP_FPS, 1) 


    def run(self): 
     while True: 
      start = time() 
      #self.imageLock.acquire() 
      retval, self.image = self.cam.read() #return a True bolean and and the image if all go right 
      #print("readimage: " + str(time() - start)) 
      #sleep(0.1) 

if len(sys.argv[1:]) == 0: 

    #Start webcam reader thread: 
    camThread = webCamGrabber() 
    camThread.start() 

    #Setup window for results 
    detector = dlib.get_frontal_face_detector() 
    win = dlib.image_window() 

    while True: 
     #camThread.imageLock.acquire() 
     if camThread.image is not False: 
      print("enter") 
      start = time() 

      myimage = camThread.image 
      for row in myimage: 
       for px in row: 
        #rgb expected... but the array is bgr? 
        r = px[2] 
        px[2] = px[0] 
        px[0] = r 


      dets = detector(myimage, 0) 
      #camThread.imageLock.release() 
      print "your faces:" +str(len(dets)) 
      nearFace = None 
      nearFaceArea = 0 

      for i, d in enumerate(dets): 
       #print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
       # i, d.left(), d.top(), d.right(), d.bottom())) 
       screenArea = (d.right() - d.left()) * (d.bottom() - d.top()) 
       #print 'area', screenArea 
       if screenArea > nearFaceArea: 
        nearFace = d 
      print("face-find-time: " + str(time() - start)) 

      print("from left: {}".format(((nearFace.left() + nearFace.right())/2)/len(camThread.image[0]))) 
      print("from top: {}".format(((nearFace.top() + nearFace.bottom())/2)/len(camThread.image))) 

      start = time() 
      win.clear_overlay() 
      win.set_image(myimage) 
      win.add_overlay(nearFace) 
      print("show: " + str(time() - start)) 

      if nearFace != None: 
       points = (nearFace.left(), nearFace.top(), nearFace.right(), nearFace.bottom()) 
       tracker = dlib.correlation_tracker() 
       tracker.start_track(myimage, dlib.rectangle(*points)) 

       while True: 
        myImage = adjustForOpenCV(camThread.image) 

        tracker.update(myImage) 
        rect = tracker.get_position() 
        cx = (rect.right() + rect.left())/2 
        cy = (rect.top() + rect.bottom())/2 
        print('correlationTracker %s,%s' % (cx, cy)) 
        print rect 
        win.clear_overlay() 
        win.set_image(myImage) 
        win.add_overlay(rect) 
        sleep(0.1) 

      #dlib.hit_enter_to_continue() 




for f in sys.argv[1:]: 
    print("Processing file: {}".format(f)) 
    img = io.imread(f) 
    # The 1 in the second argument indicates that we should upsample the image 
    # 1 time. This will make everything bigger and allow us to detect more 
    # faces. 
    dets = detector(img, 1) 
    print("Number of faces detected: {}".format(len(dets))) 
    for i, d in enumerate(dets): 
     print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
      i, d.left(), d.top(), d.right(), d.bottom())) 

    win.clear_overlay() 
    win.set_image(img) 
    win.add_overlay(dets) 
    dlib.hit_enter_to_continue() 


# Finally, if you really want to you can ask the detector to tell you the score 
# for each detection. The score is bigger for more confident detections. 
# Also, the idx tells you which of the face sub-detectors matched. This can be 
# used to broadly identify faces in different orientations. 
if (len(sys.argv[1:]) > 0): 
    img = io.imread(sys.argv[1]) 
    dets, scores, idx = detector.run(img, 1) 
    for i, d in enumerate(dets): 
     print("Detection {}, score: {}, face_type:{}".format(
      d, scores[i], idx[i])) 

Answer 1

顔検出器を毎回実行してから顔がまだ存在するかどうかを確認する必要があります。