基於OpenCV目標跟蹤實現人員計數器

class TrackableObject:
    def __init__(self, objectID, centroid):
        # store the object ID, then initialize a list of centroids
        # using the current centroid
        self.objectID = objectID
        self.centroids = [centroid]
        # initialize a boolean used to indicate if the object has
        # already been counted or not
        self.counted = False

# import the necessary packages
from pyimagesearch.centroidtracker import CentroidTracker
from pyimagesearch.trackableobject import TrackableObject
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import dlib
import cv2

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True,
    help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
    help="path to Caffe pre-trained model")
ap.add_argument("-i", "--input", type=str,
    help="path to optional input video file")
ap.add_argument("-o", "--output", type=str,
    help="path to optional output video file")
ap.add_argument("-c", "--confidence", type=float, default=0.4,
    help="minimum probability to filter weak detections")
ap.add_argument("-s", "--skip-frames", type=int, default=30,
    help="# of skip frames between detections")
args = vars(ap.parse_args())

# initialize the list of class labels MobileNet SSD was trained to detect
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
    "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
    "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
    "sofa", "train", "tvmonitor"]
# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

# if a video path was not supplied, grab a reference to the webcam
if not args.get("input", False):
    print("[INFO] starting video stream...")
    vs = VideoStream(src=0).start()
    time.sleep(2.0)
# otherwise, grab a reference to the video file
else:
    print("[INFO] opening video file...")
    vs = cv2.VideoCapture(args["input"])

# initialize the video writer (we'll instantiate later if need be)
writer = None
# initialize the frame dimensions (we'll set them as soon as we read
# the first frame from the video)
W = None
H = None
# instantiate our centroid tracker, then initialize a list to store
# each of our dlib correlation trackers, followed by a dictionary to
# map each unique object ID to a TrackableObject
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
trackers = []
trackableObjects = {}
# initialize the total number of frames processed thus far, along
# with the total number of objects that have moved either up or down
totalFrames = 0
totalDown = 0
totalUp = 0
# start the frames per second throughput estimator
fps = FPS().start()

# loop over frames from the video stream
while True:
    # grab the next frame and handle if we are reading from either
    # VideoCapture or VideoStream
    frame = vs.read()
    frame = frame[1] if args.get("input", False) else frame
    # if we are viewing a video and we did not grab a frame then we
    # have reached the end of the video
    if args["input"] is not None and frame is None:
        break
    # resize the frame to have a maximum width of 500 pixels (the
    # less data we have, the faster we can process it), then convert
    # the frame from BGR to RGB for dlib
    frame = imutils.resize(frame, width=500)
    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    # if the frame dimensions are empty, set them
    if W is None or H is None:
        (H, W) = frame.shape[:2]
    # if we are supposed to be writing a video to disk, initialize
    # the writer
    if args["output"] is not None and writer is None:
        fourcc = cv2.VideoWriter_fourcc(*"MJPG")
        writer = cv2.VideoWriter(args["output"], fourcc, 30,
            (W, H), True)

    # initialize the current status along with our list of bounding
    # box rectangles returned by either (1) our object detector or
    # (2) the correlation trackers
    status = "Waiting"
    rects = []
    # check to see if we should run a more computationally expensive
    # object detection method to aid our tracker
    if totalFrames % args["skip_frames"] == 0:
        # set the status and initialize our new set of object trackers
        status = "Detecting"
        trackers = []
        # convert the frame to a blob and pass the blob through the
        # network and obtain the detections
        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
        net.setInput(blob)
        detections = net.forward()

        # loop over the detections
        for i in np.arange(0, detections.shape[2]):
            # extract the confidence (i.e., probability) associated
            # with the prediction
            confidence = detections[0, 0, i, 2]
            # filter out weak detections by requiring a minimum
            # confidence
            if confidence > args["confidence"]:
                # extract the index of the class label from the
                # detections list
                idx = int(detections[0, 0, i, 1])
                # if the class label is not a person, ignore it
                if CLASSES[idx] != "person":
                    continue

                # compute the (x, y)-coordinates of the bounding box
                # for the object
                box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
                (startX, startY, endX, endY) = box.astype("int")
                # construct a dlib rectangle object from the bounding
                # box coordinates and then start the dlib correlation
                # tracker
                tracker = dlib.correlation_tracker()
                rect = dlib.rectangle(startX, startY, endX, endY)
                tracker.start_track(rgb, rect)
                # add the tracker to our list of trackers so we can
                # utilize it during skip frames
                trackers.append(tracker)

    # otherwise, we should utilize our object *trackers* rather than
    # object *detectors* to obtain a higher frame processing throughput
    else:
        # loop over the trackers
        for tracker in trackers:
            # set the status of our system to be 'tracking' rather
            # than 'waiting' or 'detecting'
            status = "Tracking"
            # update the tracker and grab the updated position
            tracker.update(rgb)
            pos = tracker.get_position()
            # unpack the position object
            startX = int(pos.left())
            startY = int(pos.top())
            endX = int(pos.right())
            endY = int(pos.bottom())
            # add the bounding box coordinates to the rectangles list
            rects.append((startX, startY, endX, endY))

    # draw a horizontal line in the center of the frame -- once an
    # object crosses this line we will determine whether they were
    # moving 'up' or 'down'
    cv2.line(frame, (0, H // 2), (W, H // 2), (0, 255, 255), 2)
    # use the centroid tracker to associate the (1) old object
    # centroids with (2) the newly computed object centroids
    objects = ct.update(rects)

    # loop over the tracked objects
    for (objectID, centroid) in objects.items():
        # check to see if a trackable object exists for the current
        # object ID
        to = trackableObjects.get(objectID, None)
        # if there is no existing trackable object, create one
        if to is None:
            to = TrackableObject(objectID, centroid)
        # otherwise, there is a trackable object so we can utilize it
        # to determine direction
        else:
            # the difference between the y-coordinate of the *current*
            # centroid and the mean of *previous* centroids will tell
            # us in which direction the object is moving (negative for
            # 'up' and positive for 'down')
            y = [c[1] for c in to.centroids]
            direction = centroid[1] - np.mean(y)
            to.centroids.append(centroid)
            # check to see if the object has been counted or not
            if not to.counted:
                # if the direction is negative (indicating the object
                # is moving up) AND the centroid is above the center
                # line, count the object
                if direction < 0 and centroid[1] < H // 2:
                    totalUp += 1
                    to.counted = True
                # if the direction is positive (indicating the object
                # is moving down) AND the centroid is below the
                # center line, count the object
                elif direction > 0 and centroid[1] > H // 2:
                    totalDown += 1
                    to.counted = True
        # store the trackable object in our dictionary
        trackableObjects[objectID] = to

        # draw both the ID of the object and the centroid of the
        # object on the output frame
        text = "ID {}".format(objectID)
        cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
        cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
    # construct a tuple of information we will be displaying on the
    # frame
    info = [
        ("Up", totalUp),
        ("Down", totalDown),
        ("Status", status),
    ]
    # loop over the info tuples and draw them on our frame
    for (i, (k, v)) in enumerate(info):
        text = "{}: {}".format(k, v)
        cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
            cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)

    # check to see if we should write the frame to disk
    if writer is not None:
        writer.write(frame)
    # show the output frame
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
        break
    # increment the total number of frames processed thus far and
    # then update the FPS counter
    totalFrames += 1
    fps.update()

# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# check to see if we need to release the video writer pointer
if writer is not None:
    writer.release()
# if we are not using a video file, stop the camera video stream
if not args.get("input", False):
    vs.stop()
# otherwise, release the video file pointer
else:
    vs.release()
# close any open windows
cv2.destroyAllWindows()

from pyimagesearch.centroidtracker import CentroidTracker
from pyimagesearch.trackableobject import TrackableObject
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import dlib
import cv2


# 構造參數解析並解析參數
ap = argparse.ArgumentParser()
ap.add_argument("-p", "--prototxt", required=True,
	help="path to Caffe 'deploy' prototxt file")
ap.add_argument("-m", "--model", required=True,
	help="path to Caffe pre-trained model")
ap.add_argument("-i", "--input", type=str,
	help="path to optional input video file")
ap.add_argument("-o", "--output", type=str,
	help="path to optional output video file")
ap.add_argument("-c", "--confidence", type=float, default=0.4,
	help="minimum probability to filter weak detections")
ap.add_argument("-s", "--skip-frames", type=int, default=30,
	help="# of skip frames between detections")
args = vars(ap.parse_args())

# 初始化類標簽列表
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
	"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
	"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
	"sofa", "train", "tvmonitor"]
# 從磁盤加載我們的序列化模型
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

# 如果未提供視頻路徑，請獲取網絡攝像頭的引用
if not args.get("input", False):
	print("[INFO] starting video stream...")
	vs = VideoStream(src=0).start()
	time.sleep(2.0)
# 否則，獲取對視頻文件的引用
else:
	print("[INFO] opening video file...")
	vs = cv2.VideoCapture(args["input"])

# 初始化視頻寫入器(如果需要，我們稍後將進行實例化)
writer = None
# 初始化幀尺寸（我們將在從視頻中讀取第一幀後立即設置它們）
W = None
H = None
# 實例化我們的質心跟蹤器，然後初始化一個列表來存儲每個dlib相關跟蹤器，
# 然後是一個字典來將每個唯一的對象ID映射到TrackableObject
ct = CentroidTracker(maxDisappeared=40, maxDistance=50)
trackers = []
trackableObjects = {}
# 初始化到目前為止處理的幀總數，以及向上或向下移動的對象總數
totalFrames = 0
totalDown = 0
totalUp = 0
# 啟動FPS評估器
fps = FPS().start()

# 循環視頻流中的幀
while True:
	# 如果我們正在從 VideoCapture 或 VideoStream 讀取數據，則抓取下一幀並處理
	frame = vs.read()
	frame = frame[1] if args.get("input", False) else frame
	# 如果我們正在觀看視頻並且我們沒有抓取幀，那麼我們已經到瞭視頻的結尾
	if args["input"] is not None and frame is None:
		break
	# 調整幀的最大寬度為 500 像素（我們擁有的數據越少，我們處理它的速度就越快），
	# 然後將幀從 BGR 轉換為 RGB 用於 dlib
	frame = imutils.resize(frame, width=500)
	rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
	# 如果幀尺寸為空，則設置它們
	if W is None or H is None:
		(H, W) = frame.shape[:2]
	# 如果我們應該將視頻寫入磁盤，請初始化寫入器
	if args["output"] is not None and writer is None:
		fourcc = cv2.VideoWriter_fourcc(*"MJPG")
		writer = cv2.VideoWriter(args["output"], fourcc, 30,
			(W, H), True)


	# 初始化當前狀態以及由（1）我們的對象檢測器或（2）相關跟蹤器返回的邊界框矩形列表
	status = "Waiting"
	rects = []
	# 檢查我們是否應該運行計算量更大的目標檢測方法來幫助我們的跟蹤器
	if totalFrames % args["skip_frames"] == 0:
		# 設置狀態並初始化我們的新對象跟蹤器集
		status = "Detecting"
		trackers = []
		# 將幀轉換為 blob 並通過網絡傳遞 blob 並獲得檢測結果
		blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
		net.setInput(blob)
		detections = net.forward()

		# 循環檢測結果
		for i in np.arange(0, detections.shape[2]):
			# 提取與預測相關的置信度(即概率)
			confidence = detections[0, 0, i, 2]
			# 通過要求最小置信度過濾掉弱檢測
			if confidence > args["confidence"]:
				# 從檢測列表中提取類標簽的索引
				idx = int(detections[0, 0, i, 1])
				# 如果類標簽不是人，則忽略它
				if CLASSES[idx] != "person":
					continue
				# 計算對象邊界框的 (x, y) 坐標
				box = detections[0, 0, i, 3:7] * np.array([W, H, W, H])
				(startX, startY, endX, endY) = box.astype("int")
				# 利用邊界框坐標構造一個 dlib 矩形對象，然後啟動 dlib 相關跟蹤器
				tracker = dlib.correlation_tracker()
				rect = dlib.rectangle(startX, startY, endX, endY)
				tracker.start_track(rgb, rect)
				# 將跟蹤器添加到我們的跟蹤器列表中，以便我們可以在跳幀期間使用它
				trackers.append(tracker)

	# 否則，我們應該利用目標跟蹤器而不是目標檢測器來獲得更高的FPS
	else:
		# 遍歷跟蹤器
		for tracker in trackers:
			# 將系統的狀態設置為“跟蹤”而不是“等待”或“檢測”
			status = "Tracking"
			# 更新跟蹤器並獲取更新的位置
			tracker.update(rgb)
			pos = tracker.get_position()
			# 解包位置對象
			startX = int(pos.left())
			startY = int(pos.top())
			endX = int(pos.right())
			endY = int(pos.bottom())
			# 將邊界框坐標添加到矩形列表
			rects.append((startX, startY, endX, endY))

	# 在幀中心畫一條水平線——一旦一個物體穿過這條線，我們將確定他們是在“向上”還是“向下”移動。
	cv2.line(frame, (0, H // 2), (W, H // 2), (0, 255, 255), 2)
	# 使用質心跟蹤器將 (1) 舊對象質心與 (2) 新計算的對象質心相關聯
	objects = ct.update(rects)

	# 循環遍歷被跟蹤的對象
	for (objectID, centroid) in objects.items():
		# 檢查當前對象 ID 是否存在可跟蹤對象
		to = trackableObjects.get(objectID, None)
		# 如果沒有現有的可跟蹤對象，則創建一個
		if to is None:
			to = TrackableObject(objectID, centroid)
		# 否則，有一個可追蹤的物體，所以我們可以利用它來確定方向
		else:
			# *當前*質心的 y 坐標與 *previous* 質心的平均值之間的差異
			# 將告訴我們物體在哪個方向移動（“向上”為負，“向下”為正）
			y = [c[1] for c in to.centroids]
			direction = centroid[1] - np.mean(y)
			to.centroids.append(centroid)
			# 檢查對象是否已被計數
			if not to.counted:
				# 如果方向為負(表示物體向上移動)且質心在中線以上，則計算物體
				if direction < 0 and centroid[1] < H // 2:
					totalUp += 1
					to.counted = True
				# 如果方向為正（表示物體正在向下移動）並且質心低於中心線，則計算物體
				elif direction > 0 and centroid[1] > H // 2:
					totalDown += 1
					to.counted = True
		# 將可跟蹤對象存儲在我們的字典中
		trackableObjects[objectID] = to

		# 在輸出幀上繪制對象的 ID 和對象的質心
		text = "ID {}".format(objectID)
		cv2.putText(frame, text, (centroid[0] - 10, centroid[1] - 10),
			cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
		cv2.circle(frame, (centroid[0], centroid[1]), 4, (0, 255, 0), -1)
	# 構建我們將在幀上顯示的信息元組
	info = [
		("Up", totalUp),
		("Down", totalDown),
		("Status", status),
	]
	# 遍歷信息元組並將它們繪制在我們的幀上
	for (i, (k, v)) in enumerate(info):
		text = "{}: {}".format(k, v)
		cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
			cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)



	# 檢查我們是否應該將幀寫入磁盤
	if writer is not None:
		writer.write(frame)
	# 顯示輸出幀
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF
	# 如果' q '鍵被按下，中斷循環
	if key == ord("q"):
		break
	# 增加到目前為止處理的幀總數，然後更新 FPS 計數器
	totalFrames += 1
	fps.update()

# 停止定時器，顯示FPS信息
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# 檢查我們是否需要釋放視頻寫入器指針
if writer is not None:
	writer.release()
# 如果我們不使用視頻文件，請停止攝像頭視頻流
if not args.get("input", False):
	vs.stop()
# 否則，釋放視頻文件指針
else:
	vs.release()
# 關閉所有打開的窗口
cv2.destroyAllWindows()

from scipy.spatial import distance as dist
from collections import OrderedDict
import numpy as np

class CentroidTracker:
	def __init__(self, maxDisappeared=50, maxDistance=50):
		# 初始化下一個唯一的對象ID，並使用兩個有序字典來跟蹤給定對象ID到其質心的映射，
		# 以及它被標記為“消失”的連續幀數
		self.nextObjectID = 0
		self.objects = OrderedDict()
		self.disappeared = OrderedDict()

		# 存儲一個給定對象允許被標記為“消失”的最大連續幀數，直到我們需要從跟蹤中註銷該對象
		self.maxDisappeared = maxDisappeared

		# 存儲質心之間的最大距離以關聯對象——如果距離大於這個最大距離，我們開始將對象標記為“消失”
		self.maxDistance = maxDistance

	def register(self, centroid):
		# 註冊對象時，我們使用下一個可用的對象 ID 來存儲質心
		self.objects[self.nextObjectID] = centroid
		self.disappeared[self.nextObjectID] = 0
		self.nextObjectID += 1

	def deregister(self, objectID):
		# 要註銷對象 ID，我們從各自的字典中刪除對象 ID
		del self.objects[objectID]
		del self.disappeared[objectID]

	def update(self, rects):
		# 檢查輸入邊界框矩形列表是否為空
		if len(rects) == 0:
			# 循環遍歷任何現有的跟蹤對象並將它們標記為消失
			for objectID in list(self.disappeared.keys()):
				self.disappeared[objectID] += 1

				# 如果我們已經達到給定對象被標記為消失的最大連續幀數，則取消註冊它
				if self.disappeared[objectID] > self.maxDisappeared:
					self.deregister(objectID)

			# 早點返回，因為沒有要更新的質心或跟蹤信息
			return self.objects

		# 初始化當前幀的輸入質心數組
		inputCentroids = np.zeros((len(rects), 2), dtype="int")

		# 循環邊界框矩形
		for (i, (startX, startY, endX, endY)) in enumerate(rects):
			# 使用邊界框坐標推導出質心
			cX = int((startX + endX) / 2.0)
			cY = int((startY + endY) / 2.0)
			inputCentroids[i] = (cX, cY)

		# 如果我們當前沒有跟蹤任何對象，則獲取輸入質心並註冊它們中的每一個
		if len(self.objects) == 0:
			for i in range(0, len(inputCentroids)):
				self.register(inputCentroids[i])

		# 否則，我們目前正在跟蹤對象，因此我們需要嘗試將輸入質心與現有對象質心匹配
		else:
			# 獲取一組對象 ID 和相應的質心
			objectIDs = list(self.objects.keys())
			objectCentroids = list(self.objects.values())

			# 分別計算每對對象質心和輸入質心之間的距離——我們的目標是將輸入質心與現有對象質心匹配
			D = dist.cdist(np.array(objectCentroids), inputCentroids)

			# 為瞭執行這種匹配，我們必須 (1) 找到每一行中的最小值，
			# 然後 (2) 根據它們的最小值對行索引進行排序，以便具有最小值的行位於索引列表的 *front*
			rows = D.min(axis=1).argsort()

			# 接下來，我們對列執行類似的處理，方法是在每個列中找到最小的值，
			# 然後使用之前計算的行索引列表進行排序
			cols = D.argmin(axis=1)[rows]

			# 為瞭確定我們是否需要更新、註冊或取消註冊一個對象，我們需要跟蹤我們已經檢查過的行和列索引
			usedRows = set()
			usedCols = set()

			# 循環遍歷（行，列）索引元組的組合
			for (row, col) in zip(rows, cols):
				# 如果我們之前已經檢查過行值或列值，請忽略它
				if row in usedRows or col in usedCols:
					continue

				# 如果質心之間的距離大於最大距離，則不要將兩個質心關聯到同一個對象
				if D[row, col] > self.maxDistance:
					continue

				# 否則，獲取當前行的對象 ID，設置其新質心，並重置消失的計數器
				objectID = objectIDs[row]
				self.objects[objectID] = inputCentroids[col]
				self.disappeared[objectID] = 0

				# 表明我們已經分別檢查瞭每個行和列索引
				usedRows.add(row)
				usedCols.add(col)

			# 計算我們尚未檢查的行和列索引
			unusedRows = set(range(0, D.shape[0])).difference(usedRows)
			unusedCols = set(range(0, D.shape[1])).difference(usedCols)

			# 如果對象質心的數量等於或大於輸入質心的數量，
			# 我們需要檢查並查看其中一些對象是否可能已經消失
			if D.shape[0] >= D.shape[1]:
				# 循環未使用的行索引
				for row in unusedRows:
					# 獲取相應行索引的對象 ID 並增加消失的計數器
					objectID = objectIDs[row]
					self.disappeared[objectID] += 1

					# 檢查對象的連續幀數是否被標記為“消失”，以註銷該對象
					if self.disappeared[objectID] > self.maxDisappeared:
						self.deregister(objectID)

			# 否則，如果輸入質心的數量大於現有對象質心的數量，我們需要將每個新的輸入質心註冊為可跟蹤對象
			else:
				for col in unusedCols:
					self.register(inputCentroids[col])

		# 返回可跟蹤對象的集合
		return self.objects

class TrackableObject:
	def __init__(self, objectID, centroid):
		# 存儲對象 ID，然後使用當前質心初始化質心列表
		self.objectID = objectID
		self.centroids = [centroid]

		# 初始化一個佈爾值，用於指示對象是否已被計數
		self.counted = False

python people_counter.py --prototxt mobilenet_ssd/MobileNetSSD_deploy.prototxt \
    --model mobilenet_ssd/MobileNetSSD_deploy.caffemodel \
    --input videos/example_01.mp4 --output output/output_01.avi