[opencv]基于dlib和ssd的目标追踪和多线程加速
1.opencv的追踪算法
1.1opencv的八个追踪算法
"csrt": cv2.TrackerCSRT_create, "kcf": cv2.TrackerKCF_create, "boosting": cv2.TrackerBoosting_create, "mil": cv2.TrackerMIL_create, "tld": cv2.TrackerTLD_create, "medianflow": cv2.TrackerMedianFlow_create, "mosse": cv2.TrackerMOSSE_create主要用到 kcf(卡尔曼滤波),效率和准确率都不错
1.2基于kcf的OpenCV追踪检测流程
# 实例化OpenCV's multi-object tracker
trackers = cv2.legacy.MultiTracker_create() #实例化一个追踪器
# 视频流
while True:
# 取当前帧
ret , frame = vs.cv2.VideoCapture(args["video"]) #选择参数列表传入的追踪器
# 到头了就结束
if ret is False:
print("没有视频")
break
# resize每一帧
(h, w) = frame.shape[:2]
width=600
r = width / float(w)
dim = (width, int(h * r))
frame = cv2.resize(frame,
# 追踪结果
(success, boxes) = tracker
# 绘制区域
for box in boxes:
(x, y, w, h) = [int(v)
cv2.rectangle(frame, (
# 显示
cv2.imshow("Frame", frame)
key = cv2.waitKey(100) & 0
if key == ord("s"):
# 选择一个区域，按s
box = cv2.selectROI("F
showCrosshair=True
# 创建一个新的追踪器
tracker = OPENCV_OBJEC
trackers.add(tracker,
# 退出
elif key == 27:
break
vs.release()
cv2.destroyAllWindows() 2.深度学习的追踪算法：ssd(检测器)+dlib(追踪器)
2.1dlib介绍：
它是一个高性能的计算框架。它是一个C++编写的工具包，所以在应用层面的推理速度是非常快的。而且配备了python客户端，很方便开发者在各大平台使用，大大提高了框架的灵活性。
广泛应用于工业界和学术界。包含了大多数常用的机器学习算法，许多图像处理算法和深度学习算法，被工业界和学术界广泛应用于机器人，嵌入式设备，移动电话和大型高性能计算环境领域。常见的深度学习，基于SVM的分类和递归算法，针对大规模分类和递归的降维方法，相关向量机，聚类，多层感知机等都有相关API，且配置详细文档。最重要的一点是开源，开源，开源！这就意味着，我们可以在任何APP上免费试用。
2.2算法流程
'''训练的时候怎么进行数据预处理，测试的时也需要进行相同的预处理'''
if len(tracker) == 0:
#获取blob数据
(h,w) = frame.shape[:2]
#归一化，减均值操作
blob = cv2.dnn.blobFromImage(frame,0.007843,(w,h),127.5)
#得到检测结果
net.setInput(blob)
detections = net.forward()
#遍历得到的检测结果
for i in np.arange(1,detections.shape[2]):
#会有多个结果，只保留概率最高的
confidence = detections[0,0,i,2]
#过滤
if confidence > args["confidence"]:
#将类标签的索引从检测列表中抽取出来
idx = int(detections[0,0,i,1])
label = CLASSES[idx]
#只保留人的
if CLASSES[idx] != 'person':
continue
#得到bbox
#print detections[0,0,i,3:7]
box = detections[0,0,i,3:7] * np.array([w,h,w,h])
(startX,startY,endX,endY) = box.astype('int')
#使用dlib来进行目标追踪
t = dlib.correlation_tracker()
rect = dlib.rectangle(int(startX),int(startY),int(endX),int(endY))
t.start_track(rgb,rect)
#保存结果
labels.append(label)
trackers.append(t)
2.3多进程的追踪流程
def start_tracker(box, label, rgb, inputQueue, outputQueue):
'''后两个参数传入的是队列'''
t = dlib.correlation_tracker() #创建追踪器
rect = dlib.rectangle(int(box[0]), int(box[1]), int(box[2]), int(box[3]))
t.start_track(rgb, rect) #用dlib追踪器的属性去画图
while True:
# 获取下一帧
rgb = inputQueue.get()
# 非空就开始处理
if rgb is not None:
# 更新追踪器
t.update(rgb)
pos = t.get_position()
startX = int(pos.left())
startY = int(pos.top())
endX = int(pos.right())
endY = int(pos.bottom())
# 把结果放到输出q
outputQueue.put((label, (startX, startY, endX, endY)))多进程处理:主要用到 `import multiprocessing` 工具包
from utils import FPS
import multiprocessing
import numpy as np
import argparse
import dlib
import cv2
#perfmon
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("-v", "--video", required=True,
help="path to 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=0.2,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# 一会要放多个追踪器
inputQueues = []
outputQueues = []
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
"sofa", "train", "tvmonitor"]
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])
print("[INFO] starting video stream...")
vs = cv2.VideoCapture(args["video"])
writer = None
fps = FPS().start()
if __name__ == '__main__':
while True:
(grabbed, frame) = vs.read()
if frame is None:
break
(h, w) = frame.shape[:2]
width=600
r = width / float(w)
dim = (width, int(h * r))
frame = cv2.resize(frame, dim, interpolation=cv2.INTER_AREA)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if args["output"] is not None and writer is None:
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
writer = cv2.VideoWriter(args["output"], fourcc, 30,
(frame.shape[1], frame.shape[0]), True)
#首先检测位置
if len(inputQueues) == 0:
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(frame, 0.007843, (w, h), 127.5) #推理阶段的图片预处理
net.setInput(blob) #将处理后的图片放入net,再次将网络前向传播
detections = net.forward()
for i in np.arange(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > args["confidence"]:
idx = int(detections[0, 0, i, 1])
label = CLASSES[idx]
if CLASSES[idx] != "person":
continue
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
bb = (startX, startY, endX, endY)
# 创建输入q和输出q 多进程
iq = multiprocessing.Queue()
oq = multiprocessing.Queue()
inputQueues.append(iq)
outputQueues.append(oq)
# 多核
p = multiprocessing.Process(
target=start_tracker,
args=(bb, label, rgb, iq, oq)) #Process()函数需要的参数
p.daemon = True
p.start()
cv2.rectangle(frame, (startX, startY), (endX, endY),
(0, 255, 0), 2)
cv2.putText(frame, label, (startX, startY - 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 255, 0), 2)
else:
# 多个追踪器处理的都是相同输入
for iq in inputQueues:
iq.put(rgb)
for oq in outputQueues:
# 得到更新结果
(label, (startX, startY, endX, endY)) = oq.get()
# 绘图
cv2.rectangle(frame, (startX, startY), (endX, endY),
(0, 255, 0), 2)
cv2.putText(frame, label, (startX, startY - 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 255, 0), 2)
if writer is not None:
writer.write(frame)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == 27:
break
fps.update()
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
if writer is not None:
writer.release()
cv2.destroyAllWindows()
vs.release()