【OpenCV】DNN模块实现手势关键点检测

from __future__ import division
import cv2
import time
import numpy as np

protoFile = "pose_deploy.prototxt"
weightsFile = "pose_iter_102000.caffemodel"
nPoints = 22
POSE_PAIRS = [[0, 1], [1, 2], [2, 3], [3, 4], [0, 5], [5, 6],
              [6, 7], [7, 8], [0, 9], [9, 10], [10, 11], [11, 12],
              [0, 13], [13, 14], [14, 15], [15, 16], [0, 17],
              [17, 18], [18, 19], [19, 20]]
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)

frame = cv2.imread("test.jpg")
frameCopy = np.copy(frame)
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
aspect_ratio = frameWidth/frameHeight

threshold = 0.1

t = time.time()
inHeight = 368
inWidth = int(((aspect_ratio*inHeight)*8)//8)
inpBlob = cv2.dnn.blobFromImage(frame, 1.0/255, (inWidth, inHeight), (0, 0, 0), swapRB=False, crop=False)
net.setInput(inpBlob)
output = net.forward()
print("time  : {:.3f}".format(time.time() - t))

points = []
for i in range(nPoints):
    probMap = output[0, i, :, :]
    probMap = cv2.resize(probMap, (frameWidth, frameHeight))

    minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
    if prob > threshold:
        cv2.circle(frameCopy, (int(point[0]), int(point[1])), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
        cv2.putText(frameCopy, "{}".format(i), (int(point[0]), int(point[1])), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255),
                    2, lineType=cv2.LINE_AA)
        points.append((int(point[0]), int(point[1])))
    else:
        points.append(None)

for pair in POSE_PAIRS:
    partA = pair[0]
    partB = pair[1]

    if points[partA] and points[partB]:
        cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2)
        cv2.circle(frame, points[partA], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)
        cv2.circle(frame, points[partB], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)

cv2.imshow('Keypoints', frameCopy)
cv2.imshow('Skeleton', frame)

cv2.waitKey(0)

输入图像

关键点

连接关键点