Raspberry Piでカメラ映像の骨格検出をする方法 Part 1

# ------------------------- POSE MODELS -------------------------


# Downloading the pose-model trained on COCO
COCO_POSE_URL="https://www.dropbox.com/s/2h2bv29a130sgrk/pose_iter_440000.caffemodel"
COCO_FOLDER="pose/coco/"
wget -c ${COCO_POSE_URL} -P ${COCO_FOLDER}

# Downloading the pose-model trained on MPI
MPI_POSE_URL="https://www.dropbox.com/s/drumc6dzllfed16/pose_iter_160000.caffemodel"
MPI_FOLDER="pose/mpi/"
wget -c ${MPI_POSE_URL} -P ${MPI_FOLDER}

#読み込むモデルを選択
MODE = "MPI"

if MODE is "COCO":
    protoFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/coco/pose_deploy_linevec.prototxt"
    weightsFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/coco/pose_iter_440000.caffemodel"
    nPoints = 18
    POSE_PAIRS = [ [1,0],[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],[0,14],[0,15],[14,16],[15,17]]

elif MODE is "MPI" :
    protoFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt"
    weightsFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/mpi/pose_iter_160000.caffemodel"
    nPoints = 15
    POSE_PAIRS = [[0,1], [1,2], [2,3], [3,4], [1,5], [5,6], [6,7], [1,14], [14,8], [8,9], [9,10], [14,11], [11,12], [12,13] ]

import cv2
import time
import numpy as np
import matplotlib.pyplot as plt


frame = cv2.imread(r"(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/single.jpeg")
frameCopy = np.copy(frame)
frameWidth = frame.shape[1]
frameHeight = frame.shape[0]
threshold = 0.1

#読み込むモデルを選択
MODE = "MPI"

if MODE is "COCO":
    protoFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/coco/pose_deploy_linevec.prototxt"
    weightsFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/coco/pose_iter_440000.caffemodel"
    nPoints = 18
    POSE_PAIRS = [ [1,0],[1,2],[1,5],[2,3],[3,4],[5,6],[6,7],[1,8],[8,9],[9,10],[1,11],[11,12],[12,13],[0,14],[0,15],[14,16],[15,17]]

elif MODE is "MPI" :
    protoFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt"
    weightsFile = "(ダウンロードしたファイルのディレクトリパス)/learnopencv-master/OpenPose/pose/mpi/pose_iter_160000.caffemodel"
    nPoints = 15
    POSE_PAIRS = [[0,1], [1,2], [2,3], [3,4], [1,5], [5,6], [6,7], [1,14], [14,8], [8,9], [9,10], [14,11], [11,12], [12,13] ]


print("protoFile = ", protoFile)
print("weightsFile = ", weightsFile)
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile)

inWidth = 368
inHeight = 368

inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight),
                          (0, 0, 0), swapRB=False, crop=False)

net.setInput(inpBlob)

output = net.forward()
H = output.shape[2]
W = output.shape[3]

points = []

for i in range(nPoints):
    # confidence map of corresponding body's part.
    probMap = output[0, i, :, :]

    # Find global maxima of the probMap.
    minVal, prob, minLoc, point = cv2.minMaxLoc(probMap)
    
    # Scale the point to fit on the original image
    x = (frameWidth * point[0]) / W
    y = (frameHeight * point[1]) / H

    if prob > threshold : 
        cv2.circle(frameCopy, (int(x), int(y)), 8, (0, 255, 255), thickness=-1, lineType=cv2.FILLED)
        cv2.putText(frameCopy, "{}".format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2, lineType=cv2.LINE_AA)
        cv2.circle(frame, (int(x), int(y)), 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED)

        # Add the point to the list if the probability is greater than the threshold
        points.append((int(x), int(y)))
    else :
        points.append(None)

# Draw Skeleton
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), 3)

print("画像出力")

plt.figure(figsize=[10,10])
plt.imshow(cv2.cvtColor(frameCopy, cv2.COLOR_BGR2RGB))
plt.show()
plt.figure(figsize=[10,10])
plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
plt.show()