基于opencv的人体姿势估计

最新推荐文章于 2024-10-28 19:48:46 发布

AI伐木累

最新推荐文章于 2024-10-28 19:48:46 发布

阅读量387

点赞数

文章标签：深度学习

本文介绍了一种基于视频流的人体姿态实时分析方法，利用深度学习模型将视频分解为帧进行处理，提取并绘制人体关键点，形成实时人体姿势图。通过调整参数如输入宽度、高度和阈值，可以优化人体姿态检测的准确性和效率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

基于视频流，通过解析成一帧一帧的来进行处理，分析视频信息，得到实时人体姿势图

源码实现

# To use Inference Engine backend, specify location of plugins:
# export LD_LIBRARY_PATH=/opt/intel/deeplearning_deploymenttoolkit/deployment_tools/external/mklml_lnx/lib:$LD_LIBRARY_PATH
import cv2 as cv
import numpy as np
import argparse

parser = argparse.ArgumentParser()
parser.add_argument(
    '--input', help='Path to image or video. Skip to capture frames from camera')
parser.add_argument('--thr', default=0.2, type=float,
                    help='Threshold value for pose parts heat map')
parser.add_argument('--width', default=368, type=int,
                    help='Resize input to specific width.')
parser.add_argument('--height', default=368, type=int,
                    help='Resize input to specific height.')

args = parser.parse_args()

BODY_PARTS = {"Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
              "LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
              "RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,
              "LEye": 15, "REar": 16, "LEar": 17, "Background": 18}

POSE_PAIRS = [["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
              ["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],
              ["Neck", "RHip"], ["RHip", "RKnee"], [
    "RKnee", "RAnkle"], ["Neck", "LHip"],
    ["LHip", "LKnee"], ["LKnee", "LAnkle"], [
    "Neck", "Nose"], ["Nose", "REye"],
    ["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"]]

inWidth = args.width
inHeight = args.height

net = cv.dnn.readNetFromTensorflow("graph_opt.pb")

cap = cv.VideoCapture(args.input if args.input else 0)

video_width = int(cap.get(3))
video_height = int(cap.get(4))
fps = int(cap.get(5))
# fps = 15
print(fps)

# fourcc = cv.VideoWriter_fourcc('m', 'p', '4', 'v')  # opencv3.0
# videoWriter = cv.VideoWriter(
#     'detected.mp4', fourcc, fps, (video_width, video_height))

while cv.waitKey(1) < 0:
    hasFrame, frame = cap.read()
    if not hasFrame:
        cv.waitKey()
        break

    frameWidth = frame.shape[1]
    frameHeight = frame.shape[0]

    net.setInput(cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight),
                                      (127.5, 127.5, 127.5), swapRB=True, crop=False))
    out = net.forward()
    # MobileNet output [1, 57, -1, -1], we only need the first 19 elements
    out = out[:, :19, :, :]

    assert(len(BODY_PARTS) == out.shape[1])

    points = []
    for i in range(len(BODY_PARTS)):
        # Slice heatmap of corresponging body's part.
        heatMap = out[0, i, :, :]

        # Originally, we try to find all the local maximums. To simplify a sample
        # we just find a global one. However only a single pose at the same time
        # could be detected this way.
        _, conf, _, point = cv.minMaxLoc(heatMap)
        x = (frameWidth * point[0]) / out.shape[3]
        y = (frameHeight * point[1]) / out.shape[2]
        # Add a point if it's confidence is higher than threshold.
        points.append((int(x), int(y)) if conf > args.thr else None)

    for pair in POSE_PAIRS:
        partFrom = pair[0]
        partTo = pair[1]
        assert(partFrom in BODY_PARTS)
        assert(partTo in BODY_PARTS)

        idFrom = BODY_PARTS[partFrom]
        idTo = BODY_PARTS[partTo]

        if points[idFrom] and points[idTo]:
            cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
            cv.ellipse(frame, points[idFrom], (3, 3),
                       0, 0, 360, (0, 0, 255), cv.FILLED)
            cv.ellipse(frame, points[idTo], (3, 3), 0,
                       0, 360, (0, 0, 255), cv.FILLED)

    t, _ = net.getPerfProfile()
    freq = cv.getTickFrequency() / 1000
    cv.putText(frame, '%.2fms' % (t / freq), (10, 20),
               cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    cv.imshow('OpenPose using OpenCV', frame)
    # videoWriter.write(frame)

    if cv.getWindowProperty('OpenPose using OpenCV', cv.WND_PROP_AUTOSIZE) < 1:
        # 点x退出
        break

# videoWriter.release()
cv.destroyAllWindows()

如何运行？

python openpose.py --input ../XX.mp4 or xx.jpg