Peter MaEthan FanSarah HanNatka WojcikSerena Xu
Published © GPL3+

MixPose

AI on the Edge streaming platform for yoga instructors and fitness coaches.

AdvancedFull instructions providedOver 1 day4,732

Things used in this project

Hardware components

NVIDIA Jetson Nano Developer Kit
NVIDIA Jetson Nano Developer Kit
×1
7 Inch LCD Cape for Beagle Bone Black - Touch Display
Seeed 7 Inch LCD Cape for Beagle Bone Black - Touch Display
×1
NVIDIA Shield TV Pro
×1
Webcam, Logitech® HD Pro
Webcam, Logitech® HD Pro
×1

Software apps and online services

NVIDIA JetPack SDK
TensorFlow
TensorFlow
Android Studio
Android Studio

Hand tools and fabrication machines

3D Printer (generic)
3D Printer (generic)

Story

Read more

Schematics

Jetson Schematic

Jetson Schematic

Code

mixpose.py

Python
Code to run MixPose
# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
import time
import argparse
import posenet

parser = argparse.ArgumentParser()
parser.add_argument('--model', type=int, default=101)
parser.add_argument('--cam_id', type=int, default=0)
parser.add_argument('--cam_width', type=int, default=640)
parser.add_argument('--cam_height', type=int, default=480)
parser.add_argument('--scale_factor', type=float, default=0.7125)
parser.add_argument('--file', type=str, default=None, help="Optionally use a video file instead of a live camera")
args = parser.parse_args()

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")

# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util

# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'

# Grab path to current working directory
CWD_PATH = os.getcwd()

# Path to frozen detection graph .pb file, which contains the model that is used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

# Number of classes the object detector can identify
NUM_CLASSES = 6

## Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# Here we use internal utility functions, but anything that returns a
# dictionary mapping integers to appropriate string labels would be fine
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

# Load the Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

    sess = tf.Session(graph=detection_graph)
    model_cfg, model_outputs = posenet.load_model(args.model, sess)
    output_stride = model_cfg['output_stride']
    start = time.time()
    frame_count = 0
# Define input and output tensors (i.e. data) for the object detection classifier

# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')

# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')

# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,640)
ret = video.set(4,480)

while(True):

    input_image, display_image, output_scale = posenet.read_cap(
        video, scale_factor=args.scale_factor, output_stride=output_stride)

    heatmaps_result, offsets_result, displacement_fwd_result, displacement_bwd_result = sess.run(
            model_outputs,
            feed_dict={'image:0': input_image}
    )

    pose_scores, keypoint_scores, keypoint_coords = posenet.decode_multi.decode_multiple_poses(
            heatmaps_result.squeeze(axis=0),
            offsets_result.squeeze(axis=0),
            displacement_fwd_result.squeeze(axis=0),
            displacement_bwd_result.squeeze(axis=0),
            output_stride=output_stride,
            max_pose_detections=10,
            min_pose_score=0.15)

    keypoint_coords *= output_scale

    # TODO this isn't particularly fast, use GL for drawing and display someday...
    skeleton_frame = posenet.draw_skel_and_kp_figureonly(
            display_image, pose_scores, keypoint_scores, keypoint_coords,
            min_pose_score=0.15, min_part_score=0.1)

    #cv2.imshow('posenet', overlay_image)
    
    # Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
    # i.e. a single-column array, where each item in the column has the pixel RGB value
    #ret, frame = video.read()
    frame_expanded = np.expand_dims(skeleton_frame, axis=0)

    # Perform the actual detection by running the model with the image as input
    (boxes, scores, classes, num) = sess.run(
        [detection_boxes, detection_scores, detection_classes, num_detections],
        feed_dict={image_tensor: frame_expanded})

    # Draw the results of the detection (aka 'visulaize the results')
    vis_util.visualize_boxes_and_labels_on_image_array(
        skeleton_frame,
        np.squeeze(boxes),
        np.squeeze(classes).astype(np.int32),
        np.squeeze(scores),
        category_index,
        use_normalized_coordinates=True,
        line_thickness=6,
        min_score_thresh=0.75)

    combined = cv2.add(display_image, skeleton_frame)


    # All the results have been drawn on the frame, so it's time to display it.
    cv2.imshow('Skeleton Tracker', combined)

    
    frame_count += 1
    # Press 'q' to quit
    if cv2.waitKey(1) == ord('q'):
        break
    print('Average FPS: ', frame_count / (time.time() - start))

# Clean up
video.release()
cv2.destroyAllWindows()

MixPose Jetson Repo

MixPose Jetson Repo

Credits

Peter Ma

Peter Ma

44 projects • 293 followers
Prototype Hacker, Hackathon Goer, World Traveler, Ecological balancer, integrationist, technologist, futurist.
Ethan Fan

Ethan Fan

7 projects • 21 followers
Mobile, Watch, and Glass Developer
Sarah Han

Sarah Han

10 projects • 49 followers
Software Engineer, Design, 3D
Natka Wojcik

Natka Wojcik

1 project • 2 followers
Serena Xu

Serena Xu

1 project • 0 followers
Product Designer, Frontend Developer
Thanks to Bensound.

Comments