write pose json

run.py

@@ -27,7 +27,7 @@
                         help='if provided, resize images before they are processed. default=0x0, Recommends : 432x368 or 656x368 or 1312x736 ')
     parser.add_argument('--resize-out-ratio', type=float, default=4.0,
                         help='if provided, resize heatmaps before they are post-processed. default=1.0')
-
+    parser.add_argument('--output_json', type=str, default='/tmp/', help='writing output json dir')
     args = parser.parse_args()
 
     w, h = model_wh(args.resize)
@@ -47,7 +47,7 @@
 
     logger.info('inference image: %s in %.4f seconds.' % (args.image, elapsed))
 
-    image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
+    image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False, frame=0, output_json_dir=args.output_json)
 
     import matplotlib.pyplot as plt
 

run_webcam.py

@@ -29,12 +29,16 @@
                         help='if provided, resize heatmaps before they are post-processed. default=1.0')
 
     parser.add_argument('--model', type=str, default='mobilenet_thin', help='cmu / mobilenet_thin')
+
+    parser.add_argument('--output_json', type=str, default='/tmp/', help='writing output json dir')
+
     parser.add_argument('--show-process', type=bool, default=False,
                         help='for debug purpose, if enabled, speed for inference is dropped.')
     args = parser.parse_args()
 
     logger.debug('initialization %s : %s' % (args.model, get_graph_path(args.model)))
     w, h = model_wh(args.resize)
+
     if w > 0 and h > 0:
         e = TfPoseEstimator(get_graph_path(args.model), target_size=(w, h))
     else:
@@ -44,14 +48,18 @@
     ret_val, image = cam.read()
     logger.info('cam image=%dx%d' % (image.shape[1], image.shape[0]))
 
+    frame = 0
     while True:
         ret_val, image = cam.read()
 
         logger.debug('image process+')
         humans = e.inference(image, resize_to_default=(w > 0 and h > 0), upsample_size=args.resize_out_ratio)
 
         logger.debug('postprocess+')
-        image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
+
+
+        image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False, frame=frame, output_json_dir=args.output_json)
+        frame += 1
 
         logger.debug('show+')
         cv2.putText(image,

tf_pose/estimator.py

@@ -7,7 +7,8 @@
 import numpy as np
 import tensorflow as tf
 import time
-
+import json
+import os
 from tf_pose import common
 from tf_pose.common import CocoPart
 from tf_pose.tensblur.smoother import Smoother
@@ -303,6 +304,7 @@ class TfPoseEstimator:
     def __init__(self, graph_path, target_size=(320, 240), tf_config=None):
         self.target_size = target_size
 
+
         # load graph
         logger.info('loading graph from %s(default size=%dx%d)' % (graph_path, target_size[0], target_size[1]))
         with tf.gfile.GFile(graph_path, 'rb') as f:
@@ -378,12 +380,14 @@ def _quantize_img(npimg):
         return npimg_q
 
     @staticmethod
-    def draw_humans(npimg, humans, imgcopy=False):
+    def draw_humans(npimg, humans, imgcopy=False, frame=0, output_json_dir=None):
         if imgcopy:
             npimg = np.copy(npimg)
         image_h, image_w = npimg.shape[:2]
+        dc = {"people":[]}
         centers = {}
-        for human in humans:
+        for n, human in enumerate(humans):
+            flat = [0.0 for i in range(36)]
             # draw point
             for i in range(common.CocoPart.Background.value):
                 if i not in human.body_parts.keys():
@@ -392,7 +396,11 @@ def draw_humans(npimg, humans, imgcopy=False):
                 body_part = human.body_parts[i]
                 center = (int(body_part.x * image_w + 0.5), int(body_part.y * image_h + 0.5))
                 centers[i] = center
-                cv2.circle(npimg, center, 3, common.CocoColors[i], thickness=3, lineType=8, shift=0)
+                #add x
+                flat[i*2] = center[0]
+                #add y
+                flat[i*2+1] = center[1]
+                cv2.circle(npimg, center, 8, common.CocoColors[i], thickness=3, lineType=8, shift=0)
 
             # draw line
             for pair_order, pair in enumerate(common.CocoPairsRender):
@@ -402,6 +410,13 @@ def draw_humans(npimg, humans, imgcopy=False):
                 # npimg = cv2.line(npimg, centers[pair[0]], centers[pair[1]], common.CocoColors[pair_order], 3)
                 cv2.line(npimg, centers[pair[0]], centers[pair[1]], common.CocoColors[pair_order], 3)
 
+            dc["people"].append({"pose_keypoints_2d" : flat})
+
+        if output_json_dir:
+            with open(os.path.join(output_json_dir, '{0}_keypoints.json'.format(str(frame).zfill(12))), 'w') as outfile:
+                json.dump(dc, outfile)
+
+
         return npimg
 
     def _get_scaled_img(self, npimg, scale):