IntelのRealsense D435を動かす(3)

darkflowを使って物体認識

環境構築

darkflowの導入

以下のサイトを参考に導入しました。大変助かりました。
http://ai-coordinator.jp/yolov2-tensorflow-python

物体認識

ラベルの横の数字は尤度（それっぽさ？）を表しているみたいです。 cakeが0.6もあるのはいただけないけどすごい。 とりあえず物体を認識することはできた。

コード

## License: Apache 2.0. See LICENSE file in root directory.
## Copyright(c) 2015-2017 Intel Corporation. All Rights Reserved.

###############################################
##      Open CV and Numpy integration        ##
###############################################
from darkflow.net.build import TFNet
import pyrealsense2 as rs
import numpy as np
import cv2

# Configure depth and color streams
pipeline = rs.pipeline()
config = rs.config()
config.enable_stream(rs.stream.depth, 640, 480, rs.format.z16, 30)
config.enable_stream(rs.stream.color, 640, 480, rs.format.bgr8, 30)

# Start streaming
pipeline.start(config)

options = {"model": "cfg/yolo.cfg", "load": "bin/yolo.weights", "threshold": 0.1}
tfnet = TFNet(options)
class_names = ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle',
              'bus', 'car', 'cat', 'chair', 'cow', 'diningtable',
              'dog', 'horse', 'motorbike', 'person', 'pottedplant',
              'sheep', 'sofa', 'train', 'tvmonitor']

num_classes = len(class_names)
class_colors = []
for i in range(0, num_classes):
    hue = 255*i/num_classes
    col = np.zeros((1,1,3)).astype("uint8")
    col[0][0][0] = hue
    col[0][0][1] = 128
    col[0][0][2] = 255
    cvcol = cv2.cvtColor(col, cv2.COLOR_HSV2BGR)
    col = (int(cvcol[0][0][0]), int(cvcol[0][0][1]), int(cvcol[0][0][2]))
    class_colors.append(col)



try:
    while True:

        # Wait for a coherent pair of frames:  color
        frames = pipeline.wait_for_frames()
        color_frame = frames.get_color_frame()
        if not color_frame:
            continue
        # Convert images to numpy arrays
        color_image = np.asanyarray(color_frame.get_data())
        result = tfnet.return_predict(color_image)
        print(result)

        num_classes = len(class_names)
        class_colors = []
        for i in range(0, num_classes):
            hue = 255*i/num_classes
            col = np.zeros((1,1,3)).astype("uint8")
            col[0][0][0] = hue
            col[0][0][1] = 128
            col[0][0][2] = 255
            cvcol = cv2.cvtColor(col, cv2.COLOR_HSV2BGR)
            col = (int(cvcol[0][0][0]), int(cvcol[0][0][1]), int(cvcol[0][0][2]))
            class_colors.append(col)

        for item in result:
            tlx = item['topleft']['x']
            tly = item['topleft']['y']
            brx = item['bottomright']['x']
            bry = item['bottomright']['y']
            label = item['label']
            conf = item['confidence']
            #尤度
            if conf > 0.1:
        
                for i in class_names:
                    if label == i:
                        class_num = class_names.index(i)
                        break
        
                #枠の作成
                cv2.rectangle(color_image, (tlx, tly), (brx, bry), class_colors[class_num], 2)
        
                #ラベルの作成
                text = label + " " + ('%.2f' % conf)
                cv2.rectangle(color_image, (tlx, tly - 15), (tlx + 100, tly + 5), class_colors[class_num], -1)
                cv2.putText(color_image, text, (tlx, tly), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,0), 1)         

            
                
        # Show images
        cv2.namedWindow('RealSense', cv2.WINDOW_AUTOSIZE)
        cv2.imshow('RealSense', color_image)
        cv2.waitKey(1)

finally:

    # Stop streaming
    pipeline.stop()