-
Notifications
You must be signed in to change notification settings - Fork 1
/
get_spatial_data2.py
182 lines (149 loc) · 7.95 KB
/
get_spatial_data2.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
#!/usr/bin/env python3
from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np
import time
import blobconverter
'''
Spatial Tiny-yolo example
Performs inference on RGB camera and retrieves spatial location coordinates: x,y,z relative to the center of depth map.
Can be used for tiny-yolo-v3 or tiny-yolo-v4 networks
'''
# Get argument first
# Tiny yolo v3/4 label texts
labelMap = [
"person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train",
"truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench",
"bird", "cat", "dog", "horse", "sheep", "cow", "elephant",
"bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie",
"suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat",
"baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup",
"fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich",
"orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake",
"chair", "sofa", "pottedplant", "bed", "diningtable", "toilet", "tvmonitor",
"laptop", "mouse", "remote", "keyboard", "cell phone", "microwave", "oven",
"toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors",
"teddy bear", "hair drier", "toothbrush"
]
syncNN = True
# Create pipeline
pipeline = dai.Pipeline()
# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
spatialDetectionNetwork = pipeline.create(dai.node.YoloSpatialDetectionNetwork)
monoLeft = pipeline.create(dai.node.MonoCamera)
monoRight = pipeline.create(dai.node.MonoCamera)
stereo = pipeline.create(dai.node.StereoDepth)
xoutRgb = pipeline.create(dai.node.XLinkOut)
xoutNN = pipeline.create(dai.node.XLinkOut)
xoutBoundingBoxDepthMapping = pipeline.create(dai.node.XLinkOut)
xoutDepth = pipeline.create(dai.node.XLinkOut)
xoutRgb.setStreamName("rgb")
xoutNN.setStreamName("detections")
xoutBoundingBoxDepthMapping.setStreamName("boundingBoxDepthMapping")
xoutDepth.setStreamName("depth")
# Properties
camRgb.setPreviewSize(416, 416)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
camRgb.setInterleaved(False)
camRgb.setColorOrder(dai.ColorCameraProperties.ColorOrder.BGR)
monoLeft.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P)
monoLeft.setBoardSocket(dai.CameraBoardSocket.LEFT)
monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P)
monoRight.setBoardSocket(dai.CameraBoardSocket.RIGHT)
# setting node configs
stereo.setDefaultProfilePreset(dai.node.StereoDepth.PresetMode.HIGH_DENSITY)
#stereo.setExtendedDisparity(False)
stereo.setLeftRightCheck(True)
#stereo.setSubpixel(True)
spatialDetectionNetwork.setBlobPath(blobconverter.from_zoo(name='yolo-v4-tiny-tf', shaves=6))
spatialDetectionNetwork.setConfidenceThreshold(0.5)
spatialDetectionNetwork.input.setBlocking(False)
spatialDetectionNetwork.setBoundingBoxScaleFactor(0.5)
spatialDetectionNetwork.setDepthLowerThreshold(100)
spatialDetectionNetwork.setDepthUpperThreshold(5000)
# Yolo specific parameters
spatialDetectionNetwork.setNumClasses(80)
spatialDetectionNetwork.setCoordinateSize(4)
spatialDetectionNetwork.setAnchors(np.array([10,14, 23,27, 37,58, 81,82, 135,169, 344,319]))
spatialDetectionNetwork.setAnchorMasks({ "side26": np.array([1,2,3]), "side13": np.array([3,4,5]) })
spatialDetectionNetwork.setIouThreshold(0.5)
# Linking
monoLeft.out.link(stereo.left)
monoRight.out.link(stereo.right)
camRgb.preview.link(spatialDetectionNetwork.input)
if syncNN:
spatialDetectionNetwork.passthrough.link(xoutRgb.input)
else:
camRgb.preview.link(xoutRgb.input)
spatialDetectionNetwork.out.link(xoutNN.input)
spatialDetectionNetwork.boundingBoxMapping.link(xoutBoundingBoxDepthMapping.input)
stereo.depth.link(spatialDetectionNetwork.inputDepth)
spatialDetectionNetwork.passthroughDepth.link(xoutDepth.input)
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queues will be used to get the rgb frames and nn data from the outputs defined above
previewQueue = device.getOutputQueue(name="rgb", maxSize=4, blocking=False)
detectionNNQueue = device.getOutputQueue(name="detections", maxSize=4, blocking=False)
xoutBoundingBoxDepthMappingQueue = device.getOutputQueue(name="boundingBoxDepthMapping", maxSize=4, blocking=False)
depthQueue = device.getOutputQueue(name="depth", maxSize=4, blocking=False)
startTime = time.monotonic()
counter = 0
fps = 0
color = (255, 255, 255)
while True:
inPreview = previewQueue.get()
inDet = detectionNNQueue.get()
depth = depthQueue.get()
frame = inPreview.getCvFrame()
depthFrame = depth.getFrame() # depthFrame values are in millimeters
depthFrameColor = cv2.normalize(depthFrame, None, 255, 0, cv2.NORM_INF, cv2.CV_8UC1)
depthFrameColor = cv2.equalizeHist(depthFrameColor)
depthFrameColor = cv2.applyColorMap(depthFrameColor, cv2.COLORMAP_HOT)
counter+=1
current_time = time.monotonic()
if (current_time - startTime) > 1 :
fps = counter / (current_time - startTime)
counter = 0
startTime = current_time
detections = inDet.detections
if len(detections) != 0:
boundingBoxMapping = xoutBoundingBoxDepthMappingQueue.get()
roiDatas = boundingBoxMapping.getConfigData()
for roiData in roiDatas:
roi = roiData.roi
roi = roi.denormalize(depthFrameColor.shape[1], depthFrameColor.shape[0])
topLeft = roi.topLeft()
bottomRight = roi.bottomRight()
xmin = int(topLeft.x)
ymin = int(topLeft.y)
xmax = int(bottomRight.x)
ymax = int(bottomRight.y)
cv2.rectangle(depthFrameColor, (xmin, ymin), (xmax, ymax), color, cv2.FONT_HERSHEY_SCRIPT_SIMPLEX)
# If the frame is available, draw bounding boxes on it and show the frame
height = frame.shape[0]
width = frame.shape[1]
for detection in detections:
# Denormalize bounding box
x1 = int(detection.xmin * width)
x2 = int(detection.xmax * width)
y1 = int(detection.ymin * height)
y2 = int(detection.ymax * height)
try:
label = labelMap[detection.label]
except:
label = detection.label
cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, "{:.2f}".format(detection.confidence*100), (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, f"X: {int(detection.spatialCoordinates.x)} mm", (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, f"Y: {int(detection.spatialCoordinates.y)} mm", (x1 + 10, y1 + 65), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, f"Z: {int(detection.spatialCoordinates.z)} mm", (x1 + 10, y1 + 80), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
print(str(label),"\t \t",detection.spatialCoordinates.z / 1000)
cv2.rectangle(frame, (x1, y1), (x2, y2), color, cv2.FONT_HERSHEY_SIMPLEX)
cv2.putText(frame, "NN fps: {:.2f}".format(fps), (2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color)
cv2.imshow("depth", depthFrameColor)
cv2.imshow("rgb", frame)
if cv2.waitKey(1) == ord('q'):
break