-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtruckpooling.py
176 lines (140 loc) · 6.73 KB
/
truckpooling.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
#!/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 detection network demo.
Performs inference on RGB camera and retrieves spatial location coordinates: x,y,z relative to the center of depth map.
'''
'''
# Get argument first
nnBlobPath = str((Path(__file__).parent / Path('../models/mobilenet-ssd_openvino_2021.4_6shave.blob')).resolve().absolute())
if len(sys.argv) > 1:
nnBlobPath = sys.argv[1]
'''
# NN for vehicle detection
nnBlobPath=blobconverter.from_zoo(name="person-detection-retail-0013", shaves=6)
frame_dimension = [544,320]
print("nnBlobPath: ", nnBlobPath)
if not Path(nnBlobPath).exists():
import sys
raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable} install_requirements.py"')
# MobilenetSSD label texts
labelMap = ["unkown", "person"]
syncNN = True
# Create pipeline
pipeline = dai.Pipeline()
# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
spatialDetectionNetwork = pipeline.create(dai.node.MobileNetSpatialDetectionNetwork)
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(frame_dimension[0], frame_dimension[1])
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)
# Align depth map to the perspective of RGB camera, on which inference is done
stereo.setDepthAlign(dai.CameraBoardSocket.RGB)
stereo.setOutputSize(monoLeft.getResolutionWidth(), monoLeft.getResolutionHeight())
spatialDetectionNetwork.setBlobPath(nnBlobPath)
spatialDetectionNetwork.setConfidenceThreshold(0.5)
spatialDetectionNetwork.input.setBlocking(False)
spatialDetectionNetwork.setBoundingBoxScaleFactor(0.5)
spatialDetectionNetwork.setDepthLowerThreshold(100)
spatialDetectionNetwork.setDepthUpperThreshold(5000)
# 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)
xoutBoundingBoxDepthMapping = device.getOutputQueue(name="boundingBoxDepthMapping", maxSize=4, blocking=False)
depthQueue = device.getOutputQueue(name="depth", maxSize=4, blocking=False)
startTime = time.monotonic()
counter = 0
fps = 0
while True:
inPreview = previewQueue.get()
inDet = detectionNNQueue.get()
depth = depthQueue.get()
counter+=1
current_time = time.monotonic()
if (current_time - startTime) > 1 :
fps = counter / (current_time - startTime)
counter = 0
startTime = current_time
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)
detections = inDet.detections
if len(detections) != 0:
boundingBoxMapping = xoutBoundingBoxDepthMapping.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), 255, 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)
cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 255, 0), cv2.FONT_HERSHEY_SIMPLEX)
cv2.putText(frame, "NN fps: {:.2f}".format(fps), (2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, (255,255,255))
cv2.imshow("depth", depthFrameColor)
cv2.resize(frame, [frame_dimension[0]*2,frame_dimension[1]*2])
cv2.imshow("preview", frame)
if cv2.waitKey(1) == ord('q'):
break