Synch

Author: csaba-luxonis

depthai-core

@@ -31,4 +31,12 @@ Source code
            :language: python
            :linenos:
 
+    .. tab:: C++
+
+        Also `available on GitHub <https://github.com/luxonis/depthai-core/blob/main/examples/src/rgb_rotate_warp.cpp>`__
+
+        .. literalinclude:: ../../../depthai-core/examples/src/rgb_rotate_warp.cpp
+           :language: cpp
+           :linenos:
+
 .. include::  /includes/footer-short.rst

docs/source/samples/rgb_rotate_warp.rst

@@ -46,6 +46,7 @@
 
     # Output queue will be used to get the disparity frames from the outputs defined above
     q = device.getOutputQueue(name="disparity", maxSize=4, blocking=False)
+
     while True:
         inDepth = q.get()  # blocking call, will wait until a new data has arrived
         frame = inDepth.getFrame()

examples/depth_preview.py

@@ -44,7 +44,7 @@
 # Connect to device and start pipeline
 with dai.Device(pipeline) as dev:
 
-    # Prepare data queues
+    # Output queues will be used to get the encoded data from the output defined above
     outQ1 = dev.getOutputQueue('ve1Out', maxSize=30, blocking=True)
     outQ2 = dev.getOutputQueue('ve2Out', maxSize=30, blocking=True)
     outQ3 = dev.getOutputQueue('ve3Out', maxSize=30, blocking=True)

examples/encoding_max_limit.py

@@ -22,6 +22,8 @@
 def clamp(num, v0, v1):
     return max(v0, min(num, v1))
 
+sendCamConfig = False
+
 # Create pipeline
 pipeline = dai.Pipeline()
 
@@ -73,11 +75,6 @@ def clamp(num, v0, v1):
     configQueue = device.getInputQueue(configIn.getStreamName())
     controlQueue = device.getInputQueue(controlIn.getStreamName())
 
-    def displayFrame(name, frame):
-        cv2.imshow(name, frame)
-
-    sendCamConfig = False
-
     # Defaults and limits for manual focus/exposure controls
     expTime = 20000
     expMin = 1
@@ -90,8 +87,8 @@ def displayFrame(name, frame):
     while True:
         inRight = qRight.get()
         inLeft = qLeft.get()
-        displayFrame("right", inRight.getCvFrame())
-        displayFrame("left", inLeft.getCvFrame())
+        cv2.imshow("right", inRight.getCvFrame())
+        cv2.imshow("left", inLeft.getCvFrame())
 
         # Update screen (1ms pooling rate)
         key = cv2.waitKey(1)
@@ -134,6 +131,7 @@ def displayFrame(name, frame):
                 bottomRight.x += stepSize
                 sendCamConfig = True
 
+        # Send new config to camera
         if sendCamConfig:
             cfg = dai.ImageManipConfig()
             cfg.setCropRect(topLeft.x, topLeft.y, bottomRight.x, bottomRight.y)

examples/mono_camera_control.py

@@ -6,8 +6,6 @@
 import depthai as dai
 import numpy as np
 
-flipRectified = True
-
 # Get argument first
 nnPath = str((Path(__file__).parent / Path('models/mobilenet-ssd_openvino_2021.2_6shave.blob')).resolve().absolute())
 if len(sys.argv) > 1:
@@ -21,6 +19,8 @@
 labelMap = ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow",
             "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
 
+flipRectified = True
+
 # Create pipeline
 pipeline = dai.Pipeline()
 
@@ -77,6 +77,7 @@
     qDet = device.getOutputQueue("nn", maxSize=4, blocking=False)
 
     rightFrame = None
+    disparityFrame = None
     detections = []
 
     # nn data, being the bounding box locations, are in <0..1> range - they need to be normalized with frame width/height
@@ -90,8 +91,8 @@ def show(name, frame):
         color = (255, 0, 0)
         for detection in detections:
             bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax))
-            cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
-            cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
+            cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
+            cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
             cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
         # Show the frame
         cv2.imshow(name, frame)

examples/mono_depth_mobilenetssd.py

@@ -27,15 +27,14 @@
     # Output queue will be used to get the grayscale frames from the output defined above
     qRight = device.getOutputQueue(name="right", maxSize=4, blocking=False)
 
-    # Make sure the destination path is present before starting to store the examples
     dirName = "mono_data"
     Path(dirName).mkdir(parents=True, exist_ok=True)
 
     while True:
         inRight = qRight.get()  # Blocking call, will wait until a new data has arrived
         # Data is originally represented as a flat 1D array, it needs to be converted into HxW form
         # Frame is transformed and ready to be shown
-        cv2.imshow("right", inRight.getFrame())
+        cv2.imshow("right", inRight.getCvFrame())
 
         # After showing the frame, it's being stored inside a target directory as a PNG image
         cv2.imwrite(f"{dirName}/{int(time.time() * 1000)}.png", inRight.getFrame())

examples/mono_full_resolution_saver.py

@@ -24,8 +24,8 @@
 
 # Define sources and outputs
 monoRight = pipeline.createMonoCamera()
-nn = pipeline.createMobileNetDetectionNetwork()
 manip = pipeline.createImageManip()
+nn = pipeline.createMobileNetDetectionNetwork()
 manipOut = pipeline.createXLinkOut()
 nnOut = pipeline.createXLinkOut()
 
@@ -41,7 +41,6 @@
 # The NN model expects BGR input. By default ImageManip output type would be same as input (gray in this case)
 manip.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p)
 
-# Define a neural network that will make predictions based on the source frames
 nn.setConfidenceThreshold(0.5)
 nn.setBlobPath(nnPath)
 nn.setNumInferenceThreads(2)
@@ -70,11 +69,12 @@ def frameNorm(frame, bbox):
         return (np.clip(np.array(bbox), 0, 1) * normVals).astype(int)
 
     def displayFrame(name, frame):
+        color = (255, 0, 0)
         for detection in detections:
             bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax))
-            cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
-            cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
-            cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), (255, 0, 0), 2)
+            cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
+            cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
+            cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
         # Show the frame
         cv2.imshow(name, frame)
 

examples/mono_mobilenet.py

@@ -101,9 +101,9 @@
             except:
                 label = t.label
 
-            cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
-            cv2.putText(frame, f"ID: {[t.id]}", (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
-            cv2.putText(frame, t.status.name, (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
+            cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
+            cv2.putText(frame, f"ID: {[t.id]}", (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
+            cv2.putText(frame, t.status.name, (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
             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)

examples/object_tracker.py

@@ -158,9 +158,9 @@ def displayFrame(name, frame):
             except:
                 label = t.label
 
-            cv2.putText(trackerFrame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
-            cv2.putText(trackerFrame, f"ID: {[t.id]}", (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
-            cv2.putText(trackerFrame, t.status.name, (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
+            cv2.putText(trackerFrame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
+            cv2.putText(trackerFrame, f"ID: {[t.id]}", (x1 + 10, y1 + 35), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
+            cv2.putText(trackerFrame, t.status.name, (x1 + 10, y1 + 50), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
             cv2.rectangle(trackerFrame, (x1, y1), (x2, y2), color, cv2.FONT_HERSHEY_SIMPLEX)
 
         cv2.putText(trackerFrame, "Fps: {:.2f}".format(fps), (2, trackerFrame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color)