Real-Time Jetson Image Classification with OpenCV and GoogLeNet

# ### Import OpenCV for video capture and on-screen drawing.
import cv2
# ### Import the Jetson inference module that provides pretrained classification networks like imageNet.
import jetson.inference
# ### Import Jetson utilities for GPU-friendly image conversions (NumPy <-> CUDA).
import jetson.utils

# ### Open the default camera (index 0) for live capture.
cap = cv2.VideoCapture(0)
# ### Set the camera capture width to 1280 pixels for a 720p layout.
cap.set(3,1280)
# ### Set the camera capture height to 720 pixels.
cap.set(4,720)

# ### Load the pretrained GoogLeNet classifier via jetson.inference.imageNet.
net = jetson.inference.imageNet("googlenet")

# ### Process frames in a loop while the camera is available.
while cap.isOpened():

    # ### Read a frame from the camera as a NumPy array (BGR color order).
    re, img = cap.read()
    
    # ### Convert the BGR frame to RGBA for Jetson utilities and CUDA compatibility.
    frame_rgba = cv2.cvtColor(img, cv2.COLOR_BGR2RGBA)
    # ### Move the RGBA NumPy array into GPU memory as a CUDA image for fast inference.
    cuda_frame = jetson.utils.cudaFromNumpy(frame_rgba)

    # ### Run classification on the CUDA frame and obtain top class ID and confidence score.
    class_id, confidence = net.Classify(cuda_frame)

    # ### Translate the predicted class ID into a human-readable label (e.g., "coffee mug").
    class_desc = net.GetClassDesc(class_id)

    # ### If the prediction is confident enough (greater than 0.40), draw the label on the image.
    if confidence > 0.4:
        cv2.putText(img, class_desc, (30, 80), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 0, 0), 3)

    # ### Show the current frame in a window titled 'img'.
    cv2.imshow('img', img)
    # ### Position the window at the top-left corner of the screen for convenience.
    cv2.moveWindow('img', 0, 0)

    # ### Exit the loop when the user presses the 'q' key.
    if cv2.waitKey(10) & 0xFF == ord('q'):
        break

# ### Release the camera resource gracefully.
cap.release()
# ### Close any OpenCV display windows that may be open.
cv2.destroyAllWindows()

# ### Import OpenCV for video capture and on-screen drawing. import cv2 # ### Import the Jetson inference module that provides pretrained classification networks like imageNet. import jetson.inference # ### Import Jetson utilities for GPU-friendly image conversions (NumPy <-> CUDA). import jetson.utils  # ### Open the default camera (index 0) for live capture. cap = cv2.VideoCapture(0) # ### Set the camera capture width to 1280 pixels for a 720p layout. cap.set(3,1280) # ### Set the camera capture height to 720 pixels. cap.set(4,720)  # ### Load the pretrained GoogLeNet classifier via jetson.inference.imageNet. net = jetson.inference.imageNet("googlenet")  # ### Process frames in a loop while the camera is available. while cap.isOpened():      # ### Read a frame from the camera as a NumPy array (BGR color order).     re, img = cap.read()          # ### Convert the BGR frame to RGBA for Jetson utilities and CUDA compatibility.     frame_rgba = cv2.cvtColor(img, cv2.COLOR_BGR2RGBA)     # ### Move the RGBA NumPy array into GPU memory as a CUDA image for fast inference.     cuda_frame = jetson.utils.cudaFromNumpy(frame_rgba)      # ### Run classification on the CUDA frame and obtain top class ID and confidence score.     class_id, confidence = net.Classify(cuda_frame)      # ### Translate the predicted class ID into a human-readable label (e.g., "coffee mug").     class_desc = net.GetClassDesc(class_id)      # ### If the prediction is confident enough (greater than 0.40), draw the label on the image.     if confidence > 0.4:         cv2.putText(img, class_desc, (30, 80), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 0, 0), 3)      # ### Show the current frame in a window titled 'img'.     cv2.imshow('img', img)     # ### Position the window at the top-left corner of the screen for convenience.     cv2.moveWindow('img', 0, 0)      # ### Exit the loop when the user presses the 'q' key.     if cv2.waitKey(10) & 0xFF == ord('q'):         break  # ### Release the camera resource gracefully. cap.release() # ### Close any OpenCV display windows that may be open. cv2.destroyAllWindows()