DepthAI
Software Stack

ON THIS PAGE

  • Camera isp output
  • Pipeline
  • Source code

Camera isp output

Supported on:RVC2RVC4
This example shows how to use the isp output from the Camera node. Image Signal Processor (ISP) is a key camera component that helps achieve the desired output quality in imaging systems. It is the ISP that converts raw images delivered by an image sensor into a usable form, which can then be used by the embedded vision system for various tasks.This example requires the DepthAI v3 API, see installation instructions.

Pipeline

Source code

Python
C++

Python

Python
GitHub
1import cv2
2import depthai as dai
3
4# Create pipeline
5with dai.Pipeline() as pipeline:
6    # Define source and output
7    cam = pipeline.create(dai.node.Camera).build(dai.CameraBoardSocket.CAM_B)
8    videoQueue = cam.requestOutput((800,400), fps=30).createOutputQueue()
9    videoIsp = cam.requestIspOutput(fps=2).createOutputQueue()
10    # Connect to device and start pipeline
11    pipeline.start()
12    videoIn = videoQueue.get()
13    videoInIsp = videoIsp.get()
14    print(
15        "Standard output resolution = "
16        f"{ videoIn.getCvFrame().shape[1]} x { videoIn.getCvFrame().shape[0]}"
17    )
18    print(
19        f"Isp output resolution = "
20        f"{ videoInIsp.getCvFrame().shape[1]} x { videoInIsp.getCvFrame().shape[0]}"
21    )
22    while pipeline.isRunning():
23        videoIn = videoQueue.tryGet()
24        videoInIsp = videoIsp.tryGet() # Returns 640x400
25        if videoIn:
26            cv2.imshow("video", videoIn.getCvFrame())
27        if videoInIsp:
28            cv2.imshow("videoIsp", videoInIsp.getCvFrame())
29
30        if cv2.waitKey(1) == ord("q"):
31            break

Need assistance?

Head over to Discussion Forum for technical support or any other questions you might have.