RGB & Mono Encoding

This example shows how to set up the encoder node to encode the RGB camera and both grayscale cameras (of DepthAI/OAK-D) at the same time. The RGB is set to 1920x1080 and the grayscale are set to 1280x720 each, all at 30FPS. Each encoded video stream is transferred over XLINK and saved to a respective file.

Pressing Ctrl+C will stop the recording and then convert it using ffmpeg into an mp4 to make it playable. Note that ffmpeg will need to be installed and runnable for the conversion to mp4 to succeed.

Be careful, this example saves encoded video to your host storage. So if you leave it running, you could fill up your storage on your host.

Similiar samples:

Demo

Setup

Please run the install script to download all required dependencies. Please note that this script must be ran from git context, so you have to download the depthai-python repository first and then run the script

git clone https://github.com/luxonis/depthai-python.git
cd depthai-python/examples
python3 install_requirements.py

For additional information, please follow installation guide

Source code

Also available on GitHub

 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
#!/usr/bin/env python3

import depthai as dai

# Create pipeline
pipeline = dai.Pipeline()

# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
monoLeft = pipeline.create(dai.node.MonoCamera)
monoRight = pipeline.create(dai.node.MonoCamera)
ve1 = pipeline.create(dai.node.VideoEncoder)
ve2 = pipeline.create(dai.node.VideoEncoder)
ve3 = pipeline.create(dai.node.VideoEncoder)

ve1Out = pipeline.create(dai.node.XLinkOut)
ve2Out = pipeline.create(dai.node.XLinkOut)
ve3Out = pipeline.create(dai.node.XLinkOut)

ve1Out.setStreamName('ve1Out')
ve2Out.setStreamName('ve2Out')
ve3Out.setStreamName('ve3Out')

# Properties
camRgb.setBoardSocket(dai.CameraBoardSocket.RGB)
monoLeft.setBoardSocket(dai.CameraBoardSocket.LEFT)
monoRight.setBoardSocket(dai.CameraBoardSocket.RIGHT)
# Create encoders, one for each camera, consuming the frames and encoding them using H.264 / H.265 encoding
ve1.setDefaultProfilePreset(30, dai.VideoEncoderProperties.Profile.H264_MAIN)
ve2.setDefaultProfilePreset(30, dai.VideoEncoderProperties.Profile.H265_MAIN)
ve3.setDefaultProfilePreset(30, dai.VideoEncoderProperties.Profile.H264_MAIN)

# Linking
monoLeft.out.link(ve1.input)
camRgb.video.link(ve2.input)
monoRight.out.link(ve3.input)
ve1.bitstream.link(ve1Out.input)
ve2.bitstream.link(ve2Out.input)
ve3.bitstream.link(ve3Out.input)

# Connect to device and start pipeline
with dai.Device(pipeline) as dev:

    # Output queues will be used to get the encoded data from the outputs defined above
    outQ1 = dev.getOutputQueue(name='ve1Out', maxSize=30, blocking=True)
    outQ2 = dev.getOutputQueue(name='ve2Out', maxSize=30, blocking=True)
    outQ3 = dev.getOutputQueue(name='ve3Out', maxSize=30, blocking=True)

    # The .h264 / .h265 files are raw stream files (not playable yet)
    with open('mono1.h264', 'wb') as fileMono1H264, open('color.h265', 'wb') as fileColorH265, open('mono2.h264', 'wb') as fileMono2H264:
        print("Press Ctrl+C to stop encoding...")
        while True:
            try:
                # Empty each queue
                while outQ1.has():
                    outQ1.get().getData().tofile(fileMono1H264)

                while outQ2.has():
                    outQ2.get().getData().tofile(fileColorH265)

                while outQ3.has():
                    outQ3.get().getData().tofile(fileMono2H264)
            except KeyboardInterrupt:
                # Keyboard interrupt (Ctrl + C) detected
                break

    print("To view the encoded data, convert the stream file (.h264/.h265) into a video file (.mp4), using commands below:")
    cmd = "ffmpeg -framerate 30 -i {} -c copy {}"
    print(cmd.format("mono1.h264", "mono1.mp4"))
    print(cmd.format("mono2.h264", "mono2.mp4"))
    print(cmd.format("color.h265", "color.mp4"))

Also available on GitHub

 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
#include <csignal>
#include <iostream>

// Inludes common necessary includes for development using depthai library
#include "depthai/depthai.hpp"

// Keyboard interrupt (Ctrl + C) detected
static std::atomic<bool> alive{true};
static void sigintHandler(int signum) {
    alive = false;
}

int main() {
    using namespace std;
    std::signal(SIGINT, &sigintHandler);

    // Create pipeline
    dai::Pipeline pipeline;

    // Define sources and outputs
    auto camRgb = pipeline.create<dai::node::ColorCamera>();
    auto monoLeft = pipeline.create<dai::node::MonoCamera>();
    auto monoRight = pipeline.create<dai::node::MonoCamera>();
    auto ve1 = pipeline.create<dai::node::VideoEncoder>();
    auto ve2 = pipeline.create<dai::node::VideoEncoder>();
    auto ve3 = pipeline.create<dai::node::VideoEncoder>();

    auto ve1Out = pipeline.create<dai::node::XLinkOut>();
    auto ve2Out = pipeline.create<dai::node::XLinkOut>();
    auto ve3Out = pipeline.create<dai::node::XLinkOut>();

    ve1Out->setStreamName("ve1Out");
    ve2Out->setStreamName("ve2Out");
    ve3Out->setStreamName("ve3Out");

    // Properties
    camRgb->setBoardSocket(dai::CameraBoardSocket::RGB);
    monoLeft->setBoardSocket(dai::CameraBoardSocket::LEFT);
    monoRight->setBoardSocket(dai::CameraBoardSocket::RIGHT);
    // Create encoders, one for each camera, consuming the frames and encoding them using H.264 / H.265 encoding
    ve1->setDefaultProfilePreset(30, dai::VideoEncoderProperties::Profile::H264_MAIN);
    ve2->setDefaultProfilePreset(30, dai::VideoEncoderProperties::Profile::H265_MAIN);
    ve3->setDefaultProfilePreset(30, dai::VideoEncoderProperties::Profile::H264_MAIN);

    // Linking
    monoLeft->out.link(ve1->input);
    camRgb->video.link(ve2->input);
    monoRight->out.link(ve3->input);
    ve1->bitstream.link(ve1Out->input);
    ve2->bitstream.link(ve2Out->input);
    ve3->bitstream.link(ve3Out->input);

    // Connect to device and start pipeline
    dai::Device device(pipeline);

    // Output queues will be used to get the encoded data from the output defined above
    auto outQ1 = device.getOutputQueue("ve1Out", 30, true);
    auto outQ2 = device.getOutputQueue("ve2Out", 30, true);
    auto outQ3 = device.getOutputQueue("ve3Out", 30, true);

    // The .h264 / .h265 files are raw stream files (not playable yet)
    auto videoFile1 = std::ofstream("mono1.h264", std::ios::binary);
    auto videoFile2 = std::ofstream("color.h265", std::ios::binary);
    auto videoFile3 = std::ofstream("mono2.h264", std::ios::binary);
    cout << "Press Ctrl+C to stop encoding..." << endl;

    while(alive) {
        auto out1 = outQ1->get<dai::ImgFrame>();
        videoFile1.write((char*)out1->getData().data(), out1->getData().size());
        auto out2 = outQ2->get<dai::ImgFrame>();
        videoFile2.write((char*)out2->getData().data(), out2->getData().size());
        auto out3 = outQ3->get<dai::ImgFrame>();
        videoFile3.write((char*)out3->getData().data(), out3->getData().size());
    }

    cout << "To view the encoded data, convert the stream file (.h264/.h265) into a video file (.mp4), using a command below:" << endl;
    cout << "ffmpeg -framerate 30 -i mono1.h264 -c copy mono1.mp4" << endl;
    cout << "ffmpeg -framerate 30 -i mono2.h264 -c copy mono2.mp4" << endl;
    cout << "ffmpeg -framerate 30 -i color.h265 -c copy color.mp4" << endl;

    return 0;
}

Got questions?

We’re always happy to help with code or other questions you might have.