Using Orbbec Astra 3D cameras

Prev Tutorial: Using Kinect and other OpenNI compatible depth sensors

Next Tutorial: Using Creative Senz3D and other Intel RealSense SDK compatible depth sensors

Introduction

This tutorial is devoted to the Astra Series of Orbbec 3D cameras (https://orbbec3d.com/product-astra-pro/). That cameras have a depth sensor in addition to a common color sensor. The depth sensors can be read using the open source OpenNI API with cv::VideoCapture class. The video stream is provided through the regular camera interface.

Installation Instructions

In order to use a depth sensor with OpenCV you should do the following steps:

1. Download the latest version of Orbbec OpenNI SDK (from here https://orbbec3d.com/develop/). Unzip the archive, choose the build according to your operating system and follow installation steps provided in the Readme file. For instance, if you use 64bit GNU/Linux run:

   $ cd Linux/OpenNI-Linux-x64-2.3.0.63/
   $ sudo ./install.sh

   When you are done with the installation, make sure to replug your device for udev rules to take effect. The camera should now work as a general camera device. Note that your current user should belong to group video to have access to the camera. Also, make sure to source OpenNIDevEnvironment file:

   $ source OpenNIDevEnvironment

2. Run the following commands to verify that OpenNI library and header files can be found. You should see something similar in your terminal:

   $ echo $OPENNI2_INCLUDE
   /home/user/OpenNI_2.3.0.63/Linux/OpenNI-Linux-x64-2.3.0.63/Include
   $ echo $OPENNI2_REDIST
   /home/user/OpenNI_2.3.0.63/Linux/OpenNI-Linux-x64-2.3.0.63/Redist

   If the above two variables are empty, then you need to source OpenNIDevEnvironment again. Now you can configure OpenCV with OpenNI support enabled by setting the WITH_OPENNI2 flag in CMake. You may also like to enable the BUILD_EXAMPLES flag to get a code sample working with your Astra camera. Run the following commands in the directory containing OpenCV source code to enable OpenNI support:

   $ mkdir build
   $ cd build
   $ cmake -DWITH_OPENNI2=ON ..

   If the OpenNI library is found, OpenCV will be built with OpenNI2 support. You can see the status of OpenNI2 support in the CMake log:

   --   Video I/O:
   --     DC1394:                      YES (2.2.6)
   --     FFMPEG:                      YES
   --       avcodec:                   YES (58.91.100)
   --       avformat:                  YES (58.45.100)
   --       avutil:                    YES (56.51.100)
   --       swscale:                   YES (5.7.100)
   --       avresample:                NO
   --     GStreamer:                   YES (1.18.1)
   --     OpenNI2:                     YES (2.3.0)
   --     v4l/v4l2:                    YES (linux/videodev2.h)

3. Build OpenCV:

   $ make

Code

The Astra Pro camera has two sensors – a depth sensor and a color sensor. The depth sensors can be read using the OpenNI interface with cv::VideoCapture class. The video stream is not available through OpenNI API and is only provided through the regular camera interface. So, to get both depth and color frames, two cv::VideoCapture objects should be created:

    // Open color stream
    VideoCapture colorStream(CAP_V4L2);
    // Open depth stream
    VideoCapture depthStream(CAP_OPENNI2_ASTRA);

The first object will use the Video4Linux2 interface to access the color sensor. The second one is using OpenNI2 API to retrieve depth data.

Before using the created VideoCapture objects you may want to set up stream parameters by setting objects' properties. The most important parameters are frame width, frame height and fps. For this example, we’ll configure width and height of both streams to VGA resolution as that’s the maximum resolution available for both sensors and we’d like both stream parameters to be the same:

    // Set color and depth stream parameters
    colorStream.set(CAP_PROP_FRAME_WIDTH,  640);
    colorStream.set(CAP_PROP_FRAME_HEIGHT, 480);
    depthStream.set(CAP_PROP_FRAME_WIDTH,  640);
    depthStream.set(CAP_PROP_FRAME_HEIGHT, 480);
    depthStream.set(CAP_PROP_OPENNI2_MIRROR, 0);

For setting and getting some property of sensor data generators use cv::VideoCapture::set and cv::VideoCapture::get methods respectively, e.g. :

    // Print depth stream parameters
    cout << "Depth stream: "
         << depthStream.get(CAP_PROP_FRAME_WIDTH) << "x" << depthStream.get(CAP_PROP_FRAME_HEIGHT)
         << " @" << depthStream.get(CAP_PROP_FPS) << " fps" << endl;

The following properties of cameras available through OpenNI interfaces are supported for the depth generator:

• cv::CAP_PROP_FRAME_WIDTH – Frame width in pixels.
• cv::CAP_PROP_FRAME_HEIGHT – Frame height in pixels.
• cv::CAP_PROP_FPS – Frame rate in FPS.
• cv::CAP_PROP_OPENNI_REGISTRATION – Flag that registers the remapping depth map to image map by changing the depth generator's viewpoint (if the flag is "on") or sets this view point to its normal one (if the flag is "off"). The registration process’ resulting images are pixel-aligned, which means that every pixel in the image is aligned to a pixel in the depth image.

• cv::CAP_PROP_OPENNI2_MIRROR – Flag to enable or disable mirroring for this stream. Set to 0 to disable mirroring

  Next properties are available for getting only:

• cv::CAP_PROP_OPENNI_FRAME_MAX_DEPTH – A maximum supported depth of the camera in mm.
• cv::CAP_PROP_OPENNI_BASELINE – Baseline value in mm.

After the VideoCapture objects are set up you can start reading frames from them.

Note

OpenCV's VideoCapture provides synchronous API, so you have to grab frames in a new thread to avoid one stream blocking while another stream is being read. VideoCapture is not a thread-safe class, so you need to be careful to avoid any possible deadlocks or data races.

As there are two video sources that should be read simultaneously, it’s necessary to create two threads to avoid blocking. Example implementation that gets frames from each sensor in a new thread and stores them in a list along with their timestamps:

    // Create two lists to store frames
    std::list<Frame> depthFrames, colorFrames;
    const std::size_t maxFrames = 64;

    // Synchronization objects
    std::mutex mtx;
    std::condition_variable dataReady;
    std::atomic<bool> isFinish;

    isFinish = false;

    // Start depth reading thread
    std::thread depthReader([&]
    {
        while (!isFinish)
        {
            // Grab and decode new frame
            if (depthStream.grab())
            {
                Frame f;
                f.timestamp = cv::getTickCount();
                depthStream.retrieve(f.frame, CAP_OPENNI_DEPTH_MAP);
                if (f.frame.empty())
                {
                    cerr << "ERROR: Failed to decode frame from depth stream" << endl;
                    break;
                }

                {
                    std::lock_guard<std::mutex> lk(mtx);
                    if (depthFrames.size() >= maxFrames)
                        depthFrames.pop_front();
                    depthFrames.push_back(f);
                }
                dataReady.notify_one();
            }
        }
    });

    // Start color reading thread
    std::thread colorReader([&]
    {
        while (!isFinish)
        {
            // Grab and decode new frame
            if (colorStream.grab())
            {
                Frame f;
                f.timestamp = cv::getTickCount();
                colorStream.retrieve(f.frame);
                if (f.frame.empty())
                {
                    cerr << "ERROR: Failed to decode frame from color stream" << endl;
                    break;
                }

                {
                    std::lock_guard<std::mutex> lk(mtx);
                    if (colorFrames.size() >= maxFrames)
                        colorFrames.pop_front();
                    colorFrames.push_back(f);
                }
                dataReady.notify_one();
            }
        }
    });

VideoCapture can retrieve the following data:

1. data given from the depth generator:
   • cv::CAP_OPENNI_DEPTH_MAP - depth values in mm (CV_16UC1)
   • cv::CAP_OPENNI_POINT_CLOUD_MAP - XYZ in meters (CV_32FC3)
   • cv::CAP_OPENNI_DISPARITY_MAP - disparity in pixels (CV_8UC1)
   • cv::CAP_OPENNI_DISPARITY_MAP_32F - disparity in pixels (CV_32FC1)
   • cv::CAP_OPENNI_VALID_DEPTH_MASK - mask of valid pixels (not occluded, not shaded, etc.) (CV_8UC1)
2. data given from the color sensor is a regular BGR image (CV_8UC3).

When new data are available a reading thread notifies the main thread using a condition variable. A frame is stored in the ordered list – the first frame is the latest one. As depth and color frames are read from independent sources two video streams may become out of sync even when both streams are set up for the same frame rate. A post-synchronization procedure can be applied to the streams to combine depth and color frames into pairs. The sample code below demonstrates this procedure:

    // Pair depth and color frames
    while (!isFinish)
    {
        std::unique_lock<std::mutex> lk(mtx);
        while (!isFinish && (depthFrames.empty() || colorFrames.empty()))
            dataReady.wait(lk);

        while (!depthFrames.empty() && !colorFrames.empty())
        {
            if (!lk.owns_lock())
                lk.lock();

            // Get a frame from the list
            Frame depthFrame = depthFrames.front();
            int64 depthT = depthFrame.timestamp;

            // Get a frame from the list
            Frame colorFrame = colorFrames.front();
            int64 colorT = colorFrame.timestamp;

            // Half of frame period is a maximum time diff between frames
            const int64 maxTdiff = int64(1000000000 / (2 * colorStream.get(CAP_PROP_FPS)));
            if (depthT + maxTdiff < colorT)
            {
                depthFrames.pop_front();
                continue;
            }
            else if (colorT + maxTdiff < depthT)
            {
                colorFrames.pop_front();
                continue;
            }
            depthFrames.pop_front();
            colorFrames.pop_front();
            lk.unlock();

            // Show depth frame
            Mat d8, dColor;
            depthFrame.frame.convertTo(d8, CV_8U, 255.0 / 2500);
            applyColorMap(d8, dColor, COLORMAP_OCEAN);
            imshow("Depth (colored)", dColor);

            // Show color frame
            imshow("Color", colorFrame.frame);

            // Exit on Esc key press
            int key = waitKey(1);
            if (key == 27) // ESC
            {
                isFinish = true;
                break;
            }
        }
    }

In the code snippet above the execution is blocked until there are some frames in both frame lists. When there are new frames, their timestamps are being checked – if they differ more than a half of the frame period then one of the frames is dropped. If timestamps are close enough, then two frames are paired. Now, we have two frames: one containing color information and another one – depth information. In the example above retrieved frames are simply shown with cv::imshow function, but you can insert any other processing code here.

In the sample images below you can see the color frame and the depth frame representing the same scene. Looking at the color frame it's hard to distinguish plant leaves from leaves painted on a wall, but the depth data makes it easy.

Color frame

Depth frame

The complete implementation can be found in orbbec_astra.cpp in samples/cpp/tutorial_code/videoio directory.