Getting Started in Python

Introduction

In this tutorial, you will learn how to capture and display color and depth images using OpenCV and the ZED SDK in Python.

Sample Code

Sample code is available on GitHub. Make sure the ZED Python API is installed before launching the sample. Please refer to the Getting Started documentation to proceed with the installation.

Sharing image data between ZED SDK and OpenCV Python

In Python, OpenCV store images in NumPy arrays. Sincet the ZED SDK uses its own sl.Mat class to store image data, we provide a function get_data() to convert the sl.Mat matrix into a NumPy array.

# Create an RGBA sl.Mat object
image_zed = sl.Mat(zed.get_resolution().width, zed.get_resolution().height, sl.MAT_TYPE.MAT_TYPE_8U_C4)
# Retrieve data in a numpy array with get_data()
image_ocv = image_zed.get_data()

Capturing Video

To capture video, use grab() and retrieve_image(). Then use get_data() to retrieve the sl.Mat data into a NumPy array. Display the video using cv2.imshow().

if zed.grab() == SUCCESS :
    # Retrieve the left image in sl.Mat
    zed.retrieve_image(image_zed, sl.VIEW.VIEW_LEFT)
    # Use get_data() to get the numpy array
    image_ocv = image_zed.get_data()
    # Display the left image from the numpy array
    cv2.imshow("Image", image_ocv)

Capturing Depth

A depth map is a 1-channel matrix with 32-bit float values for each pixel. Each value expresses the distance of a pixel in the scene. The depth map can be retrieved using retrieve_measure() and loaded with get_data() into a NumPy array. Please refer to the Depth API for more information.

# Create a sl.Mat with float type (32-bit)
depth_zed = sl.Mat(zed.get_resolution().width, zed.get_resolution().height, sl.MAT_TYPE.MAT_TYPE_32F_C1)

if zed.grab() == SUCCESS :
    # Retrieve depth data (32-bit)
    zed.retrieve_measure(depth_zed, sl.MEASURE.MEASURE_DEPTH)
    # Load depth data into a numpy array
    depth_ocv = depth_zed.get_data()
    # Print the depth value at the center of the image
    print(depth_ocv[int(len(depth_ocv)/2)][int(len(depth_ocv[0])/2)])

Displaying Depth

A NumPy array with 32-bit float values can’t be displayed with cv2.imshow. To display the depth map, we need to normalize the depth values between 0 and 255 (8-bit) and create a black and white representation. Do not use this representation for other purposes than displaying the image.

# Create an RGBA sl.Mat object
image_depth_zed = sl.Mat(zed.getResolution().width, sl.get_resolution().height, sl.MAT_TYPE.MAT_TYPE_8U_C4)

if zed.grab() == SUCCESS :
    # Retrieve the normalized depth image
    zed.retrieve_image(image_depth_zed, sl.VIEW.VIEW_DEPTH)
    # Use get_data() to get the numpy array
    image_depth_ocv = image_depth_zed.get_data()
    # Display the depth view from the cv::Mat object
    cv2.imshow("Image", image_depth_ocv)

UVC Capture

You can also use the ZED as a standard UVC camera in OpenCV to capture raw stereo video using the code snippet below. To get rectified images and calibration with OpenCV, use the native (Python) capture sample available on GitHub.

import cv2
import numpy

# Open the ZED camera
cap = cv2.VideoCapture(0)
if cap.isOpened() == 0:
    exit(-1)

# Set the video resolution to HD720 (2560*720)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 2560)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)

while True :
    # Get a new frame from camera
    retval, frame = cap.read()
    # Extract left and right images from side-by-side
    left_right_image = numpy.split(frame, 2, axis=1)
    # Display images
    cv2.imshow("frame", frame)
    cv2.imshow("right", left_right_image[0])
    cv2.imshow("left", left_right_image[1])
    if cv2.waitKey(30) >= 0 :
        break

exit(0)