Depth Pseudo-Color Image

1. Course Content

Run example programs, convert black and white depth images to pseudo-color images by subscribing to depth color image topics and using OpenCV image processing.

2. Program Startup

For Raspberry Pi 5 users, if the ROS container is not started, you need to start the container first,

bringup_m3

Open a terminal inside the container,

xxxxxxxxxx
exec_m3

• Enter command in terminal:

xxxxxxxxxx
ros2 launch m3_bringup depthcam_demo.launch.py

After startup, as shown in the figure below:

Different colors represent differences in depth information.

3. Source Code Analysis

• Source code path:

xxxxxxxxxx
~/yahboomM3_ws/code_ws/src/m3_common_demo/m3_common_demo/depthcamera/GetDepthColor.py

• Import required library files

xxxxxxxxxx
from cv_bridge import CvBridge
import cv2
from rclpy.node import Node
import rclpy
from sensor_msgs.msg import Image

• Define depth image decoding format

xxxxxxxxxx
encoding = ['16UC1', '32FC1']

• Define subscriber for depth image topic

xxxxxxxxxx
self.sub_depth = self.create_subscription(Image,"/camera/depth/image_raw",self.get_DepthImgCallBack,100)

• Define self.depth_bridge for converting message format to image format that OpenCV can process

xxxxxxxxxx
self.depth_bridge = CvBridge()

• Convert image data message to image

xxxxxxxxxx
depth_image = self.depth_bridge.imgmsg_to_cv2(depth_frame, encoding[1])

• Call OpenCV image processing function cv2.applyColorMap to convert depth map

xxxxxxxxxx
depth_to_color_image = cv2.applyColorMap(cv2.convertScaleAbs(depth_image, alpha=1.0), cv2.COLORMAP_JET)

cv2.convertScaleAbs: Performs linear transformation on image data and converts it to 8-bit unsigned integer (uint8) format, with scaling factor as the scaling factor.

cv2.applyColorMap: A function that converts single-channel grayscale images to pseudo-color images to enhance visualization effects through color mapping. This parameter has two variables: the first variable is a single-channel 8-bit or floating-point image (grayscale image), and the second variable is the color mapping table, with the following optional values:

xxxxxxxxxx
cv2.COLORMAP_AUTUMN            # Red-Orange-Yellow
cv2.COLORMAP_BONE              # Black-White (grayscale with blue tint)
cv2.COLORMAP_HSV               # HSV color space
cv2.COLORMAP_JET               # Blue-Cyan-Yellow-Red (classic heat map)
cv2.COLORMAP_WINTER            # Blue-Green
cv2.COLORMAP_RAINBOW           # Rainbow colors (Red-Purple)
cv2.COLORMAP_OCEAN             # Dark Blue-Light Blue
cv2.COLORMAP_SUMMER            # Green-Yellow
cv2.COLORMAP_SPRING            # Magenta-Yellow
cv2.COLORMAP_COOL              # Cyan-Magenta
cv2.COLORMAP_HSV               # HSV color space cycle
cv2.COLORMAP_PINK              # Pink tones
cv2.COLORMAP_PARULA            # MATLAB Parula style
cv2.COLORMAP_VIRIDIS           # Modern scientific color scale (Green-Purple)
cv2.COLORMAP_INFERNO           # Black-Red-Yellow-White (high contrast)
cv2.COLORMAP_PLASMA            # Purple-Red-Yellow
cv2.COLORMAP_MAGMA             # Black-Red-White
cv2.COLORMAP_TWILIGHT          # Blue-Pink-White gradient