Welcome to DOFBOT-Ultra repository

Deep Pseudo-Color Image

Please ensure that the web control program backend process is not running in the background. To close it, refer to the [Get Started Quickly - 2. Access the Terminal] section in [Disable the Auto-Start Web Control Backend Process]. After closing, please restart DofbotUltra!!!

Before starting this function, you need to close the web control program backend process.

1. Principle Introduction

After the program starts, it converts the subscribed black-and-white depth image into a pseudo-color image. Based on the distance information from the depth data, the image presents different levels of color.

2. Running the Demo

Enter in the terminal:

xxxxxxxxxx
# Start the camera
ros2 launch orbbec_camera dabai_dcw2.launch.py
# Start the depth-to-pseudo-color image program
ros2 run dofbot_ultra_depth depth_to_color

After successful startup as shown in the figure below, a window will be generated displaying the pseudo-color image,

From the actual distance, the depth information differences are intuitively reflected by colors.

3. Program Flowchart

4. Core Code Analysis

The code path is as follows:

xxxxxxxxxx
Raspberry Pi: /home/yahboom/dofbot_ultra_ws/src/dofbot_ultra_depth/dofbot_ultra_depth/depth_to_color.py
RDK: /home/sunrise/dofbot_ultra_ws/src/3d/dofbot_ultra_depth/dofbot_ultra_depth/depth_to_color.py

Code analysis:

Import necessary libraries:

xxxxxxxxxx
#ros2py library
import rclpy
from rclpy.node import Node
#opencv image processing library
import cv2 as cv
#cv_bridge library, used for conversion between message data and image data
from cv_bridge import CvBridge
#Import image data message type
from sensor_msgs.msg import Image

Define image encoding format:

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

Create subscriber and CvBridge object:

xxxxxxxxxx
#define a subscriber, subscribe to /camera/depth/image_raw topic message data, callback function is topic
self.sub = self.create_subscription(Image, '/camera/depth/image_raw', self.topic, 10)
self.depth_bridge = CvBridge()

Callback function, specifically handles received image message data, converts image and displays it:

xxxxxxxxxx
def topic(self,msg):
    #Use the imgmsg_to_cv2 method of the created depth_bridge to convert received message msg data into image data. The input parameters are the received msg data and the image encoding format, here the value is '32FC1'
    depth_image_orin = self.depth_bridge.imgmsg_to_cv2(msg, encoding[1])
    #Call the applyColorMap method in opencv to convert the depth image from the previous step into a pseudo-color image. The input parameters are the depth image scaled proportionally and the color mapping type
    depth_to_color_image = cv.applyColorMap(cv.convertScaleAbs(depth_image_orin, alpha=0.03), cv.COLORMAP_JET)
    #Display image
    cv.imshow(self.window_name, depth_to_color_image)
    cv.waitKey(1)

cv.convertScaleAbs: Used for processing images to enhance contrast or adjust brightness. Input parameters are:

• frame: Input image, usually a numpy array.

• alpha: Scaling factor, default is 1. It affects pixel value scaling.

cv.applyColorMap: A function that applies pseudo-color mapping to grayscale images, which can enhance the visualization effect of images. Input parameters are:

• frame: Input grayscale image, usually a single-channel numpy array.

• colormap: Color mapping type, the following options are available for different effects:

  • COLORMAP_AUTUMN: Gradient from black to red.

  • COLORMAP_BONE: Gradient from gray to blue.

  • COLORMAP_JET: Gradient from blue to red, commonly used for heatmaps.

  • COLORMAP_WINTER: Gradient from blue to green.

  • COLORMAP_RAINBOW: Rainbow color gradient.

  • COLORMAP_OCEAN: Gradient from deep blue to light blue.

  • COLORMAP_SUMMER: Gradient from green to yellow.

  • COLORMAP_SPRING: Gradient from pink to yellow.

  • COLORMAP_COOL: Gradient from cyan to pink.

  • COLORMAP_HSV: Gradient based on HSV color space.

  • COLORMAP_PINK: Gradient from black to pink.

  • COLORMAP_HOT: Gradient from black to red to yellow.

You can change the default COLORMAP_JET in the program to any of the above parameters to test different effects.