3D Object Recognition

1. Content Description

This course implements the functionality of obtaining color images and using the mediapipe framework to recognize 3D objects (the example only shows four types: mug, shoe, chair, and camera).

2. Program Startup

• Run command in the car terminal:

xxxxxxxxxx
ros2 launch m3_bringup depthcam_demo.launch.py demo:=Objection

After the program runs, the default recognition is for Shoe. You can press the F key to switch the recognized object. As shown in the figure below, a mug is recognized:

3. Core Code Analysis

Program code path:

xxxxxxxxxx
~/yahboomM3_ws/code_ws/src/m3_common_demo/m3_common_demo/mediapipe/07_Objection.py

Import the required library files,

xxxxxxxxxx
import mediapipe as mp
import cv2 as cv
import time
import rclpy
from rclpy.node import Node
from sensor_msgs.msg import Image
from cv_bridge import CvBridge
import os
import numpy as np

Initialize data and define publishers and subscribers,

xxxxxxxxxx
def __init__(self, staticMode=False, maxObjects=5, minDetectionCon=0.5, minTrackingCon=0.99):
    super().__init__('Objection')
    self.staticMode = staticMode
    self.maxObjects = maxObjects
    self.minDetectionCon = minDetectionCon
    self.minTrackingCon = minTrackingCon
    self.index = 0
    self.modelNames = ['Shoe', 'Chair', 'Cup', 'Camera']
    #Use the class in the mediapipe library to define a 3D detection object
    self.mpObjection = mp.solutions.Objection
    self.mpDraw = mp.solutions.drawing_utils
    self.mpObjection = self.mpObjection.Objection(
    self.staticMode, self.maxObjects, self.minDetectionCon, self.minTrackingCon, self.modelNames[self.index])
    self.bridge = CvBridge()
    #Define the subscriber for color image topic
    camera_type = os.getenv('CAMERA_TYPE', 'usb')
    topic_name = '/ascamera_hp60c/camera_publisher/rgb0/image' if camera_type == 'nuwa' else '/usb_cam/image_raw'
    self.subscription = self.create_subscription(
    Image,
    topic_name, 
    self.image_callback,
    10)

Color image callback function,

xxxxxxxxxx
def image_callback(self, msg):
    frame = self.bridge.imgmsg_to_cv2(msg, desired_encoding='bgr8')
    action = cv2.waitKey(1)
    #Press F key to switch recognized objects
    if action == ord('f') or action == ord('F') : self.configUP()
    frame = self.findObjection(frame)
    cv.imshow('Objection', frame)

configUP function for switching recognized objects, selects self.modelNames by modifying the value of self.index, self.modelNames options are ['Shoe', 'Chair', 'Cup', 'Camera']

xxxxxxxxxx
def configUP(self):
    self.index += 1
    if self.index>=4:self.index=0
        self.mpObjection = self.mpObjection.Objection(
        self.staticMode, self.maxObjects, self.minDetectionCon, self.minTrackingCon,            self.modelNames[self.index])

findObjection object recognition function,

xxxxxxxxxx
def findObjection(self, frame):
    cv.putText(frame, self.modelNames[self.index], (int(frame.shape[1] / 2) - 30, 30),
    cv.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 3)
    #Convert the color space of the input image from BGR to RGB for subsequent image processing
    img_RGB = cv.cvtColor(frame, cv.COLOR_BGR2RGB)
    #Call the process function in the mediapipe library for image processing. In init, the self.pose object was created and initialized
    results = self.mpObjection.process(img_RGB)
    #Check if target object is recognized
    if results.detected_objects:
        for id, detection in enumerate(results.detected_objects):
            #Draw coordinate system for the recognized target object on the image
            self.mpDraw.draw_landmarks(frame, detection.landmarks_2d, self.mpObjection.BOX_CONNECTIONS)
            self.mpDraw.draw_axis(frame, detection.rotation, detection.translation)
    return frame