本节的内容是生成一个语义分割相机，主要分为：四部分。

一、初始化世界以及添加车辆

二、生成语义分割相机Semantic segmentation camera

三、监听语义分割相机，进行数据处理

四、呈现最终效果

 

一、初始化世界以及添加车辆

这一节承接之前生成车辆的内容（Carla生成车辆）.设置vehicle 为自动控制模式

1.添加车辆的完整代码为：

import glob
import os
import sys
import time
import random
import time
import numpy as np
import cv2	
try:
    sys.path.append(glob.glob('../carla/dist/carla-*%d.%d-%s.egg' % (
        sys.version_info.major,
        sys.version_info.minor,
        'win-amd64' if os.name == 'nt' else 'linux-x86_64'))[0])
except IndexError:
    pass
 
import carla
 
actor_list =  []
try:
	#create client
	client = carla.Client('localhost', 2000)
	client.set_timeout(4.0)
	world = client.get_world() 
	blueprint_library = world.get_blueprint_library()
	bp = blueprint_library.filter("model3")[0]
	spawn_point = random.choice(world.get_map().get_spawn_points())
	vehicle = world.spawn_actor(bp,spawn_point)
    #设置vehicle 为自动控制模式
	vehicle.set_autopilot(enabled=True)
	actor_list.append(vehicle)
	time.sleep(50)
finally:
	for actor in actor_list:
		actor.destroy()
	print("All cleaned up!")

二、添加语义分割相机（Semantic segmentation camera）

1.添加语义分割相机（Semantic segmentation camera）， 生成语义分割相机（Semantic segmentation camera）的方法类似于生成vehicle。

    sem_bp = world.get_blueprint_library().find('sensor.camera.semantic_segmentation')

2.设置Semantic segmentation camera的属性

    IM_WIDTH = 640
    IM_HEIIGHT = 480 
	sem_bp.set_attribute("image_size_x",f"{IM_WIDTH}")
	sem_bp.set_attribute("image_size_y",f"{IM_HEIIGHT}")
	sem_bp.set_attribute("fov",str(105))
	sem_location = carla.Location(0,0,2.5)
	sem_rotation = carla.Rotation(0,0,0)
	sem_transform = carla.Transform(sem_location,sem_rotation)

3.添加Semantic segmentation camera到world中，并在actor list 中添加Semantic segmentation camera。

	sem_cam = world.spawn_actor(sem_bp,sem_transform,attach_to=vehicle,         
                                 attachment_type=carla.AttachmentType.Rigid)
	actor_list.append(sem_cam)

三、监听Semantic segmentation camera数据，并处理Semantic segmentation camera的数据

    sem_cam.listen(lambda image: process_semantic(image))
    def process_semantic(image):
        #将原始图像（即image）转化成语义分割图像
	    image.convert(carla.ColorConverter.CityScapesPalette)
        #对转化后的image进行数据处理，image的初始shape是height*width*4，类型为 32-bit BGRA 
	    array = np.frombuffer(image.raw_data, dtype=np.dtype("uint8"))
	    array = np.reshape(array, (image.height, image.width, 4))
        # 转化后的数据，提取RGB 故只需要前3列数据
	    array = array[:, :, :3]
        #显示图像
	    cv2.imshow("",array)
	    cv2.waitKey(20)
        #return array/255.0 是归一化图像
	    return array/255.0

6.最终完整的代码为

import glob
import os
import sys
import time
import random
import time
import numpy as np
import cv2		
try:
    sys.path.append(glob.glob('../carla/dist/carla-*%d.%d-%s.egg' % (
        sys.version_info.major,
        sys.version_info.minor,
        'win-amd64' if os.name == 'nt' else 'linux-x86_64'))[0])
except IndexError:
    pass
 
import carla
from carla import Transform, Location, Rotation
IM_WIDTH = 640
IM_HEIIGHT = 480 
 
def process_semantic(image):
	image.convert(carla.ColorConverter.CityScapesPalette)
	array = np.frombuffer(image.raw_data, dtype=np.dtype("uint8"))
	array = np.reshape(array, (image.height, image.width, 4))
	array = array[:, :, :3]
	cv2.imshow("",array)
	cv2.waitKey(20)
	return array/255.0
actor_list =  []
try:
	# 连接master
	client = carla.Client('localhost', 2000)
	client.set_timeout(5.0)
	world = client.get_world() 
	blueprint_library = world.get_blueprint_library()
	bp = blueprint_library.filter("model3")[0]
	spawn_point = Transform(Location(x=5.4, y=30.5, z=1.5), Rotation(pitch=0, yaw=-75.8, roll=0.0))
	vehicle = world.spawn_actor(bp,spawn_point)

	vehicle.set_autopilot(enabled=True)
	actor_list.append(vehicle)
	# 添加一个语义分割相机
	sem_cam = None
	sem_bp = world.get_blueprint_library().find('sensor.camera.semantic_segmentation')
	sem_bp.set_attribute("image_size_x",f"{IM_WIDTH}")
	sem_bp.set_attribute("image_size_y",f"{IM_HEIIGHT}")
	sem_bp.set_attribute("fov",str(105))
	sem_location = carla.Location(0,0,2.5)
	sem_rotation = carla.Rotation(0,0,0)
	sem_transform = carla.Transform(sem_location,sem_rotation)
	sem_cam = world.spawn_actor(sem_bp,sem_transform,attach_to=vehicle, attachment_type=carla.AttachmentType.Rigid)
	actor_list.append(sem_cam)
    #监听相机，并显示图像
	sem_cam.listen(lambda image: process_semantic(image))
	time.sleep(50)

finally:
	for actor in actor_list:
		actor.destroy()
	print("All cleaned up!")

7.保存代码为spawn_Semantic_camera.py

8.运行CarlaUE4.exe（位于WindowsNoEditor\文件夹下）

9.打开终端运行spawn_Semantic_camera.py （注意terminal的路径应该是你存放py文件的位置） python spawn_Semantic_camera.py