Lanenet车道线检测 --运行别人代码（1）
2024-05-11 11:33:25
2018.2发表出来的，文章下载地址：https://arxiv.org/abs/1802.05591
github上代码：https://github.com/MaybeShewill-CV/lanenet-lane-detection
【本文用的还是18年的，没有用最新的】
运行代码时可能出错:
处理：
程序里添加路径
import sys
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/config')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-masterdata_provider')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/lanenet_model')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/encoder_decoder_model')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/tools')
对应文件夹里加入一个空的 __init__.py文件
遇到库文件比如cv2等问题，在pycharm里使用更为方便。本文用的python3.5
测试结果：
2019-05-30 20:47:00.556062: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4861 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0, compute capability: 6.1)
INFO:tensorflow:Restoring parameters from model/tusimple_lanenet/tusimple_lanenet_vgg_2018-10-19-13-33-56.ckpt-200000
I0530 20:47:00.557337 7261 tf_logging.py:115] Restoring parameters from model/tusimple_lanenet/tusimple_lanenet_vgg_2018-10-19-13-33-56.ckpt-200000
I0530 20:47:01.835264 7261 test_lanenet.py:127] 单张图像车道线预测耗时: 1.20088s
预测多张，FPS应该会提高，因为预处理时间。
python tools/test_lanenet.py --is_batch True --batch_size 2 --save_dir data/tusimple_test_image/ret --weights_path model/tusimple_lanenet/tusimple_lanenet_vgg_2018-10-19-13-33-56.ckpt-200000 --image_path data/tusimple_test_image/
I0530 21:02:25.781537 9119 test_lanenet.py:208] [Epoch:2] 预处理2张图像, 共耗时: 0.01650s, 平均每张耗时: 0.00825
I0530 21:02:25.835193 9119 test_lanenet.py:215] [Epoch:2] 预测2张图像车道线, 共耗时: 0.05352s, 平均每张耗时: 0.02676s
I0530 21:02:25.957873 9119 test_lanenet.py:245] [Epoch:2] 进行2张图像车道线聚类, 共耗时: 0.10769s, 平均每张耗时: 0.05384
I0530 21:02:25.957981 9119 test_lanenet.py:198] [Epoch:3] 开始图像读取和预处理...
I0530 21:02:25.975388 9119 test_lanenet.py:208] [Epoch:3] 预处理2张图像, 共耗时: 0.01733s, 平均每张耗时: 0.00866
I0530 21:02:26.029834 9119 test_lanenet.py:215] [Epoch:3] 预测2张图像车道线, 共耗时: 0.05430s, 平均每张耗时: 0.02715s
I0530 21:02:26.092286 9119 test_lanenet.py:245] [Epoch:3] 进行2张图像车道线聚类, 共耗时: 0.04747s, 平均每张耗时: 0.02374
I0530 21:02:26.092393 9119 test_lanenet.py:198] [Epoch:4] 开始图像读取和预处理...
I0530 21:02:26.105244 9119 test_lanenet.py:208] [Epoch:4] 预处理2张图像, 共耗时: 0.01278s, 平均每张耗时: 0.00639
I0530 21:02:26.158836 9119 test_lanenet.py:215] [Epoch:4] 预测2张图像车道线, 共耗时: 0.05346s, 平均每张耗时: 0.02673s
I0530 21:02:26.210763 9119 test_lanenet.py:245] [Epoch:4] 进行2张图像车道线聚类, 共耗时: 0.04204s, 平均每张耗时: 0.02102
I0530 21:02:26.210871 9119 test_lanenet.py:198] [Epoch:5] 开始图像读取和预处理...
I0530 21:02:26.227664 9119 test_lanenet.py:208] [Epoch:5] 预处理2张图像, 共耗时: 0.01670s, 平均每张耗时: 0.00835
I0530 21:02:26.280578 9119 test_lanenet.py:215] [Epoch:5] 预测2张图像车道线, 共耗时: 0.05277s, 平均每张耗时: 0.02638s
I0530 21:02:26.344519 9119 test_lanenet.py:245] [Epoch:5] 进行2张图像车道线聚类, 共耗时: 0.04929s, 平均每张耗时: 0.02465
这下面部分运行除了问题，不要看：
自己加了个视频处理显示的py
#video_test.py 可以读取视频与处理后显示
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# @Time : 18-5-23 上午11:33
# @Author : Luo Yao
# @Site : https://github.com/MaybeShewill-CV/lanenet-lane-detection
# @File : test_lanenet.py
# @IDE: PyCharm Community Edition
"""
测试LaneNet模型
"""
import sys
ros_path = '/opt/ros/kinetic/lib/python2.7/dist-packages'
if ros_path in sys.path:sys.path.remove(ros_path)import cv2sys.path.append('/opt/ros/kinetic/lib/python2.7/dist-packages')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/config')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-masterdata_provider')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/lanenet_model')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/encoder_decoder_model')
sys.path.append('/home/zengjun/下载/lanenet-lane-detection-master/tools')import os
import os.path as ops
import argparse
import time
import mathimport tensorflow as tf
import glob
import glog as log
import numpy as np
import matplotlib.pyplot as plt
import cv2from lanenet_model import lanenet_merge_model
from lanenet_model import lanenet_cluster
from lanenet_model import lanenet_postprocess
from config import global_configCFG = global_config.cfg
VGG_MEAN = [103.939, 116.779, 123.68]def init_args():""":return:"""parser = argparse.ArgumentParser()parser.add_argument('--image_path', type=str, help='The image path or the src image save dir')parser.add_argument('--weights_path', type=str, help='The model weights path')parser.add_argument('--is_batch', type=str, help='If test a batch of images', default='false')parser.add_argument('--batch_size', type=int, help='The batch size of the test images', default=32)parser.add_argument('--save_dir', type=str, help='Test result image save dir', default=None)parser.add_argument('--use_gpu', type=int, help='If use gpu set 1 or 0 instead', default=1)return parser.parse_args()def minmax_scale(input_arr):""":param input_arr::return:"""min_val = np.min(input_arr)max_val = np.max(input_arr)output_arr = (input_arr - min_val) * 255.0 / (max_val - min_val)return output_arr'''
def test_lanenet(image_path, weights_path, use_gpu):""":param image_path::param weights_path::param use_gpu::return:"""assert ops.exists(image_path), '{:s} not exist'.format(image_path)log.info('开始读取图像数据并进行预处理')t_start = time.time()image = cv2.imread(image_path, cv2.IMREAD_COLOR)image_vis = imageimage = cv2.resize(image, (512, 256), interpolation=cv2.INTER_LINEAR)image = image - VGG_MEANlog.info('图像读取完毕, 耗时: {:.5f}s'.format(time.time() - t_start))input_tensor = tf.placeholder(dtype=tf.float32, shape=[1, 256, 512, 3], name='input_tensor')phase_tensor = tf.constant('test', tf.string)net = lanenet_merge_model.LaneNet(phase=phase_tensor, net_flag='vgg')binary_seg_ret, instance_seg_ret = net.inference(input_tensor=input_tensor, name='lanenet_model')cluster = lanenet_cluster.LaneNetCluster()postprocessor = lanenet_postprocess.LaneNetPoseProcessor()saver = tf.train.Saver()# Set sess configurationif use_gpu:sess_config = tf.ConfigProto(device_count={'GPU': 1})else:sess_config = tf.ConfigProto(device_count={'CPU': 0})sess_config.gpu_options.per_process_gpu_memory_fraction = CFG.TEST.GPU_MEMORY_FRACTIONsess_config.gpu_options.allow_growth = CFG.TRAIN.TF_ALLOW_GROWTHsess_config.gpu_options.allocator_type = 'BFC'sess = tf.Session(config=sess_config)with sess.as_default():saver.restore(sess=sess, save_path=weights_path)t_start = time.time()binary_seg_image, instance_seg_image = sess.run([binary_seg_ret, instance_seg_ret],feed_dict={input_tensor: [image]})t_cost = time.time() - t_startlog.info('单张图像车道线预测耗时: {:.5f}s'.format(t_cost))binary_seg_image[0] = postprocessor.postprocess(binary_seg_image[0])mask_image = cluster.get_lane_mask(binary_seg_ret=binary_seg_image[0],instance_seg_ret=instance_seg_image[0])for i in range(4):instance_seg_image[0][:, :, i] = minmax_scale(instance_seg_image[0][:, :, i])embedding_image = np.array(instance_seg_image[0], np.uint8)plt.figure('mask_image')plt.imshow(mask_image[:, :, (2, 1, 0)])plt.figure('src_image')plt.imshow(image_vis[:, :, (2, 1, 0)])plt.figure('instance_image')plt.imshow(embedding_image[:, :, (2, 1, 0)])plt.figure('binary_image')plt.imshow(binary_seg_image[0] * 255, cmap='gray')plt.show()sess.close()return
'''##加入视频转换
#def detect_video(yolo, video_path, output_path=""):
def test_lanenet(video_path, weights_path, use_gpu,output_path=''):
#def detect_video(yolo, output_path=""):import cv2from timeit import default_timer as timerfrom PIL import Image, ImageFont, ImageDrawprint(video_path)vid = cv2.VideoCapture(video_path)#vid = cv2.VideoCapture(0)if not vid.isOpened():raise IOError("Couldn't open webcam or video")video_FourCC = int(vid.get(cv2.CAP_PROP_FOURCC))video_fps = vid.get(cv2.CAP_PROP_FPS)video_size = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))isOutput = True if output_path != "" else Falseif isOutput:print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))out = cv2.VideoWriter(output_path, video_FourCC, video_fps, video_size)accum_time = 0curr_fps = 0fps = "FPS: ??"prev_time = timer()while True:return_value, frame = vid.read()tf.reset_default_graph()image = Image.fromarray(frame)image = cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR)log.info('开始读取图像数据并进行预处理')t_start = time.time()#image = cv2.imread(image_path, cv2.IMREAD_COLOR)image_vis = imageimage = cv2.resize(image, (512, 256), interpolation=cv2.INTER_LINEAR)image = image - VGG_MEANlog.info('图像读取完毕, 耗时: {:.5f}s'.format(time.time() - t_start))input_tensor = tf.placeholder(dtype=tf.float32, shape=[1, 256, 512, 3], name='input_tensor')phase_tensor = tf.constant('test', tf.string)net = lanenet_merge_model.LaneNet(phase=phase_tensor, net_flag='vgg')#tf.reset_default_graph() # zj添加 参考网址：https://blog.csdn.net/mr_brooks/article/details/80393396binary_seg_ret, instance_seg_ret = net.inference(input_tensor=input_tensor, name='lanenet_model')cluster = lanenet_cluster.LaneNetCluster()postprocessor = lanenet_postprocess.LaneNetPoseProcessor()saver = tf.train.Saver()# Set sess configurationif use_gpu:sess_config = tf.ConfigProto(device_count={'GPU': 1})else:sess_config = tf.ConfigProto(device_count={'CPU': 0})sess_config.gpu_options.per_process_gpu_memory_fraction = CFG.TEST.GPU_MEMORY_FRACTIONsess_config.gpu_options.allow_growth = CFG.TRAIN.TF_ALLOW_GROWTHsess_config.gpu_options.allocator_type = 'BFC'sess = tf.Session(config=sess_config)with sess.as_default():saver.restore(sess=sess, save_path=weights_path)t_start = time.time()binary_seg_image, instance_seg_image = sess.run([binary_seg_ret, instance_seg_ret],feed_dict={input_tensor: [image]})t_cost = time.time() - t_startlog.info('单张图像车道线预测耗时: {:.5f}s'.format(t_cost))binary_seg_image[0] = postprocessor.postprocess(binary_seg_image[0])mask_image = cluster.get_lane_mask(binary_seg_ret=binary_seg_image[0],instance_seg_ret=instance_seg_image[0])for i in range(4):instance_seg_image[0][:, :, i] = minmax_scale(instance_seg_image[0][:, :, i])embedding_image = np.array(instance_seg_image[0], np.uint8)'''plt.figure('mask_image')plt.imshow(mask_image[:, :, (2, 1, 0)])plt.figure('src_image')plt.imshow(image_vis[:, :, (2, 1, 0)])plt.figure('instance_image')plt.imshow(embedding_image[:, :, (2, 1, 0)])plt.figure('binary_image')plt.imshow(binary_seg_image[0] * 255, cmap='gray')plt.show()'''result = np.asarray(embedding_image[:, :, (2, 1, 0)])curr_time = timer()exec_time = curr_time - prev_timeprev_time = curr_timeaccum_time = accum_time + exec_timecurr_fps = curr_fps + 1if accum_time > 1:accum_time = accum_time - 1fps = "FPS: " + str(curr_fps)curr_fps = 0cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,fontScale=0.50, color=(255, 0, 0), thickness=2)cv2.namedWindow("result", cv2.WINDOW_NORMAL)cv2.imshow("result", result)if isOutput:out.write(result)if cv2.waitKey(1) & 0xFF == ord('q'):breaksess.close()return def test_lanenet_batch(image_dir, weights_path, batch_size, use_gpu, save_dir=None):""":param image_dir::param weights_path::param batch_size::param use_gpu::param save_dir::return:"""assert ops.exists(image_dir), '{:s} not exist'.format(image_dir)log.info('开始获取图像文件路径...')image_path_list = glob.glob('{:s}/**/*.jpg'.format(image_dir), recursive=True) + \glob.glob('{:s}/**/*.png'.format(image_dir), recursive=True) + \glob.glob('{:s}/**/*.jpeg'.format(image_dir), recursive=True)input_tensor = tf.placeholder(dtype=tf.float32, shape=[None, 256, 512, 3], name='input_tensor')phase_tensor = tf.constant('test', tf.string)net = lanenet_merge_model.LaneNet(phase=phase_tensor, net_flag='vgg')binary_seg_ret, instance_seg_ret = net.inference(input_tensor=input_tensor, name='lanenet_model')cluster = lanenet_cluster.LaneNetCluster()postprocessor = lanenet_postprocess.LaneNetPoseProcessor()saver = tf.train.Saver()# Set sess configurationif use_gpu:sess_config = tf.ConfigProto(device_count={'GPU': 1})else:sess_config = tf.ConfigProto(device_count={'GPU': 0})sess_config.gpu_options.per_process_gpu_memory_fraction = CFG.TEST.GPU_MEMORY_FRACTIONsess_config.gpu_options.allow_growth = CFG.TRAIN.TF_ALLOW_GROWTHsess_config.gpu_options.allocator_type = 'BFC'sess = tf.Session(config=sess_config)with sess.as_default():saver.restore(sess=sess, save_path=weights_path)epoch_nums = int(math.ceil(len(image_path_list) / batch_size))for epoch in range(epoch_nums):log.info('[Epoch:{:d}] 开始图像读取和预处理...'.format(epoch))t_start = time.time()image_path_epoch = image_path_list[epoch * batch_size:(epoch + 1) * batch_size]image_list_epoch = [cv2.imread(tmp, cv2.IMREAD_COLOR) for tmp in image_path_epoch]image_vis_list = image_list_epochimage_list_epoch = [cv2.resize(tmp, (512, 256), interpolation=cv2.INTER_LINEAR)for tmp in image_list_epoch]image_list_epoch = [tmp - VGG_MEAN for tmp in image_list_epoch]t_cost = time.time() - t_startlog.info('[Epoch:{:d}] 预处理{:d}张图像, 共耗时: {:.5f}s, 平均每张耗时: {:.5f}'.format(epoch, len(image_path_epoch), t_cost, t_cost / len(image_path_epoch)))t_start = time.time()binary_seg_images, instance_seg_images = sess.run([binary_seg_ret, instance_seg_ret], feed_dict={input_tensor: image_list_epoch})t_cost = time.time() - t_startlog.info('[Epoch:{:d}] 预测{:d}张图像车道线, 共耗时: {:.5f}s, 平均每张耗时: {:.5f}s'.format(epoch, len(image_path_epoch), t_cost, t_cost / len(image_path_epoch)))cluster_time = []for index, binary_seg_image in enumerate(binary_seg_images):t_start = time.time()binary_seg_image = postprocessor.postprocess(binary_seg_image)mask_image = cluster.get_lane_mask(binary_seg_ret=binary_seg_image,instance_seg_ret=instance_seg_images[index])cluster_time.append(time.time() - t_start)mask_image = cv2.resize(mask_image, (image_vis_list[index].shape[1],image_vis_list[index].shape[0]),interpolation=cv2.INTER_LINEAR)if save_dir is None:plt.ion()plt.figure('mask_image')plt.imshow(mask_image[:, :, (2, 1, 0)])plt.figure('src_image')plt.imshow(image_vis_list[index][:, :, (2, 1, 0)])plt.pause(3.0)plt.show()plt.ioff()if save_dir is not None:mask_image = cv2.addWeighted(image_vis_list[index], 1.0, mask_image, 1.0, 0)image_name = ops.split(image_path_epoch[index])[1]image_save_path = ops.join(save_dir, image_name)cv2.imwrite(image_save_path, mask_image)log.info('[Epoch:{:d}] 进行{:d}张图像车道线聚类, 共耗时: {:.5f}s, 平均每张耗时: {:.5f}'.format(epoch, len(image_path_epoch), np.sum(cluster_time), np.mean(cluster_time)))sess.close()returnif __name__ == '__main__':# init args'''args = init_args()if args.save_dir is not None and not ops.exists(args.save_dir):log.error('{:s} not exist and has been made'.format(args.save_dir))os.makedirs(args.save_dir)if args.is_batch.lower() == 'false':# test hnet model on single imagetest_lanenet(args.video_path, args.weights_path, args.use_gpu)else:# test hnet model on a batch of imagetest_lanenet_batch(image_dir=args.image_path, weights_path=args.weights_path,save_dir=args.save_dir, use_gpu=args.use_gpu, batch_size=args.batch_size)''''''python tools/vedio_test.py --is_batch False --weights_path model/tusimple_lanenet/tusimple_lanenet_vgg_2018-10-19-13-33-56.ckpt-200000 --video_path /home/zengjun/下载/lanenet-lane-detection-master/laneSource.mp4 python tools/vedio_test.py --is_batch False --batch_size 1 --video_path laneSource.mp4 --weights_path path/to/your/model_weights_file '''test_lanenet('/home/zengjun/下载/lanenet-lane-detection-master/laneSource.mp4','/home/zengjun/下载/lanenet-lane-detection-master/model/tusimple_lanenet/tusimple_lanenet_vgg_2018-10-19-13-33-56.ckpt-200000', 1)Lanenet车道线检测 --运行别人代码（1）相关推荐
- Lanenet 车道线检测网络模型学习（论文解读+官方模型）
本文讲解的是用于车道线检测的一个网络结构叫lanenet, 转载请备注,多谢哈|! 2018.2发表出来的,文章下载地址:https://arxiv.org/abs/1802.05591 github ...
- 无人驾驶：车道线检测，附代码
点击上方"3D视觉工坊",选择"星标" 干货第一时间送达 作者丨Dt Pham 编辑丨McGL 在这个项目中,我使用 Python 和 OpenCV 构建了一个 ...
- LaneNet车道线检测tusimple数据集处理
tusimple数据集处理 一.下载数据集 1.官方下载地址 https://github.com/TuSimple/tusimple-benchmark/issues/3,数据集很大,下载速度超级慢 ...
- 车道线检测参考学习资料
一.GitHub: https://github.com/amusi/awesome-lane-detection(全) https://github.com/ChengZhongShen/Advan ...
- Python实现道路车道线检测（附源码）
车道线检测是自动驾驶汽车以及一般计算机视觉的关键组件.这个概念用于描述自动驾驶汽车的路径并避免进入另一条车道的风险. 在本文中,我们将构建一个机器学习项目来实时检测车道线. 我们将使用 OpenCV ...
- python车道线检测
车道线检测是一种利用计算机视觉技术来识别和跟踪道路上的车道线的方法,它对于自动驾驶和智能交通系统等领域有着重要的应用价值.车道线检测的基本步骤如下: 边缘检测:使用Canny算法对输入的图像进行边缘检 ...
- 3.1.1 车道线检测
更多内容,请关注: github:Autopilot-Updating-Notes gitee: Autopilot-Updating-Notes 车道线检测是一种环境感知应用,其目的是通过车载相机或 ...
- 车道线检测1. lanenet代码精读（记录）
前言知识点: 因为公司做自动驾驶,所以打算对自动驾驶中的一些任务有个了解,看看论文,首先是一篇基于2d视觉的一篇车道线检测的文章.首先先上资料,也供大家学习参考,最后一个是3d检测的 Lane Det ...
- 带你读AI论文丨LaneNet基于实体分割的端到端车道线检测
摘要:LaneNet是一种端到端的车道线检测方法,包含 LanNet + H-Net 两个网络模型. 本文分享自华为云社区<[论文解读]LaneNet基于实体分割的端到端车道线检测>,作者 ...
最新文章
- php根据宽度显示html,我怎样才能动态地改变PHP的HTML div的宽度？
- 【Android 逆向】x86 CPU 架构体系 ( CPU 模型 | 内存模型 )
- 简单易懂的多线程(通过实现Runnable接口实现多线程)
- js操作DOM对象（节点的增删改）
- 大剑无锋之Hadoop的三个作业调度器【面试推荐】
- C语言错误： HEAP CORRUPTION DETECTED
- matlab如何解不等式,如何用MATLAB求解不等式组的所有可能解
- 2016年系统集成项目管理工程师最新考试说明
- 服务器返回文件格式,iOS开发--服务器返回的数据解析
- 关于身份证OCR识别，你知道多少？
- linux键盘修改工具,Linux 键盘映射的修改（Console）
- 12，verilog移位操作
- Mysql 数据补位
- abcd选项后的数据分析_引入新的数据abcs
- 主机宝linux版,主机宝linux版有什么用
- 10大好用的语音识别软件
- 第十届蓝桥杯省赛原题及参考答案
- Android网络电话软件Sipdroid试用
- Unity Shader入门精要学习笔记 - 第7章 基础纹理
- 人脸识别是否具有安全隐患？