GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → qixuxiang → Baidu_Lane_Segmentation

qixuxiang / Baidu_Lane_Segmentation

Licence: MIT license
4th place solution in Baidu Autonomous Driving Lane Segmentation

Programming Languages

python
139335 projects - #7 most used programming language

Labels

autonomous-drivingsemantic-segmentationpaddlepaddle

Projects that are alternatives of or similar to Baidu Lane Segmentation

Deeplabv3
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.
Stars: ✭ 511 (+2589.47%)
Mutual labels:  autonomous-driving, semantic-segmentation
rail marking
proof-of-concept program that detects rail-track with semantic segmentation for autonomous train system
Stars: ✭ 21 (+10.53%)
Mutual labels:  autonomous-driving, semantic-segmentation
Self Driving Golf Cart
Be Driven 🚘
Stars: ✭ 147 (+673.68%)
Mutual labels:  autonomous-driving, semantic-segmentation
Vpgnet
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (ICCV 2017)
Stars: ✭ 382 (+1910.53%)
Mutual labels:  autonomous-driving, semantic-segmentation
Keras Icnet
Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images
Stars: ✭ 85 (+347.37%)
Mutual labels:  autonomous-driving, semantic-segmentation
Openvehiclevision
An opensource lib. for vehicle vision applications (written by MATLAB), lane marking detection, road segmentation
Stars: ✭ 120 (+531.58%)
Mutual labels:  autonomous-driving, semantic-segmentation
Segmentation
TensorFlow implementation of ENet, trained on the Cityscapes dataset.
Stars: ✭ 243 (+1178.95%)
Mutual labels:  autonomous-driving, semantic-segmentation
SelfDrivingCarsControlDesign
Self Driving Cars Longitudinal and Lateral Control Design
Stars: ✭ 96 (+405.26%)
Mutual labels:  autonomous-driving
Paper-Notes
Paper notes in deep learning/machine learning and computer vision
Stars: ✭ 37 (+94.74%)
Mutual labels:  semantic-segmentation
Paddle-Image-Models
A PaddlePaddle version image model zoo.
Stars: ✭ 131 (+589.47%)
Mutual labels:  paddlepaddle
MFNet-pytorch
MFNet-pytorch, image semantic segmentation using RGB-Thermal images
Stars: ✭ 72 (+278.95%)
Mutual labels:  semantic-segmentation
SF-GRU
Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
Stars: ✭ 43 (+126.32%)
Mutual labels:  autonomous-driving
pytorch-UNet
2D and 3D UNet implementation in PyTorch.
Stars: ✭ 107 (+463.16%)
Mutual labels:  semantic-segmentation
PSPNet-Pytorch
Implemetation of Pyramid Scene Parsing Network in Pytorch
Stars: ✭ 26 (+36.84%)
Mutual labels:  semantic-segmentation
multichannel-semseg-with-uda
Multichannel Semantic Segmentation with Unsupervised Domain Adaptation
Stars: ✭ 19 (+0%)
Mutual labels:  semantic-segmentation
Scale-Adaptive-Network
Semantic Image Segmentation by Scale-Adaptive Networks (TIP 2019)
Stars: ✭ 42 (+121.05%)
Mutual labels:  semantic-segmentation
awesome-computer-vision-models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 419 (+2105.26%)
Mutual labels:  semantic-segmentation
The-Kraken-Pathfinding
A tentacle-based pathfinding library for nonholonomic robotic vehicles
Stars: ✭ 24 (+26.32%)
Mutual labels:  autonomous-driving
YOLOP-opencv-dnn
使用OpenCV部署全景驾驶感知网络YOLOP，可同时处理交通目标检测、可驾驶区域分割、车道线检测，三项视觉感知任务，包含C++和Python两种版本的程序实现。本套程序只依赖opencv库就可以运行， 从而彻底摆脱对任何深度学习框架的依赖。
Stars: ✭ 178 (+836.84%)
Mutual labels:  autonomous-driving
Remote-sensing-image-semantic-segmentation-tf2
The remote sensing image semantic segmentation repository based on tf.keras includes backbone networks such as resnet, densenet, mobilenet, and segmentation networks such as deeplabv3+, pspnet, panet, and refinenet.
Stars: ✭ 54 (+184.21%)
Mutual labels:  semantic-segmentation
View All Similar Projects ➔

Baidu_Lane_Segmentation

4th place solution in Baidu Autonomous Driving Lane Segmentation Competition

赛题介绍

比赛链接：无人车车道线检测挑战赛

数据下载地址：

软硬件环境

  • 1080ti
  • RAM>=16G
  • paddlepaddle-gpu>=1.2
  • CUDA>=8.0

复现模型

其中代码复现基本都是从Keras代码翻译到Paddle代码，所以我也贴一下上面几个模型参考的Keras源码地址：

运行

准备

数据

请下载上面数据链接中的所有数据，把训练数据zip包放到data/ApolloDatas/train目录下面并解压，把测试数据zip包放到data/ApolloDatas/test目录下面并解压。

预训练模型

请戳链接下载params文件放到params文件夹下，提取码4qsa 。

训练

python train.py --model=unet

这里训练默认为从头训练，其中unet可以替换为deeplab_v3p，deeplabv3p_ours，multires_unet，dense_unet和pannet，分别对应上面几个模型。

如果用预训练模型请在train.py下把pretrain_model的值改为1。

测试

python predict.py.py --model=unet

其中unet可以替换为deeplab_v3p，deeplabv3p_ours，multires_unet，dense_unet和pannet，分别对应上面几个模型。

方法整理

效果演示

image

感谢

感谢队友universea提供的算力资源和强力输出，比赛之后认识了一堆大佬，这场比赛收获颇丰！

我们的比赛队伍id是Litchll，最终复赛得分0.60763，排名第四。

其他问题

因为模型较大，所以运行时如果内存不足可能报错，这时可尝试调节减小输入的size让代码运行。

欢迎任何形式的PR和issue。

最后附上第一名大佬的解决方案：https://github.com/gujingxiao/Lane-Segmentation-Solution-For-BaiduAI-Autonomous-Driving-Competition ，干货满满！

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].