PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation
Rui Fan,Yuan Wang,Lei Qiao,Ruiwen Yao,Peng Han,Weidong Zhang,Ioannis Pitas,Ming Liu +7 more
- pp 1-5
Reads0
Chats0
TLDR
A residual network trained for semantic road segmentation is presented, which achieves a maximum F1-measure of approximately 91.19%, when analyzing the images from the KITTI road dataset.Abstract:
Semantic road region segmentation is a high-level task, which paves the way towards road scene understanding. This paper presents a residual network trained for semantic road segmentation. Firstly, we represent the projections of road disparities in the v-disparity map as a linear model, which can be estimated by optimizing the v-disparity map using dynamic programming. This linear model is then utilized to reduce the redundant information in the left and right road images. The right image is also transformed into the left perspective view, which greatly enhances the road surface similarity between the two images. Finally, the processed stereo images and their disparity maps are concatenated to create a set of 3D images, which are then utilized to train our neural network. The experimental results illustrate that our network achieves a maximum F1-measure of approximately 91.19%, when analyzing the images from the KITTI road dataset.read more
Citations
More filters
Posted Content
RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation
TL;DR: A lightweight, high-throughput CNN architecture namely RoadNet-RT, successfully implemented on a ZCU102 MPSoC FPGA that achieves the computation capability of 331 GOPS using INT8 quantization, which achieves 92.55% MaxF score on KITTI road segmentation dataset.
Book ChapterDOI
Road Segmentation from Satellite Images Using Custom DNN
TL;DR: In this paper, a simple and custom deep neural network (DNN) has been used for the detection of the road from satellite images, and the road region is denoted by white pixels, and black pixel denotes a non-road region.
References
More filters
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Journal ArticleDOI
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TL;DR: This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.
Posted Content
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TL;DR: DeepLab as discussed by the authors proposes atrous spatial pyramid pooling (ASPP) to segment objects at multiple scales by probing an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views.
Posted Content
Fully Convolutional Networks for Semantic Segmentation
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Posted Content
Rethinking Atrous Convolution for Semantic Image Segmentation
TL;DR: The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.