Pixel-wise Segmentation of Street with Neural Networks

2015-11-02 · Sebastian Bittel, Vitali Kaiser, Marvin Teichmann, Martin Thoma

Pixel-wise street segmentation of photographs taken from a drivers perspective is important for self-driving cars and can also support other object recognition tasks. A framework called SST was developed to examine the accuracy and execution time of different neural networks. The best neural network achieved an $F_1$-score of 89.5% with a simple feedforward neural network which trained to solve a regression task.

📄 PDF Abstract BibTeX arXiv:1511.00513

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition regressionSelf-Driving Cars

OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images

2022-08-01 · CVPR 2023 1 · Weijia Li, Yawen Lai, Linning Xu, Yuanbo Xiangli 외

This paper presents OmniCity, a new dataset for omnipotent city understanding from multi-level and multi-view images. More precisely, the OmniCity contains multi-view satellite images as well as street-level panorama and…

Instance Segmentation Segmentation Semantic Segmentation

Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection

2021-01-21 · Yuxiang Zhang, Sachin Mehta, Anat Caspi

Semantic segmentation aims to robustly predict coherent class labels for entire regions of an image. It is a scene understanding task that powers real-world applications (e.g., autonomous navigation). One important appli…

Autonomous Navigation Model Selection Scene Understanding Segmentation+1

On Boosting Semantic Street Scene Segmentation with Weak Supervision

2019-03-08 · Panagiotis Meletis, Gijs Dubbelman

Training convolutional networks for semantic segmentation requires per-pixel ground truth labels, which are very time consuming and hence costly to obtain. Therefore, in this work, we research and develop a hierarchical …

GPU Scene Segmentation Segmentation Semantic Segmentation

Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

2015-11-10 · CVPR 2016 6 · Jun Xie, Martin Kiefel, Ming-Ting Sun, Andreas Geiger

Semantic annotations are vital for training models for object recognition, semantic segmentation or scene understanding. Unfortunately, pixelwise annotation of images at very large scale is labor-intensive and only littl…

Object Recognition Scene Understanding Semantic Segmentation

Single Network Panoptic Segmentation for Street Scene Understanding

2019-02-07 · Daan de Geus, Panagiotis Meletis, Gijs Dubbelman

In this work, we propose a single deep neural network for panoptic segmentation, for which the goal is to provide each individual pixel of an input image with a class label, as in semantic segmentation, as well as a uniq…

Instance Segmentation Panoptic Segmentation Scene Understanding Segmentation+1