A Joint Convolutional Neural Networks and Context Transfer for Street Scenes Labeling

05/05/2019
by   Qi Wang, et al.
4

Street scene understanding is an essential task for autonomous driving. One important step towards this direction is scene labeling, which annotates each pixel in the images with a correct class label. Although many approaches have been developed, there are still some weak points. Firstly, many methods are based on the hand-crafted features whose image representation ability is limited. Secondly, they can not label foreground objects accurately due to the dataset bias. Thirdly, in the refinement stage, the traditional Markov Random Filed (MRF) inference is prone to over smoothness. For improving the above problems, this paper proposes a joint method of priori convolutional neural networks at superpixel level (called as "priori s-CNNs") and soft restricted context transfer. Our contributions are threefold: (1) A priori s-CNNs model that learns priori location information at superpixel level is proposed to describe various objects discriminatingly; (2) A hierarchical data augmentation method is presented to alleviate dataset bias in the priori s-CNNs training stage, which improves foreground objects labeling significantly; (3) A soft restricted MRF energy function is defined to improve the priori s-CNNs model's labeling performance and reduce the over smoothness at the same time. The proposed approach is verified on CamVid dataset (11 classes) and SIFT Flow Street dataset (16 classes) and achieves competitive performance.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

page 8

page 10

page 12

research
03/30/2021

Repopulating Street Scenes

We present a framework for automatically reconfiguring images of street ...
research
06/15/2015

Layered Interpretation of Street View Images

We propose a layered street view model to encode both depth and semantic...
research
02/25/2022

Sensing accident-prone features in urban scenes for proactive driving and accident prevention

In urban cities, visual information along and on roadways is likely to d...
research
06/26/2019

End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving

3D semantic scene labeling is a fundamental task for Autonomous Driving....
research
04/26/2020

When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition

Recognizing objects and scenes are two challenging but essential tasks i...
research
07/08/2016

CNN-LTE: a Class of 1-X Pooling Convolutional Neural Networks on Label Tree Embeddings for Audio Scene Recognition

We describe in this report our audio scene recognition system submitted ...
research
12/21/2015

Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs

Our aim is to provide a pixel-wise instance-level labeling of a monocula...

Please sign up or login with your details

Forgot password? Click here to reset