Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments

by   Youngsaeng Jin, et al.

With the availability of many datasets tailored for autonomous driving in real-world urban scenes, semantic segmentation for urban driving scenes achieves significant progress. However, semantic segmentation for off-road, unstructured environments is not widely studied. Directly applying existing segmentation networks often results in performance degradation as they cannot overcome intrinsic problems in such environments, such as illumination changes. In this paper, a built-in memory module for semantic segmentation is proposed to overcome these problems. The memory module stores significant representations of training images as memory items. In addition to the encoder embedding like items together, the proposed memory module is specifically designed to cluster together instances of the same class even when there are significant variances in embedded features. Therefore, it makes segmentation networks better deal with unexpected illumination changes. A triplet loss is used in training to minimize redundancy in storing discriminative representations of the memory module. The proposed memory module is general so that it can be adopted in a variety of networks. We conduct experiments on the Robot Unstructured Ground Driving (RUGD) dataset and RELLIS dataset, which are collected from off-road, unstructured natural environments. Experimental results show that the proposed memory module improves the performance of existing segmentation networks and contributes to capturing unclear objects over various off-road, unstructured natural scenes with equivalent computational cost and network parameters. As the proposed method can be integrated into compact networks, it presents a viable approach for resource-limited small autonomous platforms.


page 1

page 3

page 5

page 6

page 7


A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

Research in autonomous driving for unstructured environments suffers fro...

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Off-road image semantic segmentation is challenging due to the presence ...

Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving Scenes

Autonomous vehicles and driving systems use scene parsing as an essentia...

IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments

While several datasets for autonomous navigation have become available i...

TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environments

Vegetation Indices based on paired images of the visible color spectrum ...

Enhancing road signs segmentation using photometric invariants

Road signs detection and recognition in natural scenes is one of the mos...

Capturing Omni-Range Context for Omnidirectional Segmentation

Convolutional Networks (ConvNets) excel at semantic segmentation and hav...

Please sign up or login with your details

Forgot password? Click here to reset