TY - GEN
T1 - Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments
AU - Jin, Youngsaeng
AU - Han, David
AU - Ko, Hanseok
N1 - Funding Information:
*This work was supported by Air Force Office of Scientific Research under award number FA2386-19-1-4001. 1Youngsaeng Jin and Hanseok Ko are with the School of Electrical Engineering, Korea University, Seoul 136-713, South Korea youngsjin@korea.ac.kr; hsko@korea.ac.kr 2David K. Han is with Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 dkh42@drexel.edu Fig. 1. Image samples from RUGD dataset [19], collected from off-road, unstructured environments. The numbers below each image are the average pixel intensity of categories ‘sky’ and ‘tree’. Images in this dataset cover a wide range of scenes and their illumination is inconsistent.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85124349539&partnerID=8YFLogxK
U2 - 10.1109/IROS51168.2021.9636620
DO - 10.1109/IROS51168.2021.9636620
M3 - Conference contribution
AN - SCOPUS:85124349539
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 24
EP - 31
BT - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
Y2 - 27 September 2021 through 1 October 2021
ER -