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

Jin, Youngsaeng; Han, David K.; Ko, Hanseok

doi:10.1109/iros51168.2021.9636620

Cited by 12 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new model of an image segmentation network based on simplified DeconvNet [30] with knowledge transfer based on real or synthetic data was used for off-road image segmentation [26]. A segmentation method that dealt with unexpected lighting changes was proposed by adding a built-in memory module, and a specific encoder structure to cluster together instances of the same class was proposed [31]. Image segmentation was part of the proposed comprehensive solution OFFSEG framework focused on finding regions in the off-road environment that can or cannot be traversed [32].…”

Section: Semantic Segmentation Of Off-road Imagesmentioning

confidence: 99%

OffRoadSynth Open Dataset for Semantic Segmentation using Synthetic-Data-Based Weight Initialization for Autonomous UGV in Off-Road Environments

Małek,

Dybała,

Kordecki

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

This article concerns the issue of image semantic segmentation for the machine vision system of an autonomous Unmanned Ground Vehicle (UGV) moving in an off-road environment. Determining the meaning (semantics) of the areas visible in the recorded image provides a complete understanding of the scene surrounding the autonomous vehicle. It is crucial for the correct determination of a passable route. Nowadays, semantic segmentation is generally solved using convolutional neural networks (CNN), which can take an image as input and output the segmented image. However, proper training of the neural network requires the use of large amounts of data, which becomes problematic in the situation of low availability of large, dedicated image data sets that consider various off-road situations - driving on various types of roads, surrounded by diverse vegetation and in various weather and light conditions. This study introduces a synthetic image dataset called “OffRoadSynth” to address the training data scarcity for off-road scenarios. It has been shown that pre-training the neural network on this synthetic dataset improves image segmentation accuracy compared to other methods, such as random network weight initialization or using larger, generic datasets. Results suggest that using a smaller but domain-dedicated set of synthetic images to initialize network weights for training on the target real-world dataset may be an effective approach to improving semantic segmentation results of images, including those from off-road environments.

show abstract

Section: Semantic Segmentation Of Off-road Imagesmentioning

confidence: 99%

OffRoadSynth Open Dataset for Semantic Segmentation using Synthetic-Data-Based Weight Initialization for Autonomous UGV in Off-Road Environments

Małek,

Dybała,

Kordecki

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…Overall, segmentation approaches can be split into three groups: (1) Manual-based segmentation is defined as the delineation of the borders of anatomical regions that are conducted by experts (e.g., radiologists, pathologists) [8] ; (2) Conventional methods-based segmentation is described as the assignment of labels to pixels or voxels by matching the prior known object model to the image data according to the radiomics features (hand-crated or explicit features) [9] ; (3) Deep-learning-based segmentation as developed for automated feature extraction [10] , [11] , [12] . Segmentation of the lungs in COVID-19 cases involves outlining the contours of the anatomical structures of the lung or infection with computer-assisted techniques in CT or X-ray images.…”

Section: Introductionmentioning

confidence: 99%

A teacher–student framework with Fourier Transform augmentation for COVID-19 infection segmentation in CT images

Chen

Jiang²,

Ko³

et al. 2023

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

Pseudo-trilateral adversarial training for domain adaptive traversability prediction

et al. 2023

View full text Add to dashboard Cite

Traversability prediction is a fundamental perception capability for autonomous navigation. Deep neural networks (DNNs) have been widely used to predict traversability during the last decade. The performance of DNNs is significantly boosted by exploiting a large amount of data. However, the diversity of data in different domains imposes significant gaps in the prediction performance. In this work, we make efforts to reduce the gaps by proposing a novel pseudo-trilateral adversarial model named CALI to perform unsupervised domain adaptation (UDA). Our aim is to transfer the perception model with high data efficiency, eliminate the prohibitively expensive data labeling, and improve the generalization capability during the adaptation from easyto-access source domains to various challenging target domains. Existing UDA methods usually adopt a bilateral zero-sum game structure. We prove that our CALI model -a pseudo-trilateral game structure is advantageous over existing bilateral game structures. This proposed work bridges theoretical analyses and algorithm designs, leading to an efficient UDA model with easy and stable training. We show the superiorities of our proposed model over multiple baselines in several challenging domain adaptation setups. To further validate the effectiveness of our model, we then combine our perception model with a visual planner to build a navigation system and show the high reliability of our model in complex natural environments.

show abstract

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

Cited by 12 publications

References 29 publications

OffRoadSynth Open Dataset for Semantic Segmentation using Synthetic-Data-Based Weight Initialization for Autonomous UGV in Off-Road Environments

OffRoadSynth Open Dataset for Semantic Segmentation using Synthetic-Data-Based Weight Initialization for Autonomous UGV in Off-Road Environments

A teacher–student framework with Fourier Transform augmentation for COVID-19 infection segmentation in CT images

Pseudo-trilateral adversarial training for domain adaptive traversability prediction

Contact Info

Product

Resources

About