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

Metzger, Kai A.; Mortimer, Peter; Wuensche, Hans-Joachim

doi:10.1109/icpr48806.2021.9411987

Cited by 12 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For training, we include Cityscapes [31], a widespread benchmark featuring "clean" scenes, as well as more recent driving datasets covering a wide range of environmental conditions, sensor characteristics and geographical contexts including Mapillary [33], Berkeley DeepDrive (BDD) [32] and ACDC [34]. Outside of urban landscapes, RUGD [35], YCOR [37] and TAS500 [38] cover off-road grassy environments. Lastly, IDD [20] brings a unique challenge since it was captured in unstructured Indian traffic and rural scenes.…”

Section: B Cross-domain Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images

Humblot-Renaux

Marchegiani

Moeslund

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

This work tackles scene understanding for outdoor robotic navigation, solely relying on images captured by an onboard camera. Conventional visual scene understanding interprets the environment based on specific descriptive categories. However, such a representation is not directly interpretable for decision-making and constrains robot operation to a specific domain. Thus, we propose to segment egocentric images directly in terms of how a robot can navigate in them, and tailor the learning problem to an autonomous navigation task. Building around an image segmentation network, we present a generic affordance consisting of 3 driveability levels which can broadly apply to both urban and off-road scenes. By encoding these levels with soft ordinal labels, we incorporate inter-class distances during learning which improves segmentation compared to standard "hard" one-hot labelling. In addition, we propose a navigation-oriented pixel-wise loss weighting method which assigns higher importance to safety-critical areas. We evaluate our approach on large-scale public image segmentation datasets ranging from sunny city streets to snowy forest trails. In a crossdataset generalization experiment, we show that our affordance learning scheme can be applied across a diverse mix of datasets and improves driveability estimation in unseen environments compared to general-purpose, single-dataset segmentation.

show abstract

Section: B Cross-domain Datasetsmentioning

confidence: 99%

“…Cityscapes [31] (3,484) Kitti [25] (200) BDD [32] (8,000) Mapillary [33] (20,000) ACDC [34] (2,006) unstructured / off-road RUGD [35] (5492) Freiburg Forest [36] (366) YCOR [37] (1076) TAS500 [38] (540) mixed IDD [20] (8089) WildDash [6] (4256)…”

Section: Scene Typementioning

confidence: 99%

Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images

Humblot-Renaux

Marchegiani

Moeslund

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Similarly, in [17], a real-time terrain mapping method for autonomous excavators is presented, which is able to provide semantic and geometric information for the terrain using RGB images and 3D point cloud data, while a dataset which includes images from construction sites is designed and utilized. Regarding the datasets for earthy unstructured environments, in [18,19], two publicly available datasets were developed for semantic segmentation deep learning models, focusing on self-driving in semiunstructured or dense-vegetated environments. In [18], the dataset designed, for accurate comprehension in scenes with high coverage in grass, asphalt, soil and sand, while authors in [19], targeted more on dense-vegetated and rough terrain scenes for off-road self driving scenarios.…”

Section: Introductionmentioning

confidence: 99%

Lunar ground segmentation using a modified U-net neural network

Petrakis,

Partsinevelos

2024

Machine Vision and Applications

View full text Add to dashboard Cite

Semantic segmentation plays a significant role in unstructured and planetary scene understanding, offering to a robotic system or a planetary rover valuable knowledge about its surroundings. Several studies investigate rover-based scene recognition planetary-like environments but there is a lack of a semantic segmentation architecture, focused on computing systems with low resources and tested on the lunar surface. In this study, a lightweight encoder-decoder neural network (NN) architecture is proposed for rover-based ground segmentation on the lunar surface. The proposed architecture is composed by a modified MobilenetV2 as encoder and a lightweight U-net decoder while the training and evaluation process were conducted using a publicly available synthetic dataset with lunar landscape images. The proposed model provides robust segmentation results, allowing the lunar scene understanding focused on rocks and boulders. It achieves similar accuracy, compared with original U-net and U-net-based architectures which are 110–140 times larger than the proposed architecture. This study, aims to contribute in lunar landscape segmentation utilizing deep learning techniques, while it proves a great potential in autonomous lunar navigation ensuring a safer and smoother navigation on the moon. To the best of our knowledge, this is the first study which propose a lightweight semantic segmentation architecture for the lunar surface, aiming to reinforce the autonomous rover navigation.

show abstract

“…Similarly, in [17], a realtime terrain mapping method for autonomous excavators is presented, which is able to provide semantic and geometric information for the terrain using RGB images and 3D point cloud data, while a dataset which includes images from construction sites is designed and utilized. Regarding the datasets for earthy unstructured environments, in [18,19], two publicly available datasets were developed for semantic segmentation deep learning models, focusing on self-driving in semi-unstructured or densevegetated environments. In [18], the dataset designed, for accurate comprehension in scenes with high coverage in grass, asphalt, soil and sand, while authors in [19], targeted more on dense-vegetated and rough terrain scenes for off-road self driving scenarios.…”

Section: Introductionmentioning

confidence: 99%

“…Regarding the datasets for earthy unstructured environments, in [18,19], two publicly available datasets were developed for semantic segmentation deep learning models, focusing on self-driving in semi-unstructured or densevegetated environments. In [18], the dataset designed, for accurate comprehension in scenes with high coverage in grass, asphalt, soil and sand, while authors in [19], targeted more on dense-vegetated and rough terrain scenes for off-road self driving scenarios.…”

Section: Introductionmentioning

confidence: 99%

Lunar Ground Segmentation Using a Modified U-Net Neural Network

Petrakis,

Partsinevelos

2023

Preprint

View full text Add to dashboard Cite

Semantic segmentation plays a significant role in unstructured and planetary scene understanding, offering to a robotic system or a planetary rover valuable knowledge about its surroundings. Several studies investigate rover-based scene recognition planetary-like environments but there is a lack of a semantic segmentation architecture, focused on computing systems with low resources and tested on the lunar surface. In this study, a lightweight encoder-decoder neural network (NN) architecture is proposed for rover-based ground segmentation on the lunar surface. The proposed architecture is composed by a modified MobilenetV2 as encoder and a lightweight U-net decoder while the training and evaluation process were conducted using a publicly available synthetic dataset with lunar landscape images. The proposed model provides robust segmentation results, allowing the lunar scene understanding focused on rocks and boulders while it achieves similar accuracy, compared with original U-net and U-net-based architectures which are 110–140 times larger than the proposed architecture. This study, aims to contribute in lunar landscape segmentation utilizing deep learning techniques, while it proves a great potential in autonomous lunar navigation ensuring a more safe and smooth navigation on the moon. To the best of our knowledge, this is the first study which propose a lightweight semantic segmentation architecture for the lunar surface, focused on rover navigation.

show abstract

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

Cited by 12 publications

References 31 publications

Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images

Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images

Lunar ground segmentation using a modified U-net neural network

Lunar Ground Segmentation Using a Modified U-Net Neural Network

Contact Info

Product

Resources

About