Attention-based U-Net extensions for Complex Noises of Smart Campus Road Segmentation

Kuan, Ta-Wen; Gu, Yuhang; Chen, Tuoli; Shen, Yunfu

doi:10.1109/icot56925.2022.10008109

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scholars in this field, such as Kuan TW [11] The recent research results of scholars have demonstrated the potential of attention based improved U-Net neural network models in semantic segmentation tasks of moving targets, providing effective ideas and methods for solving key problems in semantic segmentation of moving targets, which is of great significance for promoting progress in this field.…”

Section: Literature Reviewmentioning

confidence: 99%

An Attention-Based Improved U-Net Neural Network Model for Semantic Segmentation of Moving Objects

Cui

2024

IEEE Access

View full text Add to dashboard Cite

The precise semantic segmentation for moving targets has always been a challenging task in computer vision. The existing methods basically had some limitations in semantic segmentation, such as inability to handle deformation of moving targets, blurred boundaries, and other issues. To address the issue, this paper develops an improved U-Net model based on attention mechanism for this purpose. Firstly, we introduce an attention mechanism to enhance the perceptual ability of the U-Net model. By adding attention modules at different levels between the encoder and decoder, the network can pay more attention to the key features of moving targets at different levels. Then, we add a residual module to improve robustness and complete the capsule network for semantic segmentation of moving targets. By learning the deformation information of moving targets, the network can better adapt to moving targets with different shapes. We have conducted experimental verification on multiple public datasets. The experimental results show that the proposed method has superior performance in semantic segmentation tasks of moving targets. Compared with traditional U-Net-based models, the proposal shows significant improvements in accuracy and robustness.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Attention-Based Improved U-Net Neural Network Model for Semantic Segmentation of Moving Objects

Cui

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This may be compared with the scavenger behavior of an herbivorous animal when it seeks out and consumes dead plants for feeding [4]. However, for an SDSB to fully achieve scavenger feeding behavior, many challenges must still be met in terms of machine vision for target detection [5][6][7] and road segmentation outdoors [8,9]. In a modern city, road conditions present a much more complex environment; this includes the presence of many interruptive noises, and the additional factors of changing weather and climate, as well as different kinds of road materials [8].…”

Section: Introductionmentioning

confidence: 99%

EnRDeA U-Net Deep Learning of Semantic Segmentation on Intricate Noise Roads

Kuan

Tseng

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

Road segmentation is beneficial to build a vision-controllable mission-oriented self-driving bot, e.g., the Self-Driving Sweeping Bot, or SDSB, for working in restricted areas. Using road segmentation, the bot itself and physical facilities may be protected and the sweeping efficiency of the SDSB promoted. However, roads in the real world are generally exposed to intricate noise conditions as a result of changing weather and climate effects; these include sunshine spots, shadowing caused by trees or physical facilities, traffic obstacles and signs, and cracks or sealing signs resulting from long-term road usage, as well as different types of road materials, such as cement or asphalt; all of these factors greatly influence the effectiveness of road segmentation. In this work, we investigate the extension of Primordial U-Net by the proposed EnRDeA U-Net, which uses an input channel applying a Residual U-Net block as an encoder and an attention gate in the output channel as a decoder, to validate a dataset of intricate road noises. In addition, we carry out a detailed analysis of the nets’ features and segmentation performance to validate the intricate noises dataset on three U-Net extensions, i.e., the Primordial U-Net, Residual U-Net, and EnRDeA U-Net. Finally, the nets’ structures, parameters, training losses, performance indexes, etc., are presented and discussed in the experimental results.

show abstract

Attention-based U-Net extensions for Complex Noises of Smart Campus Road Segmentation

Cited by 2 publications

References 9 publications

An Attention-Based Improved U-Net Neural Network Model for Semantic Segmentation of Moving Objects

An Attention-Based Improved U-Net Neural Network Model for Semantic Segmentation of Moving Objects

EnRDeA U-Net Deep Learning of Semantic Segmentation on Intricate Noise Roads

Contact Info

Product

Resources

About