Zhenguo Hou
ABSTRACT
Scene monitoring and automatic interpretation in construction site scenarios play a crucial role. However, the changes in illumination and weather conditions of construction sites have a significant impact on the imaging quality of visual cameras. The effectiveness of existing semantic segmentation methods is extremely decreased without considering this problem. To solve this issue, we propose the multi-stage feature reconstructed semantic segmentation method for all-day monitor in construction sites. This method aims to improve the robustness against changes in the external environment. Specifically, the self-calibrated module (SCM) is adopted to reconstruct the input image and calculate the effective encoded features. SCM is embedded into the network for several stages to reconstruct multi-level features. Then, the higher-level features are aggregated and enhanced along the channel dimensions, which could obtain more context information. The higher-level is gradually combined with lower-level detailed features for decoding process. The images in construction sites are randomly augmented from different aspects, which could supervise the training process to achieve robust semantic segmentation with the supplement of image reconstruction. The qualitative and quantitative experiments show that compared with several state-of-the-art semantic segmentation methods, the proposed method could better adapt to changes in the environmental conditions and achieve all-day segmentation.
- Wang Z, Zhang Y and Mosalam K M, 2022. Deep semantic segmentation for visual understanding on construction sites. Computer-Aided Civil and Infrastructure Engineering 37, 2, 145-162.Google Scholar
Digital Library
- Yu W D, Liao H C and Hsiao W T, 2020. Automatic safety monitoring of construction hazard working zone: A semantic segmentation based deep learning approach. Proceedings of the 2020 the 7th International Conference on Automation and Logistics (ICAL), pp. 54-59.Google ScholarDigital Library
- Garcia-Garcia A, Orts-Escolano S and Oprea S, 2017. A review on deep learning techniques applied to semantic segmentation. arXiv Preprint arXiv:1704.06857.Google Scholar
- Sun W and Wang R. 2018. Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM. IEEE Geoscience and Remote Sensing Letters 15, 3, 474-478.Google ScholarCross Ref
- Ronneberger O, Fischer P and Brox T. 2015. U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 234-241.Google Scholar
- Girshick R, Donahue J and Darrell T, 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580-587.Google ScholarDigital Library
- Goodfellow I, Pouget-Abadie J and Mirza M, 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27.Google Scholar
- Ma L, Ma T and Liu R, 2022. Toward fast, flexible, and robust low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5637-5646.Google ScholarCross Ref
- Carlos de Carvalho E, Martins Coelho A and Conci A, 2023. U-Net Convolutional Neural Networks for breast IR imaging segmentation on frontal and lateral view. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 11, 3, 311-316.Google ScholarCross Ref
- Zhou Z, Rahman Siddiquee M M and Tajbakhsh N, 2018. Unet++: A nested u-net architecture for medical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 3-11.Google ScholarDigital Library
- Wang H, Jiang X and Ren H, 2021. Swiftnet: Real-time video object segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1296-1305.Google ScholarCross Ref
- Li X, Zhang L and You A, 2019. Global aggregation then local distribution in fully convolutional networks[J]. arXiv Preprint arXiv:1909.07229.Google Scholar
- Yuan Y, Chen X and Wang J. 2020. Object-contextual representations for semantic segmentation. Proceedings of the European Conference on Computer Vision (ECCV), pp. 173-190.Google Scholar
- Yu C, Gao C and Wang J, 2021. Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. Proceedings of the International Journal of Computer Vision (IJCV) 129, 3051-3068.Google ScholarDigital Library
- Zhao H, Shi J and Qi X, 2017. Pyramid scene parsing network. Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 2881-2890.Google ScholarCross Ref
Index Terms
- Multi-Stage Feature Reconstructed Semantic Segmentation of Construction Sites Under Multiple Weather Conditions
Recommendations
White Matter Hyperintensity segmentation using multiple stage FCM
A2CWiC '10: Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in IndiaThe White Matter Hyperintensities (WMH) clearly visible on T2 weighted FLAIR brain MR images are associated with a number of neurodegenerative diseases including Alzheimer's Disease, vascular dementia, stroke, late-onset late-life depression, Multiple ...
kNN-based feature learning network for semantic segmentation of point cloud data
Highlights- A three-part network for semantic segmentation of unorganized point clouds is presented.
- The kNN algorithm is utilized to extract local features from the point features.
- The point, local, and global features are concatenated for ...
AbstractSemantic segmentation of sensed point cloud data plays a significant role in scene understanding and reconstruction, robot navigation, etc. This paper presents a kNN-based 3D semantic segmentation network, which is a structural model for directly ...
Multiple Abdominal Organ Segmentation: An Atlas-Based Fuzzy Connectedness Approach
Organ segmentation is an important step in various medical image applications. In this paper, a presegmented atlas is incorporated into the fuzzy connectedness (FC) framework for automatic segmentation of abdominal organs. First, the atlas is registered ...
Comments