A novel algorithm named as image cascade semantic segmentation algorithm based on deartifacting dilated residual and bidirectional attention pyramid enhancement is proposed to avoid the disadvantages of an introduction of gridding artifacts for dilated convolutions, the difficulty in fully integrating context information among different scale feature layers for the pyramid pooling module, and lacking sufficient interaction for the same scale features and the cross-scale features in ICNet algorithm. The characterization ability of the network is strengthened since the deartifacting dilated residual network is constructed to remove gridding artifacts introduced by dilated convolutions. After building the bidirectional pyramid pooling module, the semantic information is transmitted to the lower level along a top-down path while the location information is conveyed to the higher level along a bottom-up path. Moreover, the feature interactions for both cross-space and cross-scale are established by the attention pyramid enhancement module, which introduces self-attention, upward attention, and downward attention mechanism. On the Cityscapes dataset, the experimental results show that the overall accuracy, the mean pixel accuracy and the mean intersection over union of the proposed algorithm have been improved by 0.67%, 5.58% and 4.40% respectively compared to ICNet. Compared with the state-of-the-art methods, the presented method achieves outperformance on the above evaluation indexes.
JIANGB, ANX, XUS, et al. Intelligent image semantic segmentation: a review through deep learning techniques for remote sensing image analysis[J]. Journal of the Indian Society of Remote Sensing, 2023, 51(9): 1865-1878.
[2]
SUNY, ZHENGW. HRNet-and PSPNet-based multiband semantic segmentation of remote sensing images[J]. Neural Computing and Applications, 2023, 35(12): 8667-8675.
[3]
SUZ, LIW, MAZ, et al. An improved U-Net method for the semantic segmentation of remote sensing images[J]. Applied Intelligence,2022,52(3): 3276-3288.
[4]
HUANGT, SONGS, LIUQ, et al. A novel multi-exposure fusion approach for enhancing visual semantic segmentation of autonomous driving[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering,2023,237(7): 1652-1667.
[5]
FANJ, GAOB, GEQ, et al. SegTransConv: transformer and CNN hybrid method for real-time semantic segmentation of autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2024,25(2): 1586-1601.
[6]
YASMINS, DURRANIM Y, GILLANIS, et al. Small obstacles detection on roads scenes using semantic segmentation for the safe navigation of autonomous vehicles[J]. Journal of Electronic Imaging, 2022, 31(6): 061806.
[7]
JULIUS FUSICS, HARIHARANK, SITHARTHANR, et al. Scene terrain classification for autonomous vehicle navigation based on semantic segmentation method[J]. Transactions of the Institute of Measurement and Control, 2022, 44(13): 2574-2587.
[8]
RAHMANM M, MARCULESCUR. Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation[C]//Medical Imaging with Deep Learning, PMLR, 2024: 1526-1544.
[9]
HATAMIZADEHA, TANGY, NATHV, et al. UNETR: transformers for 3D medical image segmentation[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022: 1748-1758.
[10]
TYAGIP, MASSONP, JAINA, et al. Automated knowledge transfer for medical image segmentation using deep learning[C]//2024 International Conference on Communication, Computer Sciences and Engineering (IC3SE), 2024: 954-960.
[11]
SHELHAMERE, LONGJ, DARRELLT. Fully convolutional networks for semantic segmentation[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017: 640-651.
[12]
BADRINARAYANANV, KENDALLA, CIPOLLAR. SegNet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017, 39(12): 2481-2495.
[13]
PENGC, ZHANGX, YUG, et al. Large kernel matters--improve semantic segmentation by global convolutional network[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 1743-1751.
[14]
ZHAOH, SHIJ, QIX, et al. Pyramid scene parsing network[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6230-6239.
[15]
YUANY, HUANGL, GUOJ, et al. OCNet: object context for semantic segmentation[J]. International Journal of Computer Vision, 2021, 129(8): 2375-2398.
[16]
ZHAOH, QIX, SHENX, et al. ICNet for real-time semantic segmentation on high-resolution images [C]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018: 418-434.
[17]
ZHANGY, HAREJ, PRÜGEL-BENNETTA. Learning to count objects in natural images for visual question answering[J/OL].[2024-03-02]. arXiv:1802.05766v1.
PENGXiuping, TONGQisheng, LINHongbin, et al. A deep residual-feature pyramid network framework for scattered point cloud semantic segmentation[J]. Acta Automatica Sinica, 2021, 47(12): 2831-2840. (in Chinese)
[20]
PASZKEA, CHAURASIAA, KIMS, et al. ENet: a deep neural network architecture for real-time semantic segmentation[J/OL].[2024-03-02].arXiv:1606. 02147v1.
[21]
WUT, TANGS, ZHANGR, et al. Cgnet: a light-weight context guided network for semantic segmentation[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2021, 30: 1169-1179.
[22]
WANGY, ZHOUQ, LIUJ, et al. Lednet: A lightweight encoder-decoder network for real-time semantic segmentation[C]// IEEE International Conference on Image Processing (ICIP), 2019: 1860-1864.
[23]
TIANZ, HET, SHENC, et al. Decoders matter for semantic segmentation: data-dependent decoding enables flexible feature aggregation[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 3121-3130.
[24]
YUC, WANGJ, PENGC, et al. BiSeNet: bilateral segmentation network for real-time semantic segmentation[C]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018: 334-349.
[25]
ZHANGH, DANAK, SHIJ, et al. Context encoding for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 7151-7160.
[26]
LIUS, QIL, QINH, et al. Path aggregation network for instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 8759-8768.