A multimodal semantic segmentation model was proposed for indoor scene perception tasks. Existing multimodal fusion methods mainly focus on a single modality, such as RGB or depth image attention, while lacking effective utilization of attention in the joint feature space after modality fusion. Additionally, many networks suffer from a significant drop in accuracy when the number of parameters is reduced, due to their large parameter sizes. The RGB and depth features are extracted using ConvNeXt and MiT, respectively. A Cross-modal Feature Correction Module (CMFCM) is introduced to enhance spatial and channel features, facilitating interaction and correction between modalities. Additionally, a Cross-modal Attention Fusion Module (CMAFM) is designed to apply attention in the joint feature space, enabling effective multi-scale feature fusion and maximizing the utilization of segmentation information from both modalities. Depthwise separable convolution is also employed to significantly reduce computational costs. Finally, experiments on the NYU-Depth V2 dataset show that, compared with CMX, Dformer, and SA-Gate models, the proposed method improves segmentation accuracy by 1% while reducing the number of parameters by 15.1%, significantly lowering computational complexity.
语义分割作为理解图像场景的核心技术,已成为图像处理和计算机视觉领域的研究热点。由于室内场景存在语义类别多、互相遮挡和光照不均匀等问题,室内语义分割仍是最具挑战性的分割任务之一[1]。传统的目标分割技术通常基于RGB图像,但仅通过RGB图像的分割结果容易受到光照条件的影响,具有一定的局限性。深度相机通过结构光或飞行时间(Time of flight, ToF)技术发射红外光或激光以获取深度信息,进而获取目标距离和三维结构等几何信息。即使在低光照条件下,深度信息仍然可以获取距离和形状信息,对RGB数据进行补充,改善语义分割效果。近年来,RGB与深度图像结合已成为语义分割研究的一个重要方向。通过利用RGB数据的纹理、颜色特征以及深度数据的几何和空间信息,可以显著提升分割的准确性。
WangWen-jun. Research on semantic segmentation of point cloud data based on deep convolutional neural networks[D].Chengdu: School of Information and Communication Engineering, University of Electronic Science and Technology of China, 2024.
[3]
JiangJin-dong, ZhengLu-nan, LuoFei, et al. Rednet: residual encoder-decoder network for indoor RGB-D semantic segmentation[J/OL]. [2025-02-10].
[4]
SeichterD, KöhlerM, LewandowskiB, et al. Efficient RGB-D semantic segmentation for indoor scene analysis[C]//2021 IEEE International Conference on Robotics and Automation, Xi'an, China, 2021: 13525-13531.
[5]
DuS Q, TangS J, WangW X, et al. PSCNET: efficient RGB-D semantic segmentation parallel network based on spatial and channel attention[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, 1: 129-136.
[6]
ChenX, LinK Y, WangJ, et al. Bi-directional cross-modality feature propagation with separation-and-aggregation gate for RGB-D semantic segmentation[C]//European Conference on Computer Vision, Glasgow, UK, 2020: 561-577.
[7]
ZhangJia-ming, LiuHua-yao, YangKai-lun, et al. CMX: cross-modal fusion for RGB-X semantic segmentation with transformers[J]. IEEE Transactions on Intelligent Transportation Systems, 2023,24(12): 14679-14694.
[8]
YinBo-wen, ZhangXu-ying, LiZhong-yu, et al. Dformer: rethinking RGBD representation learning for semantic segmentation[J/OL].[2025-02-10].
[9]
BuiM, AlexisK. Diffusion-based RGB-D semantic segmentation with deformable attention transformer[J/OL].[2025-02-10].
[10]
DongS, FengY, YangQ, et al. Efficient multimodal semantic segmentation via dual-prompt learning[C]//2024 IEEE/RSJ International Conference on Intelligent Robots and Systems, Abu Dhabi, UAE, 2024: 14196-14203.
MiaoJun, YanJie, DuRong-hua, et al. Object pose estimation method based on bidirectional feature fusion[J]. Journal of Jilin University (Engineering and Technology Edition), 2026, 56(2): 523-532.
WangXue, LiZhan-shan, Ying-daLyu. Medical image segmentation algorithm based on multi-scale perception and semantic adaptation[J]. Journal of Jilin University (Engineering and Technology Edition),2022, 52(3): 640-647.
ZhouDa-ke, ZhangChao, YangXin. Self-supervised 3D face reconstruction based on multi-scale feature fusion and dual attention mechanism[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(10): 2428-2437.
[17]
XieE, WangW, YuZ, et al. SegFormer: simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.
[18]
LiuZ, MaoH, WuC Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 11976-11986.
[19]
SongY, WenJ, LiuD, et al. Deep robotic grasping prediction with hierarchical RGB-D fusion[J]. International Journal of Control, Automation and Systems, 2022, 20(1): 243-254.
[20]
LiuZ, TanY, HeQ, et al. SwinNet: swin transformer drives edge-aware RGB-D and RGB-T salient object detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(7): 4486-4497.
QianBai-yun, LvChao-yang, ZhangWei-ning, et al. Phase condenser rotor fault diagnosis based on multi-sensor information fusion and mixed receptive field residual convolutional neural network[J]. Computer Measurement & Control, 2023, 31(9): 29-35.