Development of data fusion methods based on wavelet decomposition for multichannel machine vision systems in robotics
How to cite
Abstract
This article presents an innovative method of data fusion based on wavelet decomposition for multichannel machine vision systems in robotics. The proposed approach solves the problem of effective integration and processing of heterogeneous data obtained from multiple sources of visual information, combining the advantages of multiscale wavelet transform and mechanisms of directed attention. The developed technique is based on the decomposition of input images into low-frequency and high-frequency components, followed by adaptive fusion of informative features at various levels of decomposition. Empirical verification of the proposed method was carried out on an extensive data set, including images with different lighting conditions, occlusions and noise distortions. The experimental results demonstrate that the developed approach surpasses modern data fusion methods in key metrics, including object recognition accuracy (increased by 8.7%), noise tolerance (improved by 12.3%), and computational efficiency (reduced resource requirements by 23.5%). The proposed method provides a significant increase in the performance of robotic systems in complex dynamic environments, which opens up new prospects for autonomous navigation, object manipulation, and human-machine interaction.
Keywords
References
Ball J.E. emerging trends in autonomous vehicle perception: multimodal fusion for 3d object detection // World electric vehicle journal. 2024. № 15(1). Р. 20.
Chen L., Han J. Infrared and visible image fusion using salient decomposition based on a generative adversarial network // Applied optics. 2021. № 60. рр. 7017-7026.
Gong C., Peng R. A novel hierarchical vision transformer and wavelet time-frequency based on multi-source information fusion for intelligent fault diagnosis // Sensors. 2024. № 24(6). рр. 1799.
Kio A.E., Xu J., Gautam N., Ding Y. Wavelet decomposition and neural networks: a potent combination for short term wind speed and power forecasting // Frontiers in energy research. 2024. № 12. рр. 127-464.
Li H., Wu X.J. DenseFuse: A fusion approach to infrared and visible images // IEEE transactions on image processing. 2018. № 28(5). рр. 2614-2623.
Mohd T.K., Singh D. Multi-modal data fusion in enhancing human-machine interaction for robotic applications: A survey // arXiv preprint. 2022.
Pajares G., de la Cruz J.M. A wavelet-based image fusion tutorial // Pattern recognition. 2024. № 37(9). рр. 1855-1872.
Trigub M.V. WaveFusionNet: Infrared and visible image fusion based on multi-scale feature encoder-decoder and discrete wavelet decomposition // Optics communications. 2024. Vol. 573. pp. 8-131.
Xian C., Zhang J., Yang W. Multi-scale progressive fusion-based depth image completion and enhancement for industrial collaborative robot applications // Journal of intelligent manufacturing. 2024. Vol. 35. рр. 2119-2135.
Yan L., Han J. Generic wavelet‐based image decomposition and reconstruction framework for multi‐modal data analysis in smart camera applications // IET Computer Vision. 2020. № 14(7). рр. 471-479.
Yang Y., Cao R., Wang H., Fu M., Wu S. Infrared and visible image fusion based on multi-level detail enhancement and generative adversarial network // Intelligent robotics. 2024. 4(4), 524-543.
Zhang W., Liu X., Wang W., Zeng Y. Multi-exposure image fusion based on wavelet transform // International journal of advanced robotic systems. 2018. № 15(2).
Zhang Y., Liu Y., Sun P., Yan H., Zhao X., Zhang L. IFCNN: A general image fusion framework based on convolutional neural network // Information fusion. 2020. Vol. 54. рр. 99-118.
Zhang Y., Tu C., Gao K. Multisensor information fusion: Future of environmental perception in intelligent vehicles // Journal of intelligent and connected vehicles. 2024. № 7(3). рр. 163-176.
Zhao J., Wen X., He Y., Yang X., Song K. Wavelet-driven multi-band feature fusion for RGB-T salient object detection // Sensors. 2024. № 24(24). рр. 8159.