CableSAM: an efficient automatic segmentation method for aircraft cabin cables

Abstract

Cabin cables, as critical components of an aircraft’s electrical system, significantly impact the operational efficiency and safety of the aircraft. The existing cable segmentation methods in civil aviation cabins are limited, especially in automation, heavily dependent on large amounts of data and resources, lacking the flexibility to adapt to different scenarios. To address these challenges, this paper introduces a novel image segmentation model, CableSAM, specifically designed for automated segmentation of cabin cables. CableSAM improves segmentation efficiency and accuracy using knowledge distillation and employs a context ensemble strategy. It accurately segments cables in various scenarios with minimal input prompts. Comparative experiments on three cable datasets demonstrate that CableSAM surpasses other advanced cable segmentation methods in performance.

References

[1] Zhang C, Tian Y, Zhang J. Complex image background segmentation for cable force estimation of urban bridges with drone-captured video and deep learning. Structural control and health monitoring, 2022, 29(4): e2910 J]

[2] Caporali A, Zanella R, De Greogrio D, et al.. Ariadne+: deep learning-based augmented framework for the instance segmentation of wires. IEEE transactions on industrial informatics, 2022, 18(12): 8607-8617 J]

[3] Caporali A, Galassi K, Zanella R, et al.. FASTDLO: fast deformable linear objects instance segmentation. IEEE robotics and automation letters, 2022, 7(4): 9075-9082 J]

[4] Luo X, Zeng W, Chen Y, et al.. SOLOv2-cable: a power cable segmentation algorithm in complex scenarios. 2022 3rd International Conference on Computer Vision, Image and Deep Learning & International Conference on Computer Engineering and Applications (CVIDL & ICCEA), 2022, New York, IEEE 1156-1161 C]

[5] Kirillov A, Mintun E, Ravi N, et al.. Segment anything. Proceedings of the IEEE/CVF International Conference on Computer Vision, October, 2023, Paris, France, 2023, New York, IEEE 4015-4026 [C]

[6] ZHANG C, HAN D, QIAO Y, et al. Faster segment anything: towards lightweight SAM for mobile applications[EB/OL]. (2023-06-25) [2023-12-26]. https://arxiv.org/abs/2306.14289.

[7] WANG X, ZHANG X, CAO Y, et al. SegGPT: segmenting everything in context[EB/OL]. (2023-06-06) [2023-12-26]. https://arxiv.org/abs/2304.03284.

[8] Zhang J, Zhang J, Chen S. Discover novel visual categories from dynamic hierarchies using multimodal attributes. IEEE transactions on industrial informatics, 2013, 9(3): 1688-1696 J]

[9] Zhang J, Liu R, Yin K, et al.. Intelligent collaborative localization among air-ground robots for industrial environment perception. IEEE transactions on industrial electronics, 2018, 66(12): 9673-9681 J]

[10] Xie Z, Zhang J, Wang P. Event-based stereo matching using semiglobal matching. International journal of advanced robotic systems, 2018, 15(1): 1729881417752759 J]

[11] Qian J, Chen K, Chen Q, et al.. Robust visual-lidar simultaneous localization and mapping system for UAV. IEEE geoscience and remote sensing letters, 2021, 19: 1-5 J]

[12] Zhang J, Liu J, Chen K, et al.. Map recovery and fusion for collaborative augment reality of multiple mobile devices. IEEE transactions on industrial informatics, 2020, 17(3): 2081-2089 J]

[13] Zhang J, Gui M, Wang Q, et al.. Hierarchical topic model based object association for semantic SLAM. IEEE transactions on visualization and computer graphics, 2019, 25(11): 3052-3062 J]

[14] Zhang J, Chen J, Wang Q, et al.. Spatiotemporal saliency detection based on maximum consistency super-pixels merging for video analysis. IEEE transactions on industrial informatics, 2019, 16(1): 606-614 J]

[15] Zanella R, Caporali A, Tadaka K, et al.. Au-to-generated wires dataset for semantic segmentation with domain-independence. 2021 International Conference on Computer, Control and Robotics (ICCCR), January 8–10, 2021, Shanghai, China, 2021, New York, IEEE 292-298 [C]

RIGHTS & PERMISSIONS

Tianjin University of Technology