Small Object Geological Carbonate Detection Algorithm Based on YOLOX
DOI:
https://doi.org/10.54691/s20g7149Keywords:
Carbonate detection; small objects; attention mechanism.Abstract
Detection of small object Carbonates poses a challenging task, primarily due to the minuscule nature of Carbonates making thcem difficult to distinguish from the background. Traditional methods often struggle when faced with these small Carbonates, as their scale is small and they exhibit minimal differences from the background, resulting in challenges in accurate detection and classification. To address this issue, this study proposes an Geological small object Carbonate detection algorithm based on spatial attention combined with self-attention mechanisms. This algorithm first utilizes spatial attention to assist the model in focusing on the regions of interest containing small object Carbonates, thereby reducing background interference and increasing attention towards small object Carbonates. Subsequently, the self-attention mechanism is employed to capture long-range dependencies across the entire image, aiding in understanding the relationship between Carbonate regions and the background, thus facilitating better differentiation between Carbonates and background. Finally, the proposed algorithm is evaluated on the public small object dataset TT-100k and the Geological Carbonate dataset NEU, respectively. Experimental results demonstrate that compared to the baseline model, the proposed algorithm achieves an improvement of 2.4% in small object average precision (APsmall) and 3.2% in overall average precision (AP0.5) at IoU=0.5 on the TT-100k dataset; and an improvement of 1.5% in APsmall and 1.8% in AP0.5 on the NEU dataset.
Downloads
References
[1] Hou R, Chen G, Han Y, et al. Multi-modal feature fusion for 3D object detection in the production workshop[J]. Applied Soft Computing, 2022, 115: 108245.
[2] Zhang P. Rapid detection method of workshop staff based on deep learning[C]//2021 2nd International Conference on Computer Science and Management Technology (ICCSMT). IEEE, 2021: 243-248.
[3] Łysakowski M, Żywanowski K, Banaszczyk A, et al. Using AR and YOLOv8-Based Object Detection to Support Real-World Visual Search in Geological Workshop: Lessons Learned from a Pilot Study[C]//2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). IEEE, 2023: 154-158.
[4] Ramachandran S, Sistu G, Kumar V R, et al. Woodscape Fisheye Object Detection for Autonomous Driving--CVPR 2022 OmniCV Workshop Challenge[J]. arXiv preprint arXiv:2206.12912, 2022.
[5] Liang Z, Hu Y, Yang R. Research on Geological Human Action Recognition based on improved slowFast[C]//2023 6th International Conference on Intelligent Autonomous Systems (ICoIAS). IEEE, 2023: 94-99.
[6] Wang Z, Yan J. Multi-sensor fusion based Geological action recognition method under the environment of intelligent manufacturing[J]. Journal of Manufacturing Systems, 2024, 74: 575-586.
[7] Wu L, Ma X G. Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Geological Assembly Lines[J]. arXiv preprint arXiv:2403.09056, 2024.
[8] Sturm F, Sathiyababu R, Hergenroether E, et al. Semi-Supervised Learning Approach for Fine Grained Human Hand Action Recognition in Geological Assembly[J]. 2023.
[9] Juanjuan Z, Xiaohan H, Zebang Q, et al. Small Object Detection Algorithm Combining Coordinate Attention Mechanism and P2-BiFPN Structure[C]//International Conference on Computer Engineering and Networks. Singapore: Springer Nature Singapore, 2023: 268-277.
[10] Qingyong Y, Chenchen H, Likun C, et al. CLAHR: Cascaded Label Assignment Head for High-Resolution Small Object Detection[J]. IEEE Access, 2024.
[11] Chen J, Wang X. Dense small object detection algorithm based on improved YOLO5 in UAV aerial images[J]. Comput. Eng. Appl.,(3), 2023: 100-108.
[12] Sun S, Mo B, Xu J, et al. Multi-YOLOv8: An Infrared Moving Small Object Detection Model Based on YOLOv8 for Air Vehicle[J]. Neurocomputing, 2024: 127685.
[13] Sun Z, Hua Z, Li H, et al. Flying Bird Object Detection Algorithm in Surveillance Video[J]. arXiv preprint arXiv:2401.03749, 2024.
[14] Zhou H, Lin Y, Yang L, et al. Benchmarking deep models on salient object detection[J]. Pattern Recognition, 2024, 145: 109951.
[15] Liu Z, Wang B, Li Y, et al. UnitModule: A lightweight joint image enhancement module for underwater object detection[J]. Pattern Recognition, 2024, 151: 110435.
[16] Yuan J, Xiao L, Wattanachote K, et al. FGNet: Fixation guidance network for salient object detection[J]. Neural Computing and Applications, 2024, 36(2): 569-584.
[17] Feng C, Wang C, Zhang D, et al. Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer[J]. Computers, Materials & Continua, 2024, 78(3).
[18] Huo D, Kastner M A, Liu T, et al. Small object detection for birds with Swin transformer[C]//2023 18th International Conference on Machine Vision and Applications (MVA). IEEE, 2023: 1-5.
[19] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10012-10022.
[20] Xu S, Zheng S C, Xu W, et al. HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection[J]. arXiv preprint arXiv:2403.10778, 2024.
[21] Liang J, Ai J. Improving Accuracy of Small Object Detection in Screen based on YOLOv7[C]//2023 10th International Conference on Dependable Systems and Their Applications (DSA). IEEE, 2023: 851-859.
[22] Chai E, Chen L, Hao X, et al. Mitigate the scale imbalance via multi-scale information interaction in small object detection[J]. Neural Computing and Applications, 2024, 36(4): 1699-1712.
[23] Zhou H P, Zhang J, Sun K L, et al. Small Object Detection in Remote Sensing Based on Contextual Information and Attention[J]. Journal of Computers, 2024, 35(1): 145-157.
[24] Jing R, Zhang W, Liu Y, et al. An effective method for small object detection in low-resolution images[J]. Engineering Applications of Artificial Intelligence, 2024, 127: 107206.
[25] Ma S, Lu H, Liu J, et al. LAYN: Lightweight Multi-Scale Attention YOLOv8 Network for Small Object Detection[J]. IEEE Access, 2024.
[26] Yue X, Zhong G, Chu B. A multi-attention fusion mechanism for collaborative Geological surface Carbonate detection[C]//Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022). SPIE, 2023, 12705: 209-218.
[27] Wang C, Wei X, Jiang X. An automated Carbonate detection method for optimizing Geological quality inspection[J]. Engineering Applications of Artificial Intelligence, 2024, 127: 107387.
[28] Li G, Shao R, Wan H, et al. A model for surface Carbonate detection of Geological products based on attention augmentation[J]. Computational Intelligence and Neuroscience, 2022, 2022.
[29] Li X, Li L, Wang P, et al. You only train twice: A lighter and faster method for Geological weld Carbonate detection based on dynamic kernel network[J]. Measurement, 2024, 231: 114642.
[30] Hu B, Zhou D, Wu Q, et al. An Improved Carbonate Detection Algorithm for Geological Products via Lightweight Convolutional Neural Network[C]//Proceedings of the 6th International Conference on Advances in Image Processing. 2022: 13-19.
[31] Zhou X, Xu X, Liang W, et al. Intelligent small object detection for digital twin in smart manufacturing with Geological cyber-physical systems[J]. IEEE Transactions on Geological Informatics, 2021, 18(2): 1377-1386.
[32] Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.
[33] Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:2004.10934, 2020.
[34] Cao Z, Simon T, Wei S E, et al. Realtime multi-person 2d pose estimation using part affinity fields[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7291-7299.
[35] Yi F, Zhang H, Yang J, et al. YOLOv7-SiamFF: Geological Carbonate detection algorithm based on improved YOLOv7[J]. Computers and Electrical Engineering, 2024, 114: 109090.
[36] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023: 7464-7475.
[37] Wan Y, Yi L, Jiang B, et al. AENet: attention enhancement network for Geological Carbonate detection in complex and sensitive scenarios[J]. The Journal of Supercomputing, 2024: 1-24.
[38] Ge Z, Liu S, Wang F, et al. Yolox: Exceeding yolo series in 2021[J]. arXiv preprint arXiv:2107.08430, 2021.
[39] Zhu Z, Liang D, Zhang S, et al. Traffic-sign detection and classification in the wild[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2110-2118.
[40] Bao Y, Song K, Liu J, et al. Triplet-graph reasoning network for few-shot metal generic surface Carbonate segmentation[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-11.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Science and Engineering
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
