Rapid and accurate identification of coal and gangue is essential for improving coal-resource utilization and reducing environmental pollution. Multispectral imaging has been widely used for coal-gangue sorting because of its abundant spectral information. However, unstable illumination and target clutter in workshop environments often limit detection accuracy and robustness. To address these challenges, a lightweight multispectral coal-gangue detection model was proposed for workshop environments, termed learnable dynamic activation-hierarchical context fusion-inner-MPDIoU YOLO (LHIM-YOLO). First, a lightweight learnable dynamic activation module (LDAM) was designed to enhance the modeling of nonlinear differences among spectral bands. Second, a hierarchical context fusion feature pyramid network (HCFFPN) was constructed to efficiently integrate multiscale features and improve the representation of fine-grained textures and macroscopic structures. Finally, an auxiliary-box-constrained inner minimum point distance intersection over union (Inner-MPDIoU) loss was introduced to strengthen geometric constraints, including center-distance and containment relationships, thereby improving localization stability in complex scenes. Experimental results show that LHIM-YOLO achieves an mAP 0.5 of 74.69% with only 3.04×106 parameters. Compared with the benchmark models, it provides superior detection performance while maintaining high accuracy and real-time capability, demonstrating strong potential for practical engineering applications.
GAO Li-peng, ZHOU Meng-ran, BIAN Kai, WANG Qiao-long, TAO Ye, HE Xiao-ya.
Multispectral Coal Gangue Image Detection Method Based on LHIM-YOLO[J].
Science Technology and Engineering, 2026, 26(29): 12530-12541 DOI:10.12404/j.issn.1671-1815.2600596
HouYifan, XuTianqi, LiYan, et al. Data-driven transient stability assessment of power systems based on Transformer-GAT parallel feature fusion[J]. Science Technology and Engineering, 2025, 25(21): 8945-8954.
[3]
BPGlobal. BP energy outlook 2025 edition[R]. London: BP Global, 2025.
YangYuhao, GuoYongcun, LiDeyong. et al Segmentation and localization method of coal and gangue identification based on visual information[J]. Journal of Zhejiang University: Engineering Science, 2025, 59(7): 1421-1433.
[12]
PanY, WangD, MeiK, et al. Optimization modeling and mechanism discussion on specific industrial coal-washing wastewater treatment[J]. International Journal of Environmental Science and Technology, 2023, 20(10): 11195-11206.
[13]
ZhouW, WangH, WangL, et al. Research on separation mechanism of coal gangue photoelectric sorting recognition[J]. Physicochemical Problems of Mineral Processing, 2024, 60(4): 192417.
MaHongwei, ZhangYe, WangPeng, et al. On the academic ideology of “sorting the gangue is sorting the images”[J]. Coal Science and Technology, 2025, 53(5): 291-300.
[16]
YanP, WenZ, WuZ, et al. Intelligent detection of coal gangue in mining operations using multispectral imaging and enhanced RT-DETR algorithm for efficient sorting[J]. Microchemical Journal, 2024, 207: 111789.
[17]
HuF, ZhouM, YanP, et al. Multispectral imaging: a new solution for identification of coal and gangue[J]. IEEE Access, 2019, 7: 169697-169704.
LiRui, LiBo, WangXuewen, et al. A classification method of coal and gangue based on XGBoost and visible-near infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2022, 42(9): 2947-2955.
[20]
XuM, MaoY, YanZ, et al. Coal and gangue classification based on laser-induced breakdown spectroscopy and deep learning[J]. ACS Omega, 2023, 8(50): 47646-47657.
ZhaoShuanfeng, WangLi, LiXiaoyu, et al. Gangue detection methods by charge-coupled frequency response multispectral in version network[J]. Journal of Xi'an University of Science and Technology, 2025, 45(1): 117-128.
[23]
YanP, KanX, ZhangH, et al. Target recognition of coal and gangue based on improved YOLOv5s and spectral technology[J]. Sensors, 2023, 23(10): 4911.
[24]
HussainM. YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection[J]. Machines, 2023, 11(7): 677.
[25]
TianY J, YeQ X, DoermannD. YOLOv12: Attention-centric real-time object detectors[C]// 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2025: 12524.
CenWeidi, JiangJialing, HuangBo, et al. Ten years of YOLO evolution: from real-time detection pioneer to multi-tasking intelligence frontier[J]. Journal of Wuhan University (Natural Science Edition), 2026, 72(1): 5-20.
[28]
KhanamR, HussainM. A review of YOLOv12: attention-based enhancements vs. previous versions[J]. arXiv prePrint, arXiv: 2504. 11995, 2025.
[29]
ZhuJ, ChenX, HeK, et al. Transformers without normalization[C]// Proceedings of the Computer Vision and Pattern Recognition Conference. Nashville: IEEE, 2025: 14901-14911.
[30]
LiS, SongW, FangL, et al. Deep learning for hyperspectral image classification: an overview[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9): 6690-6709.
[31]
NiZ, ChenX, ZhaiY, et al. Context-guided spatial feature reconstruction for efficient semantic segmentation[C]// European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 239-255.
[32]
SiliangM, YongX. MPDIoU: a loss for efficient and accurate bounding box regression[J]. arXiv prePrint, arXiv: 2307. 07662, 2023.
[33]
ZhangH, XuC, ZhangS. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[J]. arXiv prePrint, arXiv: 2311. 02877, 2023.
[34]
RogersM, Blanc-TalonJ, UrschlerM, et al. Wavelength and texture feature selection for hyperspectral imaging: a systematic literature review[J]. Journal of Food Measurement and Characterization, 2023, 17(6): 6039-6064.
[35]
ZhangZ, WangD, SunX, et al. Spatial sampling and grouping information entropy strategy based on kernel fuzzy C-means clustering method for hyperspectral band selection[J]. Remote Sensing, 2022, 14(19): 5058.
[36]
MaX, WangJ, ZhouK, et al. Quantitative evaluation of the impact of band optimization methods on the accuracy of the hyperspectral metal element inversion models[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 132: 104011.
KhanamR, HussainM. YOLOv11: an overview of the key architectural enhancements[J]. arXiv prePrint, arXiv: 2410. 17725, 2024.
[39]
ZhaoY, LüW, XuS, et al. Detrs beat yolos on real-time object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 16965-16974.
[40]
SelvarajuR R, CogswellM, DasA, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International Journal of Computer Vision, 2020, 128(2): 336-359.