光谱探测技术在无人机感知领域具有重要应用价值，其多维信息获取能力显著提升了目标识别精度与环境适应性。然而传统高光谱成像系统采用固定波段采集模式，存在硬件复杂、效率低、数据冗余等问题，难以满足无人机快速低成本目标探测需求。针对上述挑战，本文提出一种光谱波段自适应成像探测算法，支持动态调整光谱参数，设计结构简化的光学成像系统。首先，建立基于信息量与目标可分离度的光谱成像质量评价体系，量化分析窄带光谱数据的识别贡献；其次，提出基于最小切换时间间隔和最大切换谱段范围约束的光谱自适应模型，实现目标特征可辨识度与数据维度压缩的优化平衡；最后，结合阵列式光学模组给出一体化成像探测系统结构设计。实验验证了所提方法的有效性，为无人机光谱感知提供一条全新的高效解决方案。
Spectral detection technology holds significant application value in the field of UAV perception, where its multi-dimensional information acquisition capability substantially enhances target recognition accuracy and environmental adaptability. However, conventional hyperspectral imaging systems, relying on fixed-band acquisition modes, suffer from complex hardware architec-tures, low efficiency, and high data redundancy, thereby failing to meet the demand for rapid and low-cost target detection in UAV platforms. To address these challenges, this paper proposes an adaptive spectral band imaging and detection algorithm, enabling dynamic adjustment of spectral parameters and the design of structurally simplified optical imaging systems. First, a spectral imaging quality evaluation framework based on information entropy and target separability is established to quantitative-ly assess the recognition contributions of narrow-band spectral data. Second, a spectral adaptive model incorporating constraints of minimum switching time intervals and maximum spectral switching ranges is developed, achieving an optimal balance be-tween target feature discriminability and data dimensionality reduction. Finally, an integrated imaging and detection system structure is designed using array-based optical modules. Experimental results validate the effectiveness of the proposed method, offering a novel and efficient solution for UAV-based spectral perception.
[1]SONG M P, SHANG X D, WANG Y L, et al.Class information-based band selection for hyperspectral im-age classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11):8394-8416
[2]RAM B G, ODUOR P, IGATHINATHANE C, et al.A systematic review of hyperspectral imaging in precision agriculture: Analysis of its current state and future prospects[J].Computers and Electronics in Agriculture, 2024, 222:109037-
[3]张艺伟, 郭焱培, 唐荣, 等.高光谱遥感在植物多样性研究中的应用进展与趋势[J].遥感学报, 2023, 27(11):2467-2483
[4]ZHANG Y W, GUO Y P, TANG R, et al.Progress and trends of application of hyperspectral remote sensing in plant diversity research[J].National Remote Sensing Bulletin, 2023, 27(11):2467-2483
[5]WANG Y, MEI S H, MA M Y, et al.HTACPE: A Hybrid Transformer with Adaptive Content and Position Embedding for Sample Learning Efficiency of Hyperspectral Tracker[J].IEEE Transactions on Multimedia, 2025, :-
[6]熊振宇, 崔亚奇, 董凯, 等.基于属性引导的多源遥感舰船目标可解释融合关联网络[J].航空学报, 2023, 44(22):7-19
[7]XIONG Z Y, CUI Y Q, DONG K, et al.Interpretable fusion association network for multi-source remote sensing ship target based on attribute guidance[J].Acta Aeronautica et Astronautica Sinica, 2023, 44(22):7-19
[8]SHANG X D, SONG M P, WANG Y L, et al.Target-constrained interference-minimized band selection for hyperspectral target detection[J].IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(7):6044-6064
[9]FARRELL M.D and MERSEREAU R MOn the im-pact of PCA dimension reduction for hyperspectral de-tection of difficult targets[J].IEEE Geoscience and Remote Sensing Letters, 2005, 2(2):192-195
[10]LI W, PRASAD S, FOWLER J E, et al.Locality-preserving dimensionality reduction and classification for hyperspectral image analysis[J].IEEE Transactions on Geoscience and Remote Sensing, 2011, 50(4):1185-1198
[11]FALCO N, BENEDIKTSSON J A and BRUZZONE L.A study on the effectiveness of different independent component analysis algorithms for hyperspectral image classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2183-2199
[12]MA M Y, MEI S H, LI F, et al.Spectral correlation-based diverse band selection for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2023, 61:1-13
[13]XU B, LI X, HOU W, WANG Y, et al.A similarity-based ranking method for hyperspectral band selec-tion[J].IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(11):9585-9599
[14]WU M, OU X F, LU Y L, et al.Heterogeneous cuckoo search-based unsupervised band selection for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing, 2024, 62:1-16
[15]王宇轩, 孙晓兵, 提汝芳, 等.考虑局部密度的共享近邻高光谱图像波段选择方法[J].光学学报, 2024, 44(24):2428010-
[16]WANG Y X, SUN X B, TI R F, et al.Method of shared nearest neighbors in hyperspectral image band selection considering local density[J].Acta Optica Sinica, 2024, 44(24):2428010-
[17]XU Y B, LU L Y, SARAGADAM V et al.A compres-sive hyperspectral video imaging system using a single-pixel detector[J].Nature Communications, 2024, 15(1):1456-
[18]ZHANG X Y, CHEN B, ZOU W Z, et al.Progressive content-aware coded hyperspectral snapshot compres-sive imaging[J].IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(11):10817-10830
[19]HARTLEY R V.Transmission of information[J].The Bell System technical journal, 1965, 7(3):535-563
[20]ULABY F T, KOUYATE F, BRISCO B, et al.Textural information in SAR images[J].IEEE Transactions on Geoscience and Remote Sensing, 1986, (2):235-245
[21]VITERBI A.Error bounds for convolutional codes and an asymptotically optimum decoding algorithm[J].IEEE Transactions on Information Theory, 1967, 13(2):260-269
[22]CHEN L L, ZHAO Y Q, CHAN J C, et al.Histograms of oriented mosaic gradients for snapshot spectral image description[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 183:79-93
[23]KHANAM R and HUSSAIN M. Yolov11: An overview of the key architectural enhancements[DB/OL]. arXiv prepr.[J].rXiv:2410.17725, 2024., int,, :-
[24]FALCO N, BENEDIKTSSON J A and BRUZZONE L.A Study on the Effectiveness of Different Independent Component Analysis Algorithms for Hyperspectral Im-age Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2183-2199
[25]HE C L, ZHANG Y, GONG D W et al.A multitask bee colony band selection algorithm with variable-size clustering for hyperspectral images[J].IEEE Transac-tions on Evolutionary Computation, 2022, 26(6):1566-1580
[26]WANG Q, ZHANG F H, LI X L.Optimal clustering framework for hyperspectral band selection[J].IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(10):5910-5922
CJA