基于高光谱成像的烟火药快速可视化识别方法

doi:10.3964/j.issn.1000-0593(2025)08-2183-07

Abstract
References
Related Citation (15)

Download: PDF (14430 KB)
Export: BibTeX | EndNote (RIS)

Abstract In the explosive scene investigation, the rapid detection and accurate identification of fireworks and explosives play a vital role in preventing, controlling, and rapidly disposing of major explosions. However, the current rapid detection methods for fireworks and explosives mostly have problems such as low recognition speed and difficulty in visualization. Because of this, this paper proposes a method based on hyperspectral imaging technology combined with one-class support vector machine (OCSVM) for rapid detection and recognition of fireworks. Firstly, the hyperspectral data of the sample in the 400~720 nm band were collected with a hyperspectral camera. Principal component analysis (PCA) was used to reduce the dimension of the data, multiplicative scattering correction (MSc) was used to eliminate the baseline offset caused by particle scattering on the sample surface, and Savitzky-Golay (SG) was used to smooth the high-frequency noise and improve the spectral signal-to-noise ratio. Secondly, to reduce the complexity of the model and improve the efficiency, the representative pyrotechnic samples were selected from the spectral data by Kennard stone (K-S) method as the data set, which was divided into the training set and the test set at the ratio of 4∶1. On this basis, the OCSVM model was established. Thirdly, to verify the recognition ability of the model to the pyrotechnic composition, the isolated forest (iforest) and self-encoder (AE) models were established using the same training set, and the recognition ability of the three models to the pyrotechnic composition was compared. Finally, the recognition result is mapped to the RGB image of the test material, and the recognition image is obtained by marking the target pixels with the operation of the mask to realize the visual recognition effect of the pyrotechnic composition. The results show that the overall accuracy of the OCSVM method is higher than 0.95, the F1 score and AUC value are more than 0.8, and the recognition time is less than 2 seconds. The performance of OCSVM in classification accuracy, running speed, F1 score, and AUC is better than that of the isolated forest and self-encoder models. In terms of visual recognition, the recognition image based on the OCSVM model after mapping and mask operation can more accurately reflect the distribution of smoke and powder in all samples. At the same time, the recognition image based on an isolated forest and a self-encoder model can not well reflect the distribution of smoke and powder on yellow paper and black polyester cloth. The research shows that the pyrotechnic identification method based on hyperspectral imaging combined with OCSVM proposed in this paper has the characteristics of high recognition accuracy, fast response speed, and strong generalization ability, and can quickly, accurately, and nondestructively identify pyrotechnics in the test material. Its recognition accuracy, recognition speed-, and visualization effect can be well applied to the rapid discovery and on-site detection of pyrotechnic and explosive at the explosion scene, and provide an effective method for searching for pyrotechnic and explosive in the scene investigation.

Key words：Hyperspectral imaging technology; Single class support vector machine; Pyrotechnic composition; Visual recognition

Received: 2025-03-01 Accepted: 2025-04-15

ZTFLH:

O433.4

Cite this article:

LI Yun-peng,WANG Hong-wei,DAI Xue-jing, et al. Fast Visual Identification Method of Pyrotechnic Composition Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(08): 2183-2189.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)08-2183-07 OR https://www.gpxygpfx.com/EN/Y2025/V45/I08/2183

[1] LI Xing, SUN Zhen-wen, LIU Yao(李兴, 孙振文, 刘耀). Chemical Research and Application(化学研究与应用), 2022, 34(10): 2265.
[2] GU Tian-yu, ZHANG Da-cheng, FENG Zhong-qi, et al(谷天予, 张大成, 冯中琦, 等). Modern Applied Physics(现代应用物理), 2023, 14(2): 106.
[3] Zapata F, García-Ruiz C. Forensic Science International, 2017, 275: 57.
[4] HUANG Yang, ZHU Jun, HU Can, et al(黄阳, 朱军, 胡灿, 等). Physical Testing and Chemical Analysis Part B: Chemical Analysis[理化检验(化学分册)], 2023, 59(4): 489.
[5] SUN Wei, CHEN Rui-li, LUO Jian-xin(孙威, 陈蕊丽, 骆建新). Laser & Optoelectronics Progress(激光与光电子学进展), 2021, 58(6): 84.
[6] de Carvolho M A, Talhavini M, Pimertel M F, et al. Analytical Methods, 2018, 10(38): 4711.
[7] Ortega-Ojeda F E, Torre-Roldán M, García-Ruiz C. Talanta, 2017, 167: 227.
[8] Glomb P, Romaszewski M, Cholewa M, et al. Forensic Science International, 2018, 290: 227.
[9] El-Sharkawy Y H, Elbasuney S. Remote Sensing Applications: Society and Environment, 2019, 13: 31.
[10] Christoph G, Michael G, Johannes O, et al. Analytical Chemistry, 2019, 91(12): 7712.
[11] Kendziora C A, Furstenberg R, Breshike C J, et al. Proceedings of SPIE, 2021, 11727: 117270R (https://doi.org/10.1117/12.2585982).
[12] Guo W, Li X, Xie T. Aquaculture, 2021, 538: 736512.
[13] Ma L, Zhang Y, Zhang Y Y, et al. Agronomy, 2022, 12(12): 3223.
[14] ZHU Rong-guang, DUAN Hong-wei, WANG Long, et al(朱荣光, 段宏伟, 王龙, 等). Food and Fermentation Industries(食品与发酵工业）, 2016, 42(4): 189.
[15] DENG Yun, WANG Jun, CHEN Shou-xue, et al(邓昀, 王君, 陈守学, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2025, 45(2): 569.
[16] WANG Sheng-li, ZHANG Lian-peng, ZHU Shou-hong, et al(王胜利, 张连蓬, 朱寿红, 等). Bulletin of Surveying and Mapping(测绘通报), 2018, (11): 46.
[17] Yuan S R, Shi L, Yao B, et al. Remote Sensing, 2022, 14(20): 5191.
[18] Chen X, Cui Y, Gao S, et al. Infrared Physics and Technology, 2025, 145: 105704.
[19] Kingma D P, Welling M. Foundations and Trends^D○R in Machine Learning 2019, 12(4): 307.