研究方向:圖像處理,、計算機視覺,、機器視覺
地址: 佛山市南海區(qū),,佛山大學(xué)仙溪校區(qū).
個人簡介
李小松,,云南大理人,,白族,博士,,副教授(計算機科學(xué)與技術(shù)),,碩導(dǎo)。2021年博士畢業(yè)于北京航空航天大學(xué),,同年6月入職佛山大學(xué),。長期從事圖像處理、計算機視覺,、多模態(tài)融合與感知、精密視覺測量等方面研究,。獲批主持國家自然科學(xué)基金–青年項目、廣東省區(qū)域聯(lián)合基金-地區(qū)培育項目,、廣東省自然科學(xué)基金–面上項目、廣東省教育廳特色創(chuàng)新項目,、以及佛山市重點領(lǐng)域攻關(guān)課題,;近三年來,以第一/通訊作者身份在IEEE-JBHI/TIM, ESWA, KBS, MICCAI, WACV,,ICASSP, ACCV等國際期刊及會議長文上發(fā)表論文30余篇,,以第一發(fā)明人身份申請發(fā)明專利40余件(已授權(quán)14件、公開實審20余件),,授權(quán)登記軟著16件; 兩篇第一作者論文單篇被引100+次,,受邀擔(dān)任IEEE-TPAMI/TIP/TNNLS/T-CSVT/TMM, IJCV, Information Fusion, Medical Image Analysis, ICLR, ICML, NIPS, CVPR, ICCV, ECCV, AAAI, ACM MM等30余個頂級國際期刊/會議審稿人。
教育背景
2016.09至2021.01,,北京航空航天大學(xué),,測試計量技術(shù)及儀器(A+學(xué)科),工學(xué)博士學(xué)位,,導(dǎo)師:周富強教授,;
2013.09至2016.07,昆明理工大學(xué),,模式識別與智能系統(tǒng),,工學(xué)碩士學(xué)位,導(dǎo)師:李華鋒教授,;
2009.09至2013.07,,長春大學(xué),測控技術(shù)與儀器,,工學(xué)學(xué)士學(xué)位,。
工作經(jīng)歷
2021.06至2024.06, 佛山大學(xué),,物理與光電工程學(xué)院,,講師、碩導(dǎo),、特聘青年研究員,;
2024.07至2024.10, 佛山大學(xué),,物理與光電工程學(xué)院,,副教授、碩導(dǎo),、特聘青年研究員,;
2024.11至今, 佛山大學(xué),,物理與光電工程學(xué)院,,副教授、碩導(dǎo),、年輕副院長,。
科研項目
[1] 基于智能圖像融合的大場景下弱小目標(biāo)檢測研究,國家自然科學(xué)基金–青年基金(No. 62201149),,2023.01–2025.12,,30萬,主持,,在研,;
[2] 強反光干擾陶瓷缺陷檢測關(guān)鍵技術(shù)研究,,廣東省區(qū)域聯(lián)合基金–地區(qū)培育項目(No. 2023A1515140077),2023.11–2026.10,,30萬,,主持,在研,;
[3] 基于注意力機制的真實場景多模態(tài)圖像融合研究,廣東省自然科學(xué)基金–面上項目(No. 2024A1515011880),,2024.01–2026.12,,15萬,主持,,在研,;
[4] 復(fù)雜場景多干擾圖像融合關(guān)鍵技術(shù)研究,廣東省教育廳特色創(chuàng)新項目(自然科學(xué)類) (No. 2023KTSCX127), 2023.10-2025.10, 6萬,,主持,,在研;
[5] 自檢測的智慧移動PCR方艙實驗室,,佛山市重點領(lǐng)域科技攻關(guān)項目(No. 2120001008558),,2021.07–2024.08,合作單位課題負責(zé)人,,15萬,,已完成;
[6] 基于稀疏表示和卷積神經(jīng)網(wǎng)絡(luò)的目標(biāo)檢測研究,,佛山大學(xué)高層次人才科研啟動項目(No. CGZ07001),,2022.01-2024.12,30萬,,主持,,在研;
[7] 基于雙球面鏡像視覺的炮管內(nèi)膛形貌三維測量技術(shù)研究,,國家自然科學(xué)基金–面上項目(No. 62271148),,2023.01–2026.12,56萬,,參與(排名3/14),,在研;
[8] 精密管道內(nèi)表面視覺檢測儀,,廣東省科技計劃(No. X200051UZ200),,2020.03~2024.02,580萬,,參與(排名4/35),,已完成。
部分已發(fā)表論文 (#表示通訊作者,論文代碼均已開源)
[1] Yuchan Jie(21級碩士), Xiaosong Li#(指導(dǎo)老師), Tianshu Tan, Lemiao Yang, Mingyi Wang, Multi-modality image fusion using fuzzy set theory and compensation dictionary learning [J]. Optics and Laser Technology. 181, 112001, 2025.
[2] Jingxue Huang(22級碩士), Tianshu Tan, Xiaosong Li#(指導(dǎo)老師), Tao Ye, Yanxiong Wu. Multiple Attention Channels Aggregated Network for Multimodal Medical Image Fusion [J]. Medical Physics. Accept, In press.
[3] Jingxue Huang(22級碩士), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Xiaoqi Cheng. Generative adversarial network for tri-modal medical image fusion using primitive relationship reasoning [J]. IEEE Journal of Biomedical and Health Informatics. Volume: 28, Issue: 10, October 2024.
[4] Yuchan Jie (21級碩士), Xiaosong Li#(指導(dǎo)老師), Mingyi Wang, Fuqiang Zhou, Haishu Tan. Medical image fusion based on extended difference-of-Gaussians and edge-preserving [J], Expert Systems with Applications. 227, 120301, 2023.
[5] Yuchan Jie(21級碩士), Xiaosong Li#(指導(dǎo)老師), Fuqiang Zhou, Tao Ye. Tri-modal medical image fusion and denoising based on bitonicX filtering [J]. IEEE Transactions on Instrumentation and Measurement. 72. 5030815, 2023.
[6] Xiaosong Li, Fuqiang Zhou, Haishu Tan, Wanning Zhang, Congyang Zhao. Multimodal medical image fusion based on joint bilateral filter and local gradient energy [J]. Information Sciences, 569, 302-325, 2021. (被引100+次)
[7] Xiaosong Li, Fuqiang Zhou, Haishu Tan. Joint image fusion and denoising via three-layer decomposition and sparse representation [J]. Knowledge-based systems, 224, 107087, 2021. (被引100+次)
[8] Xiaosong Li, Fuqiang Zhou, Haishu Tan, Yuanze Chen, Wangxia Zuo. Multi-focus image fusion based on nonsubsampled contourlet transform and residual removal [J]. Signal processing. 184, 108062, 2021.
[9] Yushen Xu(23級碩士), Xiaosong Li#(指導(dǎo)老師), Yuchan Jie, Haishu Tan. Simultaneous Tri-Modal Medical Image Fusion and Super-Resolution using Conditional Diffusion Model [C]. Medical Image Computing and Computer Assisted Intervention (MICCAI), Marrakesh, Morocco, 6-10, 2024, Oct. arXiv:2404.17357. 2024. (入選2024年CSIG青年科學(xué)家會議墻報展示)
[10] Xilai Li(21級本科), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Jinyang Li. SAMF: Small-area-aware multi-focus image fusion for object detection [C]. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, 14~19 April 2024. (Oral)
[11] Xilai Li(21級本科), Xiaosong Li#(指導(dǎo)老師), Tao Ye, Xiaoqi Cheng, Wuyang Liu, Haishu Tan, Bridging the gap between multi-focus and multi-modal: a focused integration framework for multi-modal image fusion [C]. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, Jan. 4-8, 2024, United States of America, 2024. (入選2023年CSIG青年科學(xué)家會議墻報展示)
[12] Huichu Liu(23級碩士), Xiaosong Li#(指導(dǎo)老師), Tianshu Tan, Interaction-Guided Two-Branch Image Dehazing Network [C]. 17th Asian Conference on Computer Vision (ACCV), Hanoi, Vietnam, 8-12 Dec. 2024.
[13] Jingxue Huang(22級碩士), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Lemiao Yang, Gao Wang, Peng Yi. DeDNet: Infrared and visible image fusion with noise removal by decomposition-driven network [J]. Measurement. Available online 9 June 2024, . 2024.
[14] Jiangwei Li(21級碩士), Xilai Li, Xiaosong Li#(指導(dǎo)老師), Dingan Han. Multi-focus image fusion based on multiscale fuzzy quality assessment [J]. Digital Signal Processing, Volume 153, 104592, 2024.
[15] Wuyang Liu(22級碩士), Haishu Tan, Xiaoqi Cheng, Xiaosong Li#(指導(dǎo)老師), ESFuse: Weak Edge Structure Perception Network for Infrared and Visible Image Fusion[J]. Electronics, , 2024.
[16] Jingxue Huang(22級碩士), Xilai Li, Tianshu Tan, Xiaosong Li#(指導(dǎo)老師), Tao Ye. MMA-UNet: A Multi-Modal Asymmetric UNet Architecture for Infrared and Visible Image Fusion, arXiv preprint, arXiv: 2404.17747. 2024.
[17] Xilai Li(21級本科), Wuyang Liu, Xiaosong Li#(指導(dǎo)老師), Jinyang Li, Haishu Tan. Physical perception network and an all-weather multi-modality benchmark for adverse weather image fusion, arXiv preprint arXiv:2402.02090, 2024.
[18] Yuchan Jie(21級碩士), Yushen Xu, Xiaosong Li#(指導(dǎo)老師), Haishu Tan. TSJNet: A multi-modality target and semantic awareness joint-driven image fusion network, arXiv preprint arXiv:2402.01212, 2024.
[19] Xilai Li(21級本科), Xiaosong Li#(指導(dǎo)老師), Haishu Tan. Decomposition-based and interference perception for infrared and visible image fusion in complex scenes, arXiv preprint arXiv:2402.02096, 2024.
[20] Xilai Li (21級本科), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Xiaoqi Cheng, Fuqiang Zhou. MCDFD: Multifocus Image Fusion Based on Multiscale Cross-Difference and Focus Detection [J]. IEEE Sensors Journal. 23, 24, 2023.
[21] Yuchan Jie (21級碩士), Yong Chen, Xiaosong Li#(指導(dǎo)老師), Peng Yi, Haishu Tan, Xiaoqi Cheng. FUFusion: fuzzy sets theory for infrared and visible image fusion [C]. The 6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Xiamen, China, October 13-15, 2023.
[22] Jingxue Huang (22級碩士), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Xiaoqi Cheng. Multimodal medical image fusion based on multichannel aggregated network [C]. The 12th International Conference on Image and Graphics (ICIG), Nanjing, China. September 22–24, 2023.
[23] Xiaosong Li, Weijun Wan, Fuqiang Zhou, Xiaoqi Cheng, Yuchan Jie, Haishu Tan. Medical image fusion based on sparse representation and neighbor energy activity [J]. Biomedical Signal Processing and Control, 80, 104353, 2023.
[24] Xilai Li(21級本科), Haishu Tan, Fuqiang Zhou, Gao Wang, Xiaosong Li#(指導(dǎo)老師). Infrared and visible image fusion based on domain transform filtering and sparse representation [J]. Infrared Physics and Technology. 131, 104701, 2023.
[25] Xilai Li (21級本科), Xiaosong Li#(指導(dǎo)老師), Wuyang Liu. CBFM: contrast balance infrared and visible image fusion based on contrast-preserving guided filter [J]. Remote Sensing, 15, 2969, 2023.
[26] Yuchan Jie (21級碩士), Xiaosong Li#(指導(dǎo)老師), Haishu Tan, Fuqiang Zhou, Gao Wang. Multi-modal medical image fusion via multi-dictionary and truncated huber filtering [J]. Biomedical Signal Processing and Control. Volume 88, Part B, February 2024, 105671. 2023.
[27] Xilai Li (21級本科), Xiaosong Li#(指導(dǎo)老師). Multimodal brain image fusion based on error texture elimination and salient feature detection [J]. Frontiers in Neuroscience, 17:1204263, 2023.
[28] Yuchan Jie(21級碩士), Xiaosong Li#(指導(dǎo)老師), Mingyi Wang, Haishu Tan. Multi-focus image fusion for full-field optical angiography [J]. Entropy, 25, 951, 2023.
[29] Jiangwei Li(21級碩士), Dingan Han, Xiaopan Wang, Peng Yi, Liang Yan, Xiaosong Li#(指導(dǎo)老師). Multi-Sensor Medical-Image Fusion Technique Based on Embedding Bilateral Filter in Least Squares and Salient Detection [J]. Sensors, 23(7), 3490, pp: 1-20, 2023.
[30] Yuchan Jie (21級碩士), Fuqiang Zhou, Haishu Tan, Gao Wang, Xiaoqi Cheng, Xiaosong Li#(指導(dǎo)老師). Tri-modal medical image fusion based on adaptive energy choosing scheme and sparse representation [J]. Measurement, 204(30), 112038, 2022.
[31] Xilai Li (21級本科), Xiaopan Wang, Xiaoqi Cheng, Haishu Tan, Xiaosong Li#(指導(dǎo)老師). Multi-focus image fusion based on hessian matrix decomposition and salient difference focus detection [J]. Entropy, 24, 1527, 2022.
[32] Lemiao Yang, Fuqiang Zhou, Xiaosong Li, Wanning Zhang, Yang Liu, Haishu Tan. 3-D Vision Measurement System and Method for Small-Diameter Pipeline [J]. IEEE Transactions on Instrumentation and Measurement, dio: 10.1109/TIM.2024.3470955, in press, 2024.
[33] Tao Ye, Xiao Cong, Yuliang Li, Zhikang Zheng, Xiangpeng Deng, Xiangming Yan, Xiaosong Li, Xi Zhang. Few-Shot Railway Intrusion Detection Without Forgetting via Double RPN and Detector [J], IEEE Transactions on Intelligent Vehicles, doi: 10.1109/TIV.2024.3372776,2024.
[34] Tao Ye, Zhikang Zheng, Xiaosong Li, Zongyang Zhao, Xiao-Zhi Gao. An Efficient Few-Shot Object Detection Method for Railway Intrusion via Fine-Tune Approach and Contrastive Learning[J], IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-13, 2023, Art no. 5018713, doi: 10.1109/TIM.2023.3288258, 2023.
部分授權(quán)專利
[1] 李小松,,黎熹來等,。一種輕量級復(fù)雜場景圖像融合模型和方法[P], 中國發(fā)明專利,專利號:2024114081629,,已授權(quán).
[2] 李小松,,李錦陽等。一種基于多尺度特征融合的小目標(biāo)檢測方法和模型[P], 中國發(fā)明專利,,專利號:2024114306374,,已授權(quán).
[3] 李小松,黃敬學(xué)等,。非對稱U-Net結(jié)構(gòu)的多模態(tài)圖像融合模型及構(gòu)建方法[P], 中國發(fā)明專利,,專利號:2024114546306,已授權(quán).
[4] 李小松,,接玉嬋等,。基于條件擴散概率模型的多模態(tài)圖像融合與超分辨率方法[P], 中國發(fā)明專利,,專利號:2024107471381,,已授權(quán).
[5] 李小松,劉慧純等,。一種交互引導(dǎo)的雙分支圖像去霧模型和圖像處理方法[P], 中國發(fā)明專利,,專利號:2024107472030,已授權(quán).
[6] 李小松,,黎熹來等,。一種含霧圖像融合模型和方法[P],中國發(fā)明專利,,專利號:2024100764131,,已授權(quán).
[7] 李小松,黃敬學(xué)等,。一種同步去噪的圖像融合方法及其相關(guān)設(shè)備[P],,中國發(fā)明專利,專利號:2024101002879,,已授權(quán).
[8] 李小松,,黎熹來等。 基于多聚焦信息整合的紅外與可見光圖像融合方法及系統(tǒng)[P]. 中國發(fā)明專利,,專利號:202311108029.7,,已授權(quán).
[9] 李小松,接玉嬋等,?;跀U展高斯差分和引導(dǎo)濾波的圖像融合方法[P],,中國發(fā)明專利,專利號:ZL. 202211279027. X,,已授權(quán).
[10] 李小松,,黎熹來等。一種基于無參考焦點質(zhì)量評估的多聚焦圖像融合方法[P],,中國發(fā)明專利,,專利號:ZL. 202211235129.1,已授權(quán).
[11] 李小松,,黎熹來等,。一種多聚焦圖像融合方法、 裝置,、電子設(shè)備及存儲介質(zhì)[P],中國發(fā)明專利,,專利號:ZL.
202211121718.7,,已授權(quán).
[12] 李小松,黎熹來等,。紅外和可見光圖像融合方法,、裝置、電子設(shè)備及存儲介質(zhì)[P]. 中國發(fā)明專利,,專利號:202310766879X,,已授權(quán).
[13] 李小松,歐振聲,。一種電解鋁生產(chǎn)在線監(jiān)測顯示系統(tǒng)[P],,中國實用新型專利,專利號:202320212990X,,已授權(quán).
[14] 李小松,,歐振聲。多回路配電出線泄漏電流監(jiān)控裝置[P],,中國實用新型專利,,專利號:2023202136674,已授權(quán).
部分登記軟著
[1] 李小松,,譚海曙,,程曉琦,趙紅森,,登記號:2022SR0967839, 證書號:軟著登字第9922038號.
[2] 李小松,,接玉嬋,譚海曙,,程曉琦,,登記號:2022SR0967856, 證書號:軟著登字第9922055號.
[3] 李小松,,接玉嬋,譚海曙,,程曉琦,,登記號:2022SR0967841, 證書號:軟著登字第9922040號.
[4] 李小松,接玉嬋,,程曉琦,,譚海曙,登記號:2022SR0998686, 證書號:軟著登字第9952885號.
[5] 李小松,,接玉嬋,,譚海曙,程曉琦,,登記號:2022SR1008062, 證書號:軟著登字第9962261號.
[6] 李小松,,譚海曙,程曉琦,,張益,,登記號:2022SR1041583, 證書號:軟著登字第9995782號.
[7] 李小松,黎熹來,,譚海曙,,周賀蕊,登記號:2022SR0956619, 證書號:軟著登字第9910818號.
[8] 李小松,,李江偉,,程曉琦,譚海曙,,登記號:2022SR0956543, 證書號:軟著登字第9910742號.
[9] 李小松,,接玉嬋,譚海曙,,程曉琦,,登記號:2022SR1043844, 證書號:軟著登字第9998043號.
[10] 李小松,黎熹來,,譚海曙,,梁耀中,登記號:2022SR1007944, 證書號:軟著登字第9962143號.
所授課程
[1] 理論課:模擬電子技術(shù),、工程計算,、大學(xué)物理;
[2] 實驗課:模擬電子技術(shù)實驗課(含課程設(shè)計),、大學(xué)物理實驗,、普通物理實驗。
課題組學(xué)生參加的國內(nèi)外學(xué)術(shù)交流
2024年: WACV(美國夏威夷), ICASSP(韓國首爾), VALSE(重慶), CCIG(西安), 西湖大學(xué)(暑期夏令營,,杭州), MICCAI(摩洛哥馬拉喀什), PRCV(烏魯木齊), ACCV(越南河內(nèi)), CSIG青年科學(xué)家會議(杭州);
2023年: CCIG(蘇州), VALSE(無錫), ChinaMM(昆明), ICIG(南京), PRCV(廈門), CSIG青年科學(xué)家會議(廣州);
2022年: PRCV(深圳),。
其它
[1] 在《中國教育報》2025年2月25日第11版發(fā)表“培養(yǎng)光電類專業(yè)復(fù)合型創(chuàng)新人才——佛山大學(xué)物理與光電工程學(xué)院深化科產(chǎn)教融合”文章,;
[2] 佛山大學(xué)2022,2024年終考核優(yōu)秀,,佛山大學(xué)2024年度優(yōu)秀班主任,;
[3] 聘期高層次人才中期考核優(yōu)秀,期滿考核合格(最高檔為合格),;
[4] 指導(dǎo)學(xué)生獲2023年挑戰(zhàn)杯省賽一等獎,,2025挑戰(zhàn)杯校賽一等獎(擬參加省賽);
[5] 指導(dǎo)的21級碩士接玉嬋,、22級碩士黃敬學(xué)獲研究生國家獎學(xué)金,、接玉嬋獲優(yōu)秀畢業(yè)生等稱號;
[6] 指導(dǎo)的21級本科生黎熹來獲批主持大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計劃國家級項目2項,。
在讀學(xué)生
2023級博士:鄭伊玫
2024級碩士:黃莊釩,、王玉春、楊麗芳
2023級碩士:陳璁,、徐宇燊,、劉慧純
2022級碩士:黃敬學(xué)、劉武陽
本科生:黎熹來(2021級),、李浩宇(2022級)、蔣煒?。?/span>2023級)
畢業(yè)生及去向
[1] 2021級,,接玉嬋(電子信息專碩),華南理工大學(xué),,計算機科學(xué)與技術(shù)專業(yè)博士,;在讀期間以第一作者發(fā)表中科院一區(qū)×1,二區(qū)×4,,三區(qū)×1,,C會×1,發(fā)明專利授權(quán)×2,、實審×7,,軟著×5,一區(qū)在審×2,。
[2] 2021級,,李江偉(光學(xué)工程學(xué)碩),深圳市玻爾智造科技有限公司,,光學(xué)工程師,;在讀期間以第一作者發(fā)表中科院三區(qū)×3,實審發(fā)明專利×4,。
招生要求
大學(xué)英語六級或四級450分及以上,,編程能力強,,數(shù)學(xué)基礎(chǔ)好,對計算機視覺,、圖像處理,、模式識別等方向感興趣。課題組在物電,、機電和電信學(xué)院均有少量學(xué)碩,、專碩指標(biāo),歡迎大家報考,!
(注意:發(fā)郵件請說明你選擇讀研的原因,,研究生期間計劃,以及你的目標(biāo)及未來打算等)