基于CiteSpace的小目标检测研究热点与发展趋势探析
Research Hotspots and Development Trends of Small Target Detection Based on CiteSpace
DOI: 10.12677/sea.2026.152013, PDF,    科研立项经费支持
作者: 佟 磊:河北软件职业技术学院软件工程系,河北 保定;河北省智能互联装备与多模态大数据应用技术研发中心,河北 保定
关键词: 小目标检测文献计量法CiteSpace知识图谱研究热点发展趋势Small Target Detection Bibliometrics CiteSpace Knowledge Graph Research Hotspots Development Trend
摘要: 为系统梳理小目标检测领域的研究脉络与发展态势,精准捕捉领域知识结构与前沿动态,以中国知网收录的1728篇核心期刊论文为研究对象,综合运用文献计量法与CiteSpace可视化分析技术,从文献时间分布、关键词共现网络、聚类结构及突现特征四个维度展开深度分析。研究结果表明,小目标检测领域的发展历程呈现萌芽探索、平稳积累、爆发增长三阶段演化特征;领域研究热点已形成算法优化、场景应用、技术支撑相互关联的三层体系;前沿演进路径遵循从传统图像处理方法到深度学习深度融合,再到轻量化模型工程化落地的清晰逻辑。本文通过量化分析与质性研究相结合的方式,全面呈现小目标检测领域的学术图景,可为科研人员把握领域研究动态、布局创新研究方向提供重要参考,同时为相关技术的产业化落地提供理论支撑与实践指导。
Abstract: To systematically sort out the research context and development trend in the field of small target detection, and accurately capture the domain knowledge structure and cutting-edge dynamics, this paper takes 1728 core journal papers included in China National Knowledge Infrastructure (CNKI) as the research objects, and conducts an in-depth analysis from four dimensions: temporal distribution of literature, keyword co-occurrence network, clustering structure and burst characteristics, by comprehensively adopting bibliometrics and CiteSpace visual analysis technology. The research results show that the development process of the small target detection field presents distinct evolutionary characteristics of three stages, namely embryonic exploration, steady accumulation and explosive growth; the research hotspots in this field have formed an interrelated three-tier system composed of algorithm optimization, scenario application and technical support; the cutting-edge evolution path follows a clear logic from traditional image processing methods to the in-depth integration of deep learning, and then to the engineering implementation of lightweight models. By combining quantitative analysis with qualitative research, this paper comprehensively presents the academic landscape of the small target detection field, which can provide an important reference for researchers to grasp the research dynamics and layout innovative research directions in this field, and also offer theoretical support and practical guidance for the industrialization of relevant technologies.
文章引用:佟磊. 基于CiteSpace的小目标检测研究热点与发展趋势探析[J]. 软件工程与应用, 2026, 15(2): 127-136. https://doi.org/10.12677/sea.2026.152013

参考文献

[1] Lin, T., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014) Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B. and Tuytelaars, T., Eds., Computer VisionECCV 2014, Springer, 740-755. [Google Scholar] [CrossRef
[2] Krishna, H. and Jawahar, C.V. (2017) Improving Small Object Detection. 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), Nanjing, 26-29 November 2017, 340-345. [Google Scholar] [CrossRef
[3] 刘耿焕, 曾祥津, 豆嘉真, 等. 基于深度学习的小目标检测技术研究进展(特邀) [J]. 红外与激光工程, 2024, 53(9): 196-228.
[4] 王新增, 严国莉, 关晓歉. 灰度形态学滤波的红外运动小目标检测方法[J]. 中国测试技术, 2006(5): 79-81.
[5] 李胜勇, 姜涛, 朱强华. 红外序列图像中小目标实时检测系统设计与实现[J]. 红外技术, 2010, 32(8): 471-474.
[6] 高星, 刘剑飞, 郝禄国, 等. 基于YOLOv3算法的训练集优化和检测方法的研究[J]. 计算机工程与科学, 2020, 42(1): 103-109.
[7] 李澄非, 蔡嘉伦, 邱世汉, 等. 基于改进YOLOv4算法的PCB缺陷检测[J]. 电子测量技术, 2021, 44(17): 146-153.
[8] 牛为华, 殷苗苗. 基于改进YOLOv5的道路小目标检测算法[J]. 传感技术学报, 2023, 36(1): 36-44.
[9] 冯泰梾, 张雪松, 宋存利, 等. 改进YOLOv7的小目标检测方法[J]. 计算机工程与应用, 2025, 61(10): 203-213.
[10] 王建敏, 孙廷松, 孙建宇, 等. 遥感图像的多尺度和密集小目标检测算法[J]. 测绘科学, 2025, 50(11): 66-74.
[11] 陈超美, 陈悦, 侯剑华, 等. CiteSpaceⅡ: 科学文献中新趋势与新动态的识别与可视化[J]. 情报学报, 2009, 28(3): 401-421.
[12] 王鹏, 程思儒. 人工智能高质量数据集的发展趋势及热点——基于CiteSpace的知识图谱分析[J]. 技术经济与管理研究, 2025(4): 43-48.
[13] 陈伊高, 黄楚新. 人工智能技术与出版深度融合的焦点透视与趋势展望——基于CiteSpace的可视化分析[J]. 科技与出版, 2024(4): 112-120.
[14] 张瑞芳, 杜伊婷, 程小辉. 无人机视角下小目标检测算法BiEO-YOLOv8s[J/OL]. 激光与光电子学进展: 1-11.
https://link.cnki.net/urlid/31.1690.TN.20240624.2253.044, 2026-02-05.
[15] 翁智, 刘海鑫, 郑志强. CSD-YOLOv8s:基于无人机图像的密集小目标羊只检测模型[J]. 智慧农业(中英文), 2024, 6(4): 42-52.
[16] 胡佳乐, 周敏, 申飞. 面向无人机小目标的RTDETR改进检测算法[J]. 计算机工程与应用, 2024, 60(20): 198-206.
[17] 徐辛超, 孟祥柯, 于佳琪. 基于改进YOLOv5s的遥感影像小目标检测[J]. 测绘科学, 2024, 49(6): 143-153.
[18] 洪炎, 汪磊, 苏静明, 等. 基于改进YOLOv8的煤矿输送带异物检测[J]. 工矿自动化, 2024, 50(6): 61-69.
[19] 桑雨, 李立权, 李铁. 轻量化YOLOv7-tiny的遥感图像小目标检测[J]. 科学技术与工程, 2024, 24(18): 7726-7732.
[20] 胡昭华, 李昱辉. 基于YOLOX-Tiny有偏特征融合网络的遥感目标检测[J]. 遥感技术与应用, 2024, 39(3): 590-602.
[21] 李峻宇, 刘乾坤, 付莹. 融合注意力机制的红外小目标检测[J]. 航空学报, 2024, 45(14): 84-95.
[22] Chen, Y., Chen, C.M., Liu, Z.Y., et al. (2015) The Methodology Function of Cite Space Mapping Knowledge Domains. Studies in Science of Science, 33, 242-253.