复杂光照环境下融合轻量级光照增强网络的视觉SLAM方法

doi:10.11947/j.AGCS.2026.20250514

测绘学报 ›› 2026, Vol. 55 ›› Issue (7): 1278-1292.doi: 10.11947/j.AGCS.2026.20250514

• 摄影测量学与遥感 • 上一篇

复杂光照环境下融合轻量级光照增强网络的视觉SLAM方法

曾路兵¹(), 李建胜¹^,²^,³(), 王安成¹^,²^,³^,⁴, 杨子迪¹, 高宇宁¹, 张嘉杰¹

^1.信息工程大学地理空间信息学院，河南　郑州　450001
^2.智慧中原地理信息技术河南省协同创新中心，河南　郑州　450001
^3.北斗导航应用技术河南省协同创新中心，河南　郑州　450001
^4.智慧地球重点实验室，北京　100029

收稿日期:2025-12-05 修回日期:2026-07-18 发布日期:2026-08-18
通讯作者: 李建胜 E-mail:zlb17275600401@163.com;ljs2021@vip.henu.edu.cn
作者简介:曾路兵（2002—），男，硕士生，研究方向为计算机视觉、多源融合导航。 E-mail：zlb17275600401@163.com
基金资助:
国家自然科学基金(42330113)

A visual SLAM method fusing lightweight illumination enhancement network in complex illumination environments

Lubing Zeng¹(), Jiansheng Li¹^,²^,³(), Ancheng Wang¹^,²^,³^,⁴, Zidi Yang¹, Yuning Gao¹, Jiajie Zhang¹

^1.School of Geospatial Information, Information Engineering University, Zhengzhou 450001
^2.Collaborative Innovation Center of Geo-Information Technology for Smart Central Plains, Zhengzhou 450001
^3.Collaborative Innovation Center of BDS Navigation Application Technology, Zhengzhou 450001
^4.Key Laboratory of Smart Earth, Beijing 100029

Received:2025-12-05 Revised:2026-07-18 Published:2026-08-18
Contact: Jiansheng Li E-mail:zlb17275600401@163.com;ljs2021@vip.henu.edu.cn
About author:Zeng Lubing (2002—), male, postgraduate, majors in computer vision and multi-source fusion navigation. E-mail: zlb17275600401@163.com
Supported by:
The National Natural Science Foundation of China(42330113)

摘要/Abstract

摘要：

视觉同时定位与建图（SLAM）在低光照、高曝光等复杂光照下易因特征质量退化而跟踪失败。为此，本文提出一种基于轻量级光照增强网络的视觉SLAM方法。首先，设计了一种空间自适应的光照均衡（IE）曲线，通过逐像素空间趋势图实现低光照增强与高曝光抑制，同时维持正常光照区域的光度一致性。然后，通过提出一种基于图像均值驱动的自适应连续迭代策略，动态调整曲线阶数以适应不同曝光程度的图像，有效避免了固定迭代的局限性。最后，通过改进DCE-Net网络，采用深度可分离卷积（DSC）与末端批归一化实现在几乎同等参数量的情况下维持训练的稳定性。经测试，CPU端单帧处理仅需12 ms，满足SLAM前端实时性的要求。在EuRoC、TUM-VI及KITTI数据集的12个复杂光照序列上进行试验验证，并与多种传统和深度学习视觉增强算法对比分析，本文方法的绝对轨迹误差（ATE）的均方根误差（RMSE）比VINS-Fusion平均降低32.3%，在所有对比方法中性能最优，为视觉SLAM在复杂光照环境下的可靠部署提供了解决方案。

关键词: 视觉SLAM, 图像增强, 复杂光照, 深度学习

Abstract:

Visual simultaneous localization and mapping (SLAM) is susceptible to tracking failure under complex illumination conditions such as low-light and high-exposure due to feature quality degradation. To address this challenge, we propose a visual SLAM method based on a lightweight illumination enhancement network. First, a spatially adaptive illumination equalization (IE) curve is designed to achieve low-light enhancement and high-exposure suppression through per-pixel spatial trend maps while maintaining photometric consistency in normally illuminated regions. Then, an image-mean-driven adaptive continuous iteration strategy is proposed to dynamically adjust the curve order for images with varying exposure levels, effectively avoiding the limitations of fixed iterations. Finally, we improve the deep curve estimation network (DCE-Net) by employing depth-wise separable convolutions (DSC) and end-batch normalization to maintain training stability with almost the same parameter count. Tests show that single-frame processing on the CPU requires only 12 ms, meeting the real-time requirements of the SLAM frontend. To validate the proposed method, experiments were conducted on 12 challenging illumination sequences from the EuRoC, TUM-VI, and KITTI datasets. Comparative analyses were performed with various traditional and deep learning visual enhancement algorithms. The experimental results demonstrate that the root mean square error (RMSE) of absolute trajectory error (ATE) is reduced by 32.3% on average compared with VINS-Fusion, achieving the best performance among all compared methods. This method provides a solution for the reliable deployment of visual SLAM in complex illumination environments.

Key words: visual SLAM, image enhancement, complex illumination, deep learning

中图分类号:

曾路兵, 李建胜, 王安成, 杨子迪, 高宇宁, 张嘉杰. 复杂光照环境下融合轻量级光照增强网络的视觉SLAM方法[J]. 测绘学报, 2026, 55(7): 1278-1292.

Lubing Zeng, Jiansheng Li, Ancheng Wang, Zidi Yang, Yuning Gao, Jiajie Zhang. A visual SLAM method fusing lightweight illumination enhancement network in complex illumination environments[J]. Acta Geodaetica et Cartographica Sinica, 2026, 55(7): 1278-1292.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xb.chinasmp.com/CN/10.11947/j.AGCS.2026.20250514

http://xb.chinasmp.com/CN/Y2026/V55/I7/1278

图/表 22

图1

图2

图3

图4

图5

图6

表1

表2

图7

表3

表4

表5

表6

图8

表7

表8

表9

表10

表11

图9

图10

表12

参考文献 35

[1]	陈锐志, 王磊, 李德仁, 等. 导航与遥感技术融合综述[J]. 测绘学报, 2019, 48(12): 1507-1522. DOI: . doi: 10.11947/j.AGCS.2019.20190446
	Chen Ruizhi, Wang Lei, Li Deren, et al. A survey on the fusion of the navigation and the remote sensing techniques[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12): 1507-1522. DOI: . doi: 10.11947/j.AGCS.2019.20190446
[2]	王晨捷, 罗斌, 李成源, 等. 无人机视觉SLAM协同建图与导航[J]. 测绘学报, 2020, 49(6): 767-776. DOI: . doi: 10.11947/j.AGCS.2020.20190145
	Wang Chenjie, Luo Bin, Li Chengyuan, et al. The collaborative mapping and navigation based on visual SLAM in UAV platform[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(6): 767-776. DOI: . doi: 10.11947/j.AGCS.2020.20190145
[3]	Yuan Zikang, Lang Fengtian, Xu Tianle, et al. SR-LIO: LiDAR-inertial odometry with sweep reconstruction[C]//Proceedings of 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024: 7862-7869.
[4]	张继贤, 刘飞. 视觉SLAM环境感知技术现状与智能化测绘应用展望[J]. 测绘学报, 2023, 52(10): 1617-1630. DOI: . doi: 10.11947/j.AGCS.2023.20220240
	Zhang Jixian, Liu Fei. Review of visual SLAM environment perception technology and intelligent surveying and mapping application[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(10): 1617-1630. DOI: . doi: 10.11947/j.AGCS.2023.20220240
[5]	Pan Youqi, Zhou Wugen, Cao Yingdian, et al. Adaptive VIO: deep visual-inertial odometry with online continual learning[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 18019-18028.
[6]	Peng Xiongfeng, Liu Zhihua, Li Weiming, et al. DVI-SLAM: a dual visual inertial SLAM network[C]//Proceedings of 2024 IEEE International Conference on Robotics and Automation, 2024: 12020-12026.
[7]	Xu Kuan, Hao Yuefan, Yuan Shenghai, et al. AirSLAM: an efficient and illumination-robust point-line visual SLAM system[J]. IEEE Transactions on Robotics, 2025, 41: 1673-1692.
[8]	Hana F M, Maulida I D. Analysis of contrast limited adaptive histogram equalization (CLAHE) parameters on finger knuckle print identification[J]. Journal of Physics: Conference Series, 2021, 1764(1): 012049.
[9]	Jobson D J, Rahman Z, Woodell G A. A multiscale retinex for bridging the gap between color images and the human observation of scenes[J]. IEEE Transactions on Image Processing, 1997, 6(7): 965-976.
[10]	Jobson D J. Retinex processing for automatic image enhancement[J]. Journal of Electronic Imaging, 2004, 13(1): 100.
[11]	Petro A B, Sbert C, Morel J M. Multiscale retinex[J]. Image Processing on Line, 2014, 4: 71-88.
[12]	李艳, 张科, 李明辉. 微光场景下基于改进自适应Retinex的视觉SLAM算法[J]. 计算机工程与应用, 2026, 62(6): 391-400.
	Li Yan, Zhang Ke, Li Minghui. Visual SLAM algorithm based on improved adaptive Retinex in low-light scenarios[J]. Computer Engineering and Applications, 2026, 62(6): 391-400.
[13]	李雪强, 李建胜, 王安成, 等. 低光照条件下基于图像增强的视觉惯性组合导航方法[J]. 测绘科学技术学报, 2025, 41(1): 21-26.
	Li Xueqiang, Li Jiansheng, Wang Ancheng, et al. Visual-inertial integrated navigation method based on image enhancement under low illumination conditions[J]. Journal of Geomatics Science and Technology, 2025, 41(1): 21-26.
[14]	蔺小虎, 杨鑫, 姚顽强, 等. 面向复杂地下空间的多源传感器数据动态加权融合SLAM方法[J]. 测绘学报, 2025, 54(3): 523-535. DOI: . doi: 10.11947/j.AGCS.2025.20230586
	Lin Xiaohu, Yang Xin, Yao Wanqiang, et al. A dynamic weighted fusion SLAM method using multi-source sensor data in complex underground spaces[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(3): 523-535. DOI: . doi: 10.11947/j.AGCS.2025.20230586
[15]	王纪武, 万伟鹏, 尚学强, 等. 基于图像增强和自适应阈值的语义视觉SLAM系统[J]. 计算机集成制造系统, 2024, 30(12): 4217-4232.
	Wang Jiwu, Wan Weipeng, Shang Xueqiang, et al. Semantic visual SLAM system based on image enhancement and adaptive thresholding[J]. Computer Integrated Manufacturing Systems, 2024, 30(12): 4217-4232.
[16]	Chen Gang, Du Guoqiang, Yang Chenguang, et al. An underwater visual SLAM system with adaptive image enhancement[J]. Ocean Engineering, 2025, 326: 120896.
[17]	Wei Chen, Wang Wenjing, Yang Wenhan, et al. Deep retinex decomposition for low-light enhancement[PP/OL]. arXiv (2018-08-14) [2026-03-15]. https://doi.org/10.48550/arXiv.1808.04560.
[18]	Guo Chunle, Li Chongyi, Guo Jichang, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1777-1786.
[19]	Shi Yiqi, Liu Duo, Zhang Liguo, et al. ZERO-IG: zero-shot illumination-guided joint denoising and adaptive enhancement for low-light images[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 3015-3024.
[20]	Yan Qingsen, Feng Yixu, Zhang Cheng, et al. HVI: a new color space for low-light image enhancement[C]//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025: 5678-5687.
[21]	Li Yiyu, Xu Ke, Hancke G P, et al. Color shift estimation-and-correction for image enhancement[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024: 25389-25398.
[22]	江松, 崔智翔, 代碧波, 等. 暗环境适应性的基于SLAM的煤矿井下机器人定位方法[J]. 煤炭科学技术, 2025, 53(5): 349-361.
	Jiang Song, Cui Zhixiang, Dai Bibo, et al. SLAM-based localization method of coal mine underground robot with adaptability to dark illumination environment[J]. Coal Science and Technology, 2025, 53(5): 349-361.
[23]	Jiang Kuosheng, Zhu Chengbing, Yang Jinbao. Research on low-light environment SLAM system via retinex enhancement and deep feature optimization[J]. IEEE Sensors Journal, 2025, 25(15): 29992-30004.
[24]	Liu Yanjie, Wu Heng, Zhang Weiwu, et al. Low-light enhancement visual SLAM via deep deformable power curve estimation[J]. IEEE Sensors Journal, 2025, 25(10): 17404-17412.
[25]	Qin Tong, Cao Shaozu, Pan Jie, et al. A general optimization-based framework for global pose estimation with multiple sensors[PP/OL]. arXiv (2019-01-11) [2026-03-15]. https://doi.org/10.48550/arXiv.1901.03642.
[26]	Li Chongyi, Guo Chunle, Loy C C. Learning to enhance low-light image via zero-reference deep curve estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(8): 4225-4238.
[27]	Cai Jianrui, Gu Shuhang, Zhang Lei. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, 2018, 27(4): 2049-2062.
[28]	Hai Jiang, Xuan Zhu, Yang Ren, et al. R2RNet: low-light image enhancement via real-low to real-normal network[J]. Journal of Visual Communication and Image Representation, 2023, 90: 103712.
[29]	Zhang Ru, Zhu Feng, Liu Jianyi, et al. Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis[J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 1138-1150.
[30]	Baker S, Matthews I. Lucas-kanade 20 years on: a unifying framework[J]. International Journal of Computer Vision, 2004, 56(3): 221-255.
[31]	Burri M, Nikolic J, Gohl P, et al. The EuRoC micro aerial vehicle datasets[J]. The International Journal of Robotics Research, 2016, 35(10): 1157-1163.
[32]	Geiger A, Lenz P, Stiller C, et al. Vision meets robotics: the KITTI dataset[J]. International Journal of Robotics Research, 2013, 32(11): 1231-1237.
[33]	Schubert D, Goll T, Demmel N, et al. The TUM VI benchmark for evaluating visual-inertial odometry[C]//Proceedings of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018: 1680-1687.
[34]	Hadjivelichkov D, Ægidius S, Modugno V, et al. Task-critical part alignment improves imitation of object interactions[C]//Proceedings of 2025 IEEE International Conference on Advanced Robotics, 2025: 329-334.
[35]	Qin Tong, Li Peiliang, Shen Shaojie. VINS-mono: a robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics, 2018, 34(4): 1004-1020.

层名	结构
layer1
layer2-4
layer5-6
layer7

方法	FLOPs	模型参数量	处理时间/ms	计算平台
CLAHE	—	—	0.971	CPU
MSRCR	—	—	1 336.574	CPU
Zero-DCE	20 761 804 800	79 416	175.437	CPU
Zero-DCE	20 761 804 800	79 416	4.257	GPU
Zero-DCE++	49 917 952	10 561	9.704	CPU
Zero-DCE++	49 917 952	10 561	1.830	GPU
CIDNet	32 531 742 720	1 973 496	947.859	CPU
CIDNet	32 531 742 720	1 973 496	41.738	GPU
本文方法	49 967 104	10 567	12.679	CPU
本文方法	49 967 104	10 567	1.453	GPU

图像	均值	标准差	平均梯度	信息熵	NIQE
原始图像	14.338 1	8.022 5	5.182 0	4.897 1	7.207 5
CLAHE结果	35.542 8	19.216 1	14.078 6	6.082 5	7.729 9
MSRCR结果	165.257 6	37.994 8	28.678 1	6.908 2	7.977 6
Zero-DCE结果	75.921 2	34.795 3	23.097 5	6.695 5	8.021 4
Zero-DCE++结果	77.276 0	34.536 5	23.194 1	6.704 8	8.218 9
CIDNet结果	68.344 6	40.698 7	21.632 7	6.493 9	6.409 4
本文方法结果	119.783 9	60.017 8	31.589 6	6.003 9	6.710 2

图像	均值	标准差	平均梯度	信息熵	NIQE
原始图像	124.830 3	60.627 8	31.971 9	7.474 5	3.788 9
CLAHE结果	136.767 1	63.630 5	53.221 3	7.647 8	4.066 9
MSRCR结果	174.830 5	19.451 1	21.402 6	6.244 7	4.029 6
Zero-DCE结果	170.069 2	39.685 8	32.786 1	7.051 0	3.960 5
Zero-DCE++结果	177.933 8	37.298 8	32.818 3	6.994 8	4.024 0
CIDNet结果	178.311 7	44.844 0	29.506 4	7.229 7	4.089 8
本文方法结果	125.197 7	59.427 4	31.439 9	7.447 3	3.769 6

图像	均值	标准差	平均梯度	信息熵	NIQE
原始图像	134.376 7	65.374 0	22.437 3	7.690 9	3.870 4
CLAHE结果	141.493 1	62.546 3	32.603 4	7.756 7	3.216 4
MSRCR结果	205.829 7	22.048 6	13.681 0	5.769 1	3.960 9
Zero-DCE结果	173.656 3	44.543 9	24.447 5	7.318 9	3.642 2
Zero-DCE++结果	179.398 9	44.409 1	24.519 7	7.296 8	3.671 7
CIDNet结果	187.037 6	54.634 6	22.166 5	7.143 2	3.606 7
本文方法结果	132.241 2	64.060 3	22.185 7	7.685 3	3.859 7

复杂光照环境下融合轻量级光照增强网络的视觉SLAM方法

A visual SLAM method fusing lightweight illumination enhancement network in complex illumination environments

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 22

参考文献 35

相关文章 15

编辑推荐

Metrics

本文评价

图像	均值	标准差	平均梯度	信息熵	NIQE
原始图像	202.709 7	45.871 7	57.450 5	7.099 7	2.976 1
CLAHE结果	169.854 7	62.755 1	101.586 7	7.635 1	4.211 1
MSRCR结果	220.877 6	18.824 5	38.561 8	5.834 6	2.863 2
Zero-DCE结果	220.220 8	30.939 0	44.316 4	6.547 2	2.852 2
Zero-DCE++结果	220.815 7	30.356 7	45.868 2	6.519 0	2.869 0
CIDNet结果	216.408 5	34.584 2	34.282 6	6.544 7	3.100 8
本文方法结果	140.392 7	69.858 5	104.129 0	7.375 0	2.750 4

方法	匹配数量					匹配成功率/（%）
方法	图像A	图像B	图像C	图像D	图像E	图像A	图像B	图像C	图像D	图像E
原始图像	41	285	35	247	247	78.0	97.9	14.3	25.5	40.9
CLAHE	71	286	79	251	246	77.5	96.9	5.6	17.9	38.2
MSRCR	275	274	40	270	248	41.5	96.0	12.5	24.4	30.6
Zero-DCE	229	287	61	263	254	47.6	97.2	9.8	22.8	42.1
Zero-DCE++	253	287	48	258	254	49.4	98.3	10.4	20.2	46.1
CIDNet	252	271	50	269	248	78.2	97.0	10.0	22.3	46.8
本文方法	279	289	85	272	258	86.4	99.3	18.8	31.2	48.8

VINS-Fusion	LE曲线	IE曲线	固定迭代	自适应迭代	匹配特征点平均数量			平均耗时/ms
VINS-Fusion	LE曲线	IE曲线	固定迭代	自适应迭代	MH_04_difficult	room1	00	MH_04_difficult	room1	00
√	×	×	×	×	196	75	212	1.0	1.0	1.5
√	√	×	√	×	221	115	223	8.3	9.0	15.3
√	√	×	×	√	231	117	225	7.8	8.6	12.5
√	×	√	√	×	231	131	226	10.2	12.5	18.8
√	×	√	×	√	234	152	227	9.7	10.4	15.8

序列名称	长度/m	特点
V1_03_difficult	78.982	室内环境，平台运动剧烈，光照变化明显，包含无纹理区域
V2_03_difficult	86.128	室内环境，平台运动剧烈，光照变化明显，包含无纹理区域，图像序列存在丢帧问题
MH_04_difficult	91.747	大型工业环境，存在光照变化，管道多，平台经过一段极端黑暗
MH_05_difficult	97.593	的区域

序列名称	长度/m	特点
room1	146.790	室内环境，平台运动剧烈，存在长时间绕圈行为，光照变化明显，包含无纹理区域，鱼眼相机视野范围广
room2	141.598
room3	135.522
room4	68.698

序列名称	长度/m	特点
00	3 724.187	住宅区场景，平台高速运动，转弯速度快，相机帧率低，视野内存在运动车辆和行人，光照分布不均，存在大量墙面反光、路面反光、镜头眩光和车窗玻璃反射光的强逆光场景
02	5 067.233
03	560.888
09	1 705.051

数据集	序列名称	RMSE/m
数据集	序列名称	VINS-Fusion	CLAHE	Zero-DCE++	CIDNet	Our-8	Our-it
EuRoC	V1_03_difficult	0.137	0.118	0.126	0.107	0.144	0.101
	V2_03_difficult	0.293	0.255	0.300	0.294	0.259	0.228
	MH_04_difficult	0.244	0.209	0.282	0.165	0.157	0.146
	MH_05_difficult	0.343	0.409	0.302	0.295	0.317	0.238
TUM-VI	room1	0.117	0.140	0.112	0.092	0.085	0.086
	room2	0.141	0.122	0.071	0.117	0.103	0.066
	room3	0.127	0.194	0.231	0.178	0.092	0.083
	room4	0.081	0.088	0.072	0.064	0.066	0.051
KITTI	00	29.214	17.082	18.494	15.739	15.546	13.261
	02	25.777	29.256	27.202	25.873	22.630	19.916
	03	1.806	1.471	1.657	1.641	1.515	1.376
	09	9.224	14.643	8.644	8.880	7.769	7.753

[1]	李贺, 陈克杰, 崔文峰, 柴海山, 方荣新, 彭朝勇, 孙丽. 基于北斗三号PPP-B2b同震位移与深度学习的震级快速估算——以2025年定日Mw 7.1和曼德勒Mw 7.7地震为例[J]. 测绘学报, 2026, 55(7): 1171-1182.
[2]	赵曦, 袁强强, 徐佳丹. 面向复杂海洋环境的侧扫声呐目标样本生成与增强方法[J]. 测绘学报, 2026, 55(7): 1229-1239.
[3]	刘硕, 孙海丽, 钟若飞. 多尺度边缘信息融合的隧道渗漏水检测方法[J]. 测绘学报, 2026, 55(6): 1116-1127.
[4]	时天东, 赵玲, 赵文豪, 齐霁, 崔浩, 彭程里, 张新长. 时空信息显式引导的高分光学遥感影像可控生成方法[J]. 测绘学报, 2026, 55(5): 894-908.
[5]	王家耀, 陈琳, 程士源, 王利军, 熊思奇. 人工智能赋能地图科学数智化[J]. 测绘学报, 2026, 55(3): 381-389.
[6]	禄小敏, 张志义, 闫浩文, 何毅, 苏小宁. 融合深度图信息最大化和多层感知机的建筑物群组模式识别方法[J]. 测绘学报, 2026, 55(3): 425-438.
[7]	季顺平, 刘瑾, 高建, 龚健雅. 多视影像深度学习密集匹配三维重建智能框架[J]. 测绘学报, 2025, 54(9): 1633-1646.
[8]	张继贤, 顾海燕, 倪欢, 李海涛, 杨懿, 丁少鹏, 隋淞蔓. 遥感智能变化检测的深度学习方法：演变与发展趋势[J]. 测绘学报, 2025, 54(8): 1347-1370.
[9]	方帅, 刘加恩, 张晶. 自适应参考特征引入与多尺度特征聚合的时空融合算法[J]. 测绘学报, 2025, 54(8): 1476-1488.
[10]	孟妮娜, 李凤梅, 周校东. 数据与认知双驱动的建筑物群制图综合结果与尺度一致性识别[J]. 测绘学报, 2025, 54(7): 1318-1331.
[11]	王亚青, 王中辉. 异构图卷积网络支持下的河系自动选取方法[J]. 测绘学报, 2025, 54(7): 1332-1345.
[12]	安晓亚, 郭伟茹, 张鹏鑫, 李欣欣, 石磊. 顾及几何位置和移动特征相似性的船舶轨迹聚类方法[J]. 测绘学报, 2025, 54(6): 1107-1121.
[13]	王超, 陈天宇, 张同, AhmedTanvir, 纪立强, 谢涛, 杨佳俊, 王帅. 基于全局差分增强模块和平衡惩罚损失的多源光学遥感影像变化检测[J]. 测绘学报, 2025, 54(5): 873-887.
[14]	罗卿莉, 李雪岩, 黄国满, 陈红辉, 薛铭龙, 李健. AOSN：α-最优网络模型的山区单通道SAR高程重建方法[J]. 测绘学报, 2025, 54(5): 888-898.
[15]	蔺小虎, 杨鑫, 姚顽强, 马宏伟, 马柏林, 马雄伟. 面向复杂地下空间的多源传感器数据动态加权融合SLAM方法[J]. 测绘学报, 2025, 54(3): 523-535.