Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (3): 722-731.DOI: 10.11772/j.issn.1001-9081.2023030313
Special Issue: 人工智能
• Artificial intelligence • Previous Articles Next Articles
Yuqiu LI1, Liping HOU1, Jian XUE1, Ke LYU1,2(), Yong WANG3
Received:
2023-03-24
Revised:
2023-06-16
Accepted:
2023-06-19
Online:
2023-09-05
Published:
2024-03-10
Contact:
Ke LYU
About author:
LI Yuqiu, born in 1998, M. S. candidate. His research interests include computer vision, remote sensing image processing.Supported by:
通讯作者:
吕科
作者简介:
李雨秋(1998—),男,山东德州人,硕士研究生,CCF会员,主要研究方向:计算机视觉、遥感图像处理基金资助:
CLC Number:
Yuqiu LI, Liping HOU, Jian XUE, Ke LYU, Yong WANG. Remote sensing image recommendation method based on content interpretation[J]. Journal of Computer Applications, 2024, 44(3): 722-731.
李雨秋, 侯利萍, 薛健, 吕科, 王泳. 基于内容解译的遥感图像推荐方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 722-731.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023030313
用户 | 拍摄时间 | 经度( | 纬度( | 分辨率 | 图像来源 |
---|---|---|---|---|---|
生态环境部 卫星环境应用中心 | 2021-05-10 | 109.5—110.5 | 34.0—35.0 | 0.5/2 | GF-2 |
2021-06-20 | 103.0—104.5 | 30.0—31.5 | 1/4/3 | JL-1 | |
2022-01-15 | 115.5—116.5 | 38.0—39.0 | 3/5 | CycloMedia | |
2022-05-30 | 112.0—113.0 | 36.0—37.0 | 1/4/3 | Landsat-9 | |
2022-11-05 | 102.5—103.5 | 31.5—32.5 | 0.5/1/10 | Google Earth | |
中国交通通信信息中心 | 2021-07-02 | 116.0—117.0 | 39.5—40.5 | 1/4/3 | JL-1 |
2022-04-20 | 116.5—117.5 | 40.5—41.5 | 2 | Landsat-9 | |
2022-02-28 | 117.0—118.0 | 40.0—41.0 | 1/4/3 | JL-1 | |
2022-03-08 | 116.0—117.0 | 39.5—40.5 | 0.5/2 | GF-2 | |
2021-06-08 | 115.5—116.5 | 39.0—40.0 | 3/5 | CycloMedia |
Tab. 1 Theme element (X) values of some orders
用户 | 拍摄时间 | 经度( | 纬度( | 分辨率 | 图像来源 |
---|---|---|---|---|---|
生态环境部 卫星环境应用中心 | 2021-05-10 | 109.5—110.5 | 34.0—35.0 | 0.5/2 | GF-2 |
2021-06-20 | 103.0—104.5 | 30.0—31.5 | 1/4/3 | JL-1 | |
2022-01-15 | 115.5—116.5 | 38.0—39.0 | 3/5 | CycloMedia | |
2022-05-30 | 112.0—113.0 | 36.0—37.0 | 1/4/3 | Landsat-9 | |
2022-11-05 | 102.5—103.5 | 31.5—32.5 | 0.5/1/10 | Google Earth | |
中国交通通信信息中心 | 2021-07-02 | 116.0—117.0 | 39.5—40.5 | 1/4/3 | JL-1 |
2022-04-20 | 116.5—117.5 | 40.5—41.5 | 2 | Landsat-9 | |
2022-02-28 | 117.0—118.0 | 40.0—41.0 | 1/4/3 | JL-1 | |
2022-03-08 | 116.0—117.0 | 39.5—40.5 | 0.5/2 | GF-2 | |
2021-06-08 | 115.5—116.5 | 39.0—40.0 | 3/5 | CycloMedia |
方法 | mAP/% | AP50/% | AP75/% | 帧率/(frame·s-1) |
---|---|---|---|---|
YOLOv4[ | 43.5 | 65.7 | 47.3 | 62.0 |
RFBNet[ | 51.5 | 68.6 | 57.1 | 41.5 |
EfficientDet[ | 52.1 | 70.1 | 57.5 | 56.5 |
YOLOX[ | 51.2 | 69.6 | 55.7 | 60.0 |
RetinaNet[ | 52.1 | 71.8 | 56.5 | 37.0 |
YOLOv3 | 42.7 | 63.8 | 45.9 | 55.0 |
YOLOv3(MobileNet v3) | 44.6 | 66.1 | 47.7 | 89.9 |
YOLOv3 (MobileNet v3+ PANet) | 48.1 | 68.9 | 52.3 | 74.0 |
RS-YOLO | 52.2 | 69.9 | 56.5 | 70.0 |
Tab. 2 Detection result comparison with different methods on DOTAv2.0
方法 | mAP/% | AP50/% | AP75/% | 帧率/(frame·s-1) |
---|---|---|---|---|
YOLOv4[ | 43.5 | 65.7 | 47.3 | 62.0 |
RFBNet[ | 51.5 | 68.6 | 57.1 | 41.5 |
EfficientDet[ | 52.1 | 70.1 | 57.5 | 56.5 |
YOLOX[ | 51.2 | 69.6 | 55.7 | 60.0 |
RetinaNet[ | 52.1 | 71.8 | 56.5 | 37.0 |
YOLOv3 | 42.7 | 63.8 | 45.9 | 55.0 |
YOLOv3(MobileNet v3) | 44.6 | 66.1 | 47.7 | 89.9 |
YOLOv3 (MobileNet v3+ PANet) | 48.1 | 68.9 | 52.3 | 74.0 |
RS-YOLO | 52.2 | 69.9 | 56.5 | 70.0 |
用户 | 元素项 | 不同组的需求频次 | 权重 | |||
---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | |||
生态环境部 卫星环境 应用中心 | 拍摄时间 | 18 | 13 | 13 | 17 | 0.22 |
空间 | 20 | 20 | 20 | 20 | 0.30 | |
图像来源 | 15 | 19 | 12 | 17 | 0.23 | |
分辨率 | 17 | 20 | 20 | 10 | 0.25 | |
总样本数 | 20 | 20 | 20 | 20 | — | |
中国交通通信 信息中心 | 拍摄时间 | 5 | 8 | 9 | 8 | 0.24 |
空间 | 10 | 10 | 10 | 10 | 0.31 | |
图像来源 | 8 | 7 | 4 | 6 | 0.20 | |
分辨率 | 9 | 10 | 8 | 5 | 0.25 | |
总样本数 | 10 | 10 | 10 | 10 | — |
Tab. 3 Frequency and weight of each theme element
用户 | 元素项 | 不同组的需求频次 | 权重 | |||
---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | |||
生态环境部 卫星环境 应用中心 | 拍摄时间 | 18 | 13 | 13 | 17 | 0.22 |
空间 | 20 | 20 | 20 | 20 | 0.30 | |
图像来源 | 15 | 19 | 12 | 17 | 0.23 | |
分辨率 | 17 | 20 | 20 | 10 | 0.25 | |
总样本数 | 20 | 20 | 20 | 20 | — | |
中国交通通信 信息中心 | 拍摄时间 | 5 | 8 | 9 | 8 | 0.24 |
空间 | 10 | 10 | 10 | 10 | 0.31 | |
图像来源 | 8 | 7 | 4 | 6 | 0.20 | |
分辨率 | 9 | 10 | 8 | 5 | 0.25 | |
总样本数 | 10 | 10 | 10 | 10 | — |
正样本推荐度 (平均) | 负样本推荐度 (平均) | 区分度 (正/负) | ||
---|---|---|---|---|
0.5 | 0.05 | 0.434 | 0.034 | 12.76 |
0.10 | 0.472 | 0.032 | 14.75 | |
0.20 | 0.453 | 0.035 | 12.94 | |
0.50 | 0.415 | 0.037 | 11.22 | |
1.0 | 0.05 | 0.584 | 0.052 | 11.23 |
0.10 | 0.659 | 0.049 | 13.45 | |
0.20 | 0.621 | 0.054 | 11.50 | |
0.50 | 0.546 | 0.056 | 9.75 | |
1.5 | 0.10 | 0.846 | 0.066 | 12.82 |
0.20 | 0.784 | 0.072 | 10.89 | |
2.0 | 0.10 | 1.033 | 0.083 | 12.45 |
0.20 | 0.950 | 0.090 | 10.56 |
Tab. 4 Comparative experiment results on parameters λ and α
正样本推荐度 (平均) | 负样本推荐度 (平均) | 区分度 (正/负) | ||
---|---|---|---|---|
0.5 | 0.05 | 0.434 | 0.034 | 12.76 |
0.10 | 0.472 | 0.032 | 14.75 | |
0.20 | 0.453 | 0.035 | 12.94 | |
0.50 | 0.415 | 0.037 | 11.22 | |
1.0 | 0.05 | 0.584 | 0.052 | 11.23 |
0.10 | 0.659 | 0.049 | 13.45 | |
0.20 | 0.621 | 0.054 | 11.50 | |
0.50 | 0.546 | 0.056 | 9.75 | |
1.5 | 0.10 | 0.846 | 0.066 | 12.82 |
0.20 | 0.784 | 0.072 | 10.89 | |
2.0 | 0.10 | 1.033 | 0.083 | 12.45 |
0.20 | 0.950 | 0.090 | 10.56 |
用户 | 关联度 指标 | 样本 正/负 | 不同组的平均关联度与推荐度 | ||||
---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | |||
生态环境部 卫星环境 应用中心 | 主题元素 | 正 | 0.548 | 0.598 | 0.534 | 0.534 | 0.619 |
负 | 0.072 | 0.012 | 0.061 | 0.063 | 0.034 | ||
图像内容 | 正 | 0.803 | 0.785 | 0.794 | 0.767 | 0.810 | |
负 | 0.108 | 0.037 | 0.021 | 0.107 | 0.073 | ||
推荐度 | 正 | 0.676 | 0.692 | 0.664 | 0.651 | 0.715 | |
负 | 0.090 | 0.025 | 0.041 | 0.085 | 0.054 | ||
中国交通通信 信息中心 | 主题元素 | 正 | 0.591 | 0.489 | 0.577 | 0.574 | 0.626 |
负 | 0.032 | 0.007 | 0.003 | 0.016 | 0.015 | ||
图像内容 | 正 | 0.672 | 0.721 | 0.701 | 0.683 | 0.745 | |
负 | 0.080 | 0.106 | 0.061 | 0.042 | 0.033 | ||
推荐度 | 正 | 0.632 | 0.605 | 0.639 | 0.629 | 0.686 | |
负 | 0.056 | 0.057 | 0.032 | 0.029 | 0.024 |
Tab.5 Average correlation and recommendation of data to be distributed under different groups of training data
用户 | 关联度 指标 | 样本 正/负 | 不同组的平均关联度与推荐度 | ||||
---|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | |||
生态环境部 卫星环境 应用中心 | 主题元素 | 正 | 0.548 | 0.598 | 0.534 | 0.534 | 0.619 |
负 | 0.072 | 0.012 | 0.061 | 0.063 | 0.034 | ||
图像内容 | 正 | 0.803 | 0.785 | 0.794 | 0.767 | 0.810 | |
负 | 0.108 | 0.037 | 0.021 | 0.107 | 0.073 | ||
推荐度 | 正 | 0.676 | 0.692 | 0.664 | 0.651 | 0.715 | |
负 | 0.090 | 0.025 | 0.041 | 0.085 | 0.054 | ||
中国交通通信 信息中心 | 主题元素 | 正 | 0.591 | 0.489 | 0.577 | 0.574 | 0.626 |
负 | 0.032 | 0.007 | 0.003 | 0.016 | 0.015 | ||
图像内容 | 正 | 0.672 | 0.721 | 0.701 | 0.683 | 0.745 | |
负 | 0.080 | 0.106 | 0.061 | 0.042 | 0.033 | ||
推荐度 | 正 | 0.632 | 0.605 | 0.639 | 0.629 | 0.686 | |
负 | 0.056 | 0.057 | 0.032 | 0.029 | 0.024 |
方法 | 不同样本的平均推荐度 | 区分度 | |
---|---|---|---|
正样本 | 负样本 | ||
文献[ | 0.548 | 0.072 | 7.61 |
文献[ | 0.553 | 0.076 | 7.28 |
本文方法 | 0.656 | 0.053 | 12.38 |
Tab. 6 Comparison of average recommendation among different methods
方法 | 不同样本的平均推荐度 | 区分度 | |
---|---|---|---|
正样本 | 负样本 | ||
文献[ | 0.548 | 0.072 | 7.61 |
文献[ | 0.553 | 0.076 | 7.28 |
本文方法 | 0.656 | 0.053 | 12.38 |
用户 | 组号 | 训练样本数 占比/% | 不同方法错误率/% | ||
---|---|---|---|---|---|
文献[ 方法 | 文献[ 方法 | 本文 方法 | |||
国家减灾中心 | 1 | 10 | 19.8 | 14.0 | 10.0 |
2 | 20 | 17.6 | 9.0 | 11.4 | |
3 | 50 | 11.0 | 5.4 | 7.4 | |
4 | 100 | 6.8 | 4.0 | 3.2 | |
生态环境部 卫星环境 应用中心 | 1 | 10 | 13.6 | 17.0 | 11.6 |
2 | 20 | 11.6 | 14.8 | 9.4 | |
3 | 50 | 6.4 | 9.8 | 9.2 | |
4 | 100 | 5.4 | 5.2 | 4.2 | |
中国交通通信 信息中心 | 1 | 10 | 17.8 | 19.2 | 13.6 |
2 | 20 | 14.0 | 14.4 | 13.4 | |
3 | 50 | 6.8 | 8.4 | 9.2 | |
4 | 100 | 6.5 | 4.6 | 4.0 |
Tab. 7 Comparison of recommendation error rate among different methods
用户 | 组号 | 训练样本数 占比/% | 不同方法错误率/% | ||
---|---|---|---|---|---|
文献[ 方法 | 文献[ 方法 | 本文 方法 | |||
国家减灾中心 | 1 | 10 | 19.8 | 14.0 | 10.0 |
2 | 20 | 17.6 | 9.0 | 11.4 | |
3 | 50 | 11.0 | 5.4 | 7.4 | |
4 | 100 | 6.8 | 4.0 | 3.2 | |
生态环境部 卫星环境 应用中心 | 1 | 10 | 13.6 | 17.0 | 11.6 |
2 | 20 | 11.6 | 14.8 | 9.4 | |
3 | 50 | 6.4 | 9.8 | 9.2 | |
4 | 100 | 5.4 | 5.2 | 4.2 | |
中国交通通信 信息中心 | 1 | 10 | 17.8 | 19.2 | 13.6 |
2 | 20 | 14.0 | 14.4 | 13.4 | |
3 | 50 | 6.8 | 8.4 | 9.2 | |
4 | 100 | 6.5 | 4.6 | 4.0 |
1 | 王密,杨芳. 智能遥感卫星与遥感影像实时服务[J]. 测绘学报, 2019, 48(12): 1586-1594. |
WANG M, YANG F. Intelligent remote sensing satellite and remote sensing image real-time service[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(12): 1586-1594. | |
2 | 李德仁, 沈欣. 我国天基信息实时智能服务系统发展战略研究[J]. 中国工程科学, 2020, 22(2): 138-143. 10.15302/j-sscae-2020.02.017 |
LI D R, SHEN X. Research on the development strategy of real-time and intelligent space-based information service system in China [J]. Strategic Study of CAE, 2020, 22(2): 138-143. 10.15302/j-sscae-2020.02.017 | |
3 | 程滔. 大数据时代遥感数据管理与服务模式探索[J]. 国土资源遥感, 2016, 28(4): 202-206. 10.6046/gtzyyg.2016.04.31 |
CHENG T. Exploring management and service mode for remote sensing data in big data era [J]. Remote Sensing for Land and Resources, 2016, 28(4): 202-206. 10.6046/gtzyyg.2016.04.31 | |
4 | 成鹏飞, 黄钰譞, 刘正,等. 电子商务平台大数据个性化推荐方法研究[J]. 商学研究, 2021, 28(3): 116-124. 10.3969/j.issn.1008-2107.2021.03.012 |
CHENG P F, HUANG Y X, LIU Z, et al. Research on personalized recommendation method of big data on E-commerce platform [J]. Commercial Science Research, 2021, 28(3): 116-124. 10.3969/j.issn.1008-2107.2021.03.012 | |
5 | 韦二龙,刘东,龙恩,等.基于用户画像的遥感信息精准服务系统设计[J]. 无线电工程,2021,51(8):720-724. 10.3969/j.issn.1003-3106.2021.08.007 |
WEI E L, LIU D, LONG E, et al. Design of precision service system based on user portrait for remote sensing information [J]. Radio Engineering, 2021,51(8): 720-724. 10.3969/j.issn.1003-3106.2021.08.007 | |
6 | 杨晓霞,徐婷,李少达,等.用户模型驱动的遥感信息智能服务方法[J].测绘学报,2015,44(11):1285-1294. 10.11947/j.AGCS.2015.20140413 |
YANG X X, XU T, LI S D, et al. A user profile-driven intelligent service of remote sensing information [J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(11):1285-1294. 10.11947/j.AGCS.2015.20140413 | |
7 | 龙恩, 吕守业, 岑鹏瑞,等. 顾及用户画像的多源遥感信息智能推荐方法[J]. 测绘学报, 2023, 52(2): 297-306. |
LONG E, LÜ S Y, CEN P R, et al. An intelligent recommendation method of multi-source remote sensing information considering user portrait [J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(2): 297-306. | |
8 | ZHU X X, TUIA D, MOU L, et al. Deep learning in remote sensing: a comprehensive review and list of resources [J]. IEEE Geoscience and Remote Sensing Magazine, 2017, 5(4): 8-36. 10.1109/mgrs.2017.2762307 |
9 | LU X, WANG B, ZHENG X, et al. Exploring models and data for remote sensing image caption generation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(4): 2183-2195. 10.1109/tgrs.2017.2776321 |
10 | CHENG Q, HUANG H, XU Y, et al. NWPU-Captions dataset and MLCA-Net for remote sensing image captioning [J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5629419. 10.1109/tgrs.2022.3201474 |
11 | ZHAN Y, XIONG Z T, YUAN Y. RSVG: exploring data and models for visual grounding on remote sensing data [EB/OL]. [2023-02-11]. . 10.1109/tgrs.2023.3250471 |
12 | 冯号, 黄朝兵, 文元桥. 基于改进YOLOv3的遥感图像小目标检测[J]. 计算机应用, 2022, 42(12):3723-3732. |
FENG H, HUANG C B, WEN Y Q. Remote sensing image small target detection based on improved YOLOv3 [J]. Journal of Computer Applications, 2022, 42(12): 3723-3732. | |
13 | AHMED M, SERAJ R, ISLAM S M S. The k-means algorithm: a comprehensive survey and performance evaluation [J]. Electronics, 2020, 9(8): 1295. 10.3390/electronics9081295 |
14 | XU S, WANG X, LV W, et al. PP-YOLOE: an evolved version of YOLO [EB/OL]. [2023-02-13]. . |
15 | CHAROU E, KABASSI K, MARTINIS A, et al. Integrating multimedia GIS technologies in a recommendation system for geotourism [C]// Proceedings of the 2010 Conference on Multimedia Services in Intelligent Environments: Smart Innovation, Systems and Technologies. Berlin: Springer, 2010: 63-74. 10.1007/978-3-642-13396-1_3 |
16 | SONG X, GUO Y, CHANG Y, et al. A hybrid recommendation system for marine science observation data based on content and literature filtering [J]. Sensors, 2020, 20(22): 6414. 10.3390/s20226414 |
17 | CHEN X, LIU Y, LI F, et al. Remote sensing image recommendation based on spatial-temporal embedding topic model[J]. Computers & Geosciences, 2021, 157: 104935. 10.1016/j.cageo.2021.104935 |
18 | 中国电子科技集团公司第五十四研究所. 一种基于多属性融合的遥感影像推荐方法:CN202011037613.4[P]. 2021-11-09. |
The 54th Research Institute of China Electronics Technology Group Corporation. A remote sensing image recommendation method based on multi-attribute fusion: CN202011037613.4[P]. 2021-11-09. | |
19 | 北京数慧时空信息技术有限公司. 基于强化学习的遥感影像推荐系统及方法: CN202210953208.X [P]. 2022-11-01. |
Beijing Shuhui Shikong Information Technology Company Limited. Remote sensing image recommendation system and method based on reinforcement learning: CN202210953208.X [P]. 2022-11-01. | |
20 | DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2005, 1: 886-893. 10.1109/cvpr.2005.4 |
21 | LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60: 91-110. 10.1023/b:visi.0000029664.99615.94 |
22 | 郭正胜,李参海. 基于深度学习的遥感图像匹配方法[J]. 测绘与空间地理信息, 2019,42(1):138-141,146. 10.3969/j.issn.1672-5867.2019.01.038 |
GUO Z S, LI C H. Deep learning based remote sensing image matching method[J]. Mapping and Spatial Geographic Information, 2019, 42(1): 138-141,146. 10.3969/j.issn.1672-5867.2019.01.038 | |
23 | REDMON J, FARHADI A. YOLOv3: an incremental improvement [EB/OL]. [2022-12-14]. . 10.1109/cvpr.2017.690 |
24 | REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2015: 91-99. |
25 | LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multiBox detector [C]// Proceedings of the 14th European Conference on Computer Vision. Cham: Springer, 2016: 21-37. 10.1007/978-3-319-46448-0_2 |
26 | REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6517-6525. 10.1109/cvpr.2017.690 |
27 | BOCHKOVSKIY A, WANG C-Y, LIAO H-Y M. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. [2022-09-15]. . |
28 | Ultralytics. YOLOv5: state-of-the-art object detection model — YOLOv5 in PyTorch [EB/OL]. [2022-12-07]. . |
29 | HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3 [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1314-1324. 10.1109/iccv.2019.00140 |
30 | LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768. 10.1109/cvpr.2018.00913 |
31 | LIN T-Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944. 10.1109/cvpr.2017.106 |
32 | HU J, SHEN L, SUN G. Squeeze-and-excitation networks [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141. 10.1109/cvpr.2018.00745 |
33 | PADDLEPADDLE. PaddleDetection: object detection and instance segmentation toolkit based on PaddlePaddle [EB/OL]. [2022-11-22]. . |
34 | DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database [C]// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2009: 248-255. 10.1109/cvpr.2009.5206848 |
35 | DING J, XUE N, XIA G-S, et al. Object detection in aerial images: a large-scale benchmark and challenges [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7778-7796. 10.1109/tpami.2021.3117983 |
36 | LIU S, HUANG D, WANG Y. Receptive field block net for accurate and fast object detection [C]// Proceedings of the 15th European Conference on Computer Vision. Cham: Springer, 2018: 404-419. 10.1007/978-3-030-01252-6_24 |
37 | TAN M, PANG R, LE Q V. EfficientDet: scalable and efficient object detection [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10778-10787. 10.1109/cvpr42600.2020.01079 |
38 | GE Z, LIU S, WANG F, et al. YOLOX: exceeding yolo series in 2021 [EB/OL]. [2023-01-13]. . |
39 | LIN T-Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection [C]// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007. 10.1109/iccv.2017.324 |
[1] | Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969. |
[2] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[3] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[4] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[5] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[6] | Yingjun ZHANG, Niuniu LI, Binhong XIE, Rui ZHANG, Wangdong LU. Semi-supervised object detection framework guided by curriculum learning [J]. Journal of Computer Applications, 2024, 44(8): 2326-2333. |
[7] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[8] | Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625. |
[9] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[10] | Yeheng LI, Guangsheng LUO, Qianmin SU. Logo detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2024, 44(8): 2580-2587. |
[11] | Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318. |
[12] | Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199. |
[13] | Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215. |
[14] | Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263. |
[15] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||