《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (1): 292-300.DOI: 10.11772/j.issn.1001-9081.2024010125
收稿日期:
2024-02-05
修回日期:
2024-04-01
接受日期:
2024-04-07
发布日期:
2024-05-09
出版日期:
2025-01-10
通讯作者:
刘赏
作者简介:
周煜炜(1998—),女,天津人,硕士研究生,主要研究方向:图像处理、目标检测;基金资助:
Shang LIU1(), Yuwei ZHOU1, Rao DAI1, Linfang DONG1, Meng LIU2
Received:
2024-02-05
Revised:
2024-04-01
Accepted:
2024-04-07
Online:
2024-05-09
Published:
2025-01-10
Contact:
Shang LIU
About author:
ZHOU Yuwei, born in 1998, M. S. candidate. Her research interests include image processing, object detection.Supported by:
摘要:
对多尺度的遥感图像进行小目标检测时,基于深度学习的目标检测算法容易出现误检和漏检的情况。这是因为此类算法的特征提取模块进行了多次的下采样操作;而且未能根据不同类别、不同尺度的目标关注所需的上下文信息。为了解决该问题,提出一种融合注意力和上下文信息的遥感图像小目标检测算法ACM-YOLO(Attention-Context-Multiscale YOLO)。首先,应用细粒度的查询感知稀疏注意力以减少小目标特征信息的丢失,从而避免漏检;其次,设计局部上下文增强(LCE)函数以更好地关注不同类别的遥感目标所需的上下文信息,从而避免误检;最后,使用加权双向特征金字塔网络(BiFPN)强化特征融合模块对遥感图像小目标的多尺度特征融合能力,从而改善算法检测效果。在DOTA数据集和NWPU VHR-10数据集上进行对比实验和消融实验,以验证所提算法的有效性和泛化性。实验结果表明,在2个数据集上所提算法的平均精确率均值(mAP) 分别达到了77.33%和96.12%,而相较于YOLOv5算法,召回率分别提升了10.00和7.50个百分点。可见,所提算法能有效提升mAP和召回率,减少误检和漏检。
中图分类号:
刘赏, 周煜炜, 代娆, 董林芳, 刘猛. 融合注意力和上下文信息的遥感图像小目标检测算法[J]. 计算机应用, 2025, 45(1): 292-300.
Shang LIU, Yuwei ZHOU, Rao DAI, Linfang DONG, Meng LIU. Small target detection algorithm in remote sensing images integrating attention and contextual information[J]. Journal of Computer Applications, 2025, 45(1): 292-300.
LCE卷积核大小 | mAP/% | LCE卷积核大小 | mAP/% |
---|---|---|---|
5 | 94.43 | 33 | 95.24 |
15 | 94.48 | 35 | 95.37 |
20 | 95.05 | 40 | 95.14 |
30 | 95.16 |
表1 LCE不同卷积核大小的mAP结果
Tab. 1 mAP results of LCE with different kernel size
LCE卷积核大小 | mAP/% | LCE卷积核大小 | mAP/% |
---|---|---|---|
5 | 94.43 | 33 | 95.24 |
15 | 94.48 | 35 | 95.37 |
20 | 95.05 | 40 | 95.14 |
30 | 95.16 |
算法 | AP | mAP | |||
---|---|---|---|---|---|
船只 | 飞机 | 小型汽车 | 大型汽车 | ||
RetinaNet[ | 62.2 | 83.4 | 65.7 | 48.3 | 64.90 |
YOLO-CLD[ | 57.6 | 67.6 | 37.9 | 60.1 | 55.80 |
FMSSD[ | 76.9 | 89.1 | 69.2 | 73.6 | 77.20 |
RRPN[ | 47.2 | 83.9 | 34.7 | 49.7 | 53.88 |
Dai[ | 65.0 | 78.0 | 37.0 | 59.0 | 59.75 |
CSL[ | 64.9 | 84.2 | 67.6 | 51.5 | 67.05 |
Xiao[ | 66.5 | 85.7 | 69.2 | 54.2 | 68.90 |
YOLOv6[ | 71.0 | 58.5 | 23.2 | 37.9 | 47.65 |
YOLOv8 | 70.4 | 60.9 | 30.0 | 45.2 | 51.63 |
YOLOv5 | 78.7 | 78.7 | 54.2 | 60.3 | 67.98 |
ACM-YOLO | 85.4 | 89.2 | 60.3 | 74.4 | 77.33 |
表2 不同算法在DOTA数据集上的AP和mAP对比 ( %)
Tab. 2 Comparison of AP and mAP among different algorithms on DOTA dataset
算法 | AP | mAP | |||
---|---|---|---|---|---|
船只 | 飞机 | 小型汽车 | 大型汽车 | ||
RetinaNet[ | 62.2 | 83.4 | 65.7 | 48.3 | 64.90 |
YOLO-CLD[ | 57.6 | 67.6 | 37.9 | 60.1 | 55.80 |
FMSSD[ | 76.9 | 89.1 | 69.2 | 73.6 | 77.20 |
RRPN[ | 47.2 | 83.9 | 34.7 | 49.7 | 53.88 |
Dai[ | 65.0 | 78.0 | 37.0 | 59.0 | 59.75 |
CSL[ | 64.9 | 84.2 | 67.6 | 51.5 | 67.05 |
Xiao[ | 66.5 | 85.7 | 69.2 | 54.2 | 68.90 |
YOLOv6[ | 71.0 | 58.5 | 23.2 | 37.9 | 47.65 |
YOLOv8 | 70.4 | 60.9 | 30.0 | 45.2 | 51.63 |
YOLOv5 | 78.7 | 78.7 | 54.2 | 60.3 | 67.98 |
ACM-YOLO | 85.4 | 89.2 | 60.3 | 74.4 | 77.33 |
算法 | 精确率 | 召回率 | mAP |
---|---|---|---|
Faster-R CNN[ | 63.5 | 90.8 | 76.47 |
SSD[ | 92.3 | 78.2 | 74.12 |
Fan[ | — | — | 93.36 |
YOLOv3[ | 88.7 | 86.1 | 84.35 |
YOLOv4[ | 87.6 | 89.7 | 86.76 |
YOLOv6[ | 93.5 | 85.0 | 90.40 |
YOLOv8 | 93.9 | 84.8 | 90.90 |
YOLOv5 | 96.8 | 87.3 | 90.70 |
ACM-YOLO | 95.6 | 94.8 | 96.12 |
表3 不同算法在NWPU VHR-10数据集上的性能对比 ( %)
Tab. 3 Performance comparison of different algorithms on NWPU VHR-10 dataset
算法 | 精确率 | 召回率 | mAP |
---|---|---|---|
Faster-R CNN[ | 63.5 | 90.8 | 76.47 |
SSD[ | 92.3 | 78.2 | 74.12 |
Fan[ | — | — | 93.36 |
YOLOv3[ | 88.7 | 86.1 | 84.35 |
YOLOv4[ | 87.6 | 89.7 | 86.76 |
YOLOv6[ | 93.5 | 85.0 | 90.40 |
YOLOv8 | 93.9 | 84.8 | 90.90 |
YOLOv5 | 96.8 | 87.3 | 90.70 |
ACM-YOLO | 95.6 | 94.8 | 96.12 |
算法 | AP | mAP | 小目标mAP | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
飞机 | 船舰 | 储油罐 | 棒球场 | 网球场 | 篮球场 | 田径场 | 港口 | 桥梁 | 车辆 | |||
Faster-RCNN[ | 82.8 | 77.6 | 52.5 | 96.4 | 62.7 | 69.4 | 98.2 | 82.6 | 78.8 | 63.7 | 76.47 | 74.70 |
SSD[ | 90.3 | 72.5 | 60.3 | 87.5 | 58.9 | 65.2 | 90.3 | 80.5 | 77.9 | 57.8 | 74.12 | 73.53 |
Fan[ | 99.9 | 90.7 | 89.5 | 92.4 | 99.2 | 90.8 | 90.7 | 99.2 | 90.9 | 90.3 | 93.36 | 93.63 |
YOLOv3[ | 92.5 | 75.8 | 86.1 | 89.3 | 82.7 | 75.5 | 88.4 | 90.2 | 84.4 | 78.6 | 84.35 | 82.30 |
YOLOv4[ | 94.6 | 79.8 | 94.1 | 95.4 | 89.2 | 71.5 | 98.7 | 80.6 | 95.3 | 68.4 | 86.76 | 80.93 |
YOLOv6[ | 99.5 | 89.6 | 98.7 | 98.0 | 89.9 | 67.9 | 99.4 | 98.8 | 77.0 | 84.9 | 90.40 | 91.30 |
YOLOv8 | 99.4 | 89.2 | 99.0 | 98.4 | 89.8 | 68.2 | 99.4 | 97.5 | 80.1 | 87.7 | 90.90 | 92.10 |
YOLOv5 | 99.4 | 88.6 | 98.5 | 98.8 | 82.1 | 75.8 | 99.5 | 98.2 | 80.2 | 86.0 | 90.70 | 91.33 |
ACM-YOLO | 99.5 | 91.0 | 98.5 | 98.9 | 96.2 | 97.3 | 99.5 | 99.3 | 89.2 | 91.6 | 96.12 | 94.03 |
表4 不同算法在NWPU VHR-10数据集不同类别的AP和mAP对比 ( %)
Tab. 4 Comparison of AP and mAP among different algorithms in different categories on NWPU VHR-10 dataset
算法 | AP | mAP | 小目标mAP | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
飞机 | 船舰 | 储油罐 | 棒球场 | 网球场 | 篮球场 | 田径场 | 港口 | 桥梁 | 车辆 | |||
Faster-RCNN[ | 82.8 | 77.6 | 52.5 | 96.4 | 62.7 | 69.4 | 98.2 | 82.6 | 78.8 | 63.7 | 76.47 | 74.70 |
SSD[ | 90.3 | 72.5 | 60.3 | 87.5 | 58.9 | 65.2 | 90.3 | 80.5 | 77.9 | 57.8 | 74.12 | 73.53 |
Fan[ | 99.9 | 90.7 | 89.5 | 92.4 | 99.2 | 90.8 | 90.7 | 99.2 | 90.9 | 90.3 | 93.36 | 93.63 |
YOLOv3[ | 92.5 | 75.8 | 86.1 | 89.3 | 82.7 | 75.5 | 88.4 | 90.2 | 84.4 | 78.6 | 84.35 | 82.30 |
YOLOv4[ | 94.6 | 79.8 | 94.1 | 95.4 | 89.2 | 71.5 | 98.7 | 80.6 | 95.3 | 68.4 | 86.76 | 80.93 |
YOLOv6[ | 99.5 | 89.6 | 98.7 | 98.0 | 89.9 | 67.9 | 99.4 | 98.8 | 77.0 | 84.9 | 90.40 | 91.30 |
YOLOv8 | 99.4 | 89.2 | 99.0 | 98.4 | 89.8 | 68.2 | 99.4 | 97.5 | 80.1 | 87.7 | 90.90 | 92.10 |
YOLOv5 | 99.4 | 88.6 | 98.5 | 98.8 | 82.1 | 75.8 | 99.5 | 98.2 | 80.2 | 86.0 | 90.70 | 91.33 |
ACM-YOLO | 99.5 | 91.0 | 98.5 | 98.9 | 96.2 | 97.3 | 99.5 | 99.3 | 89.2 | 91.6 | 96.12 | 94.03 |
算法 | 精确率/% | 召回率/% | 权重模型大小/MB | 参数量/106 | GPU浮点运算数/GFLOPs | mAP/% |
---|---|---|---|---|---|---|
YOLOv5 | 77.8 | 64.5 | 14.5 | 7.05 | 15.9 | 67.98 |
YOLOv5_Attention&LCE | 81.1 | 72.7 | 15.2 | 7.38 | 275.3 | 76.69 |
YOLOv5_BiFPN | 80.7 | 74.3 | 14.7 | 7.11 | 16.1 | 77.00 |
ACM-YOLO | 80.9 | 74.5 | 15.2 | 7.38 | 275.3 | 77.33 |
表5 在DOTA数据集上的消融实验结果
Tab. 5 Ablation experimental results on DOTA dataset
算法 | 精确率/% | 召回率/% | 权重模型大小/MB | 参数量/106 | GPU浮点运算数/GFLOPs | mAP/% |
---|---|---|---|---|---|---|
YOLOv5 | 77.8 | 64.5 | 14.5 | 7.05 | 15.9 | 67.98 |
YOLOv5_Attention&LCE | 81.1 | 72.7 | 15.2 | 7.38 | 275.3 | 76.69 |
YOLOv5_BiFPN | 80.7 | 74.3 | 14.7 | 7.11 | 16.1 | 77.00 |
ACM-YOLO | 80.9 | 74.5 | 15.2 | 7.38 | 275.3 | 77.33 |
算法 | 精确率/% | 召回率/% | 权重模型大小/MB | 参数量/106 | GPU浮点运算数/GFLOPs | mAP/% |
---|---|---|---|---|---|---|
YOLOv5 | 96.8 | 87.3 | 14.5 | 7.04 | 15.8 | 90.70 |
YOLOv5_Attention&LCE | 95.5 | 93.7 | 15.0 | 7.30 | 275.1 | 95.56 |
YOLOv5_BiFPN | 96.8 | 92.3 | 14.6 | 7.10 | 16.0 | 94.47 |
ACM-YOLO | 95.6 | 94.8 | 15.2 | 7.37 | 275.3 | 96.12 |
表6 在NWPU VHR-10数据集上的消融实验结果
Tab. 6 Ablation experimental results on NWPU VHR-10 dataset
算法 | 精确率/% | 召回率/% | 权重模型大小/MB | 参数量/106 | GPU浮点运算数/GFLOPs | mAP/% |
---|---|---|---|---|---|---|
YOLOv5 | 96.8 | 87.3 | 14.5 | 7.04 | 15.8 | 90.70 |
YOLOv5_Attention&LCE | 95.5 | 93.7 | 15.0 | 7.30 | 275.1 | 95.56 |
YOLOv5_BiFPN | 96.8 | 92.3 | 14.6 | 7.10 | 16.0 | 94.47 |
ACM-YOLO | 95.6 | 94.8 | 15.2 | 7.37 | 275.3 | 96.12 |
1 | 李坤亚,欧鸥,刘广滨,等.改进YOLOv5的遥感图像目标检测算法[J].计算机工程与应用, 2023, 59(9): 207-214. |
LI K Y, OU O, LIU G B, et al. Target detection algorithm of remote sensing image based on improved YOLOv5 [J]. Computer Engineering and Applications, 2023, 59(9): 207-214. | |
2 | KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]// Proceedings of the 25th International Conference on Neural Information Processing Systems, Volume 1. Red Hook: Curran Associates Inc., 2012: 1097-1105. |
3 | GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587. |
4 | GIRSHICK R. Fast R-CNN [C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448. |
5 | REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. |
6 | LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector [C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9905. Cham: Springer, 2016: 21-37. |
7 | 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: 2999-300. |
8 | REDMON J, DIVVALA S K, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788. |
9 | 汪鹏,辛雪静,王利琴,等.基于YOLOv3的光学遥感图像目标检测算法[J].激光与光电子学进展, 2021, 58(20): No.2028006. |
WANG P, XIN X J, WANG L Q, et al. Object detection algorithm of optical remote sensing images based on YOLOv3 [J]. Laser and Optoelectronics Progress, 2021, 58(20): No.2028006. | |
10 | REDMON J, FARHADI A. YOLOv3: an incremental improvement [EB/OL]. [2023-12-10]. . |
11 | 林文龙,阿里甫·库尔班,陈一潇,等.面向遥感影像目标检测的ACFEM-RetinaNet算法[J].计算机工程与应用, 2024, 60(1): 245-253. |
LIN W L, ALIFU K, CHEN Y X, et al. ACFEM RetinaNet algorithm for remote sensing image target detection [J]. Computer Engineering and Applications, 2024, 60(1): 245-253. | |
12 | GONG H, MU T, LI Q, et al. Swin-transformer-enabled YOLOv5 with attention mechanism for small object detection on satellite images [J]. Remote Sensing, 2022, 14(12): No.2861. |
13 | 周华平,郭伟.改进YOLOv5网络在遥感图像目标检测中的应用[J].遥感信息, 2022, 37(5): 23-30. |
ZHOU H P, GUO W. Improved YOLOv5 network in application of remote sensing image object detection [J]. Remote Sensing Information, 2022, 37(5): 23-30. | |
14 | 李惠惠,范军芳,陈启丽.改进YOLOv5的遥感图像目标检测[J].弹箭与制导学报, 2022, 42(4): 17-23. |
LI H H, FAN J F, CHEN Q L. Improved YOLOv5 remote sensing image target detection [J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2022, 42(4): 17-23. | |
15 | 万羽欣.基于YOLO改进算法的遥感图像小目标检测方法研究[D].北京:北京交通大学, 2022: 72-72. |
WAN Y X. Research on small object detection method in remote sensing image based on improved YOLO algorithm [D]. Beijing: Beijing Jiaotong University, 2022: 72-72. | |
16 | WANG P, SUN X, DIAO W, et al. FMSSD: feature-merged single-shot detection for multiscale objects in large-scale remote sensing imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(5): 3377-3390. |
17 | SHAO J, YANG Q, LUO C, et al. Vessel detection from nighttime remote sensing imagery based on deep learning [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 12536-12544. |
18 | 赵文清,孔子旭,周震东,等.增强小目标特征的航空遥感目标检测[J].中国图象图形学报, 2021, 26(3): 644-653. |
ZHAO W Q, KONG Z X, ZHOU Z D, et al. Target detection algorithm of aerial remote sensing based on feature enhancement technology [J]. Journal of Image and Graphics, 2021, 26(3): 644-653. | |
19 | 范新南,严炜,史朋飞,等.多尺度深度特征融合网络的遥感图像目标检测[J].遥感学报, 2022, 26(11): 2292-2303. |
FAN X N, YAN W, SHI P F, et al. Remote sensing image target detection based on a multi-scale deep feature fusion network [J]. National Remote Sensing Bulletin, 2022, 26(11): 2292-2303. | |
20 | 王怀济,李广明,张红良,等.融合卷积通道注意力的遥感图像目标检测方法[J].计算机工程与应用, 2024, 60(2): 200-210. |
WANG H J, LI G M, ZHANG H L, et al. Rotating object detection method based on convolutional block channel attention in remote sensing images [J]. Computer Engineering and Applications, 2024, 60(2): 200-210. | |
21 | 赵文清,康怿瑾,赵振兵,等.改进YOLOv5s的遥感图像目标检测[J].智能系统学报, 2023, 18(1): 86-95. |
ZHAO W Q, KANG Y J, ZHAO Z B, et al. A remote sensing image object detection algorithm with improved YOLOv5s [J]. CAAI Transactions on Intelligent Systems, 2023, 18(1): 86-95. | |
22 | ZHU L, WANG X, KE Z, et al. BiFormer: vision transformer with bi-level routing attention [C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 10323-10333. |
23 | 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. |
24 | REN S, ZHOU D, HE S, et al. Shunted self-attention via multi-scale token aggregation [C]// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 10843-10852. |
25 | CHENG G, HAN J, ZHOU P, et al. Multi-class geospatial object detection and geographic image classification based on collection of part detectors [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98: 119-132. |
26 | 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. |
27 | 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. |
28 | 张朝阳,张上,王恒涛,等.多尺度下遥感小目标多头注意力检测[J].计算机工程与应用, 2023, 59(8): 227-238. |
ZHANG Z Y, ZHANG S, WANG H T, et al. Multi-head attention detection of small targets in remote sensing at multiple scales [J]. Computer Engineering and Applications, 2023, 59(8): 227-238. | |
29 | XIA G S, BAI X, DING J, et al. DOTA: a large-scale dataset for object detection in aerial images [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 3974-3983. |
30 | MA J, SHAO W, YE H, et al. Arbitrary-oriented scene text detection via rotation proposals [J]. IEEE Transactions on Multimedia, 2018, 20(11): 3111-3122. |
31 | 戴媛,易本顺,肖进胜,等.基于改进旋转区域生成网络的遥感图像目标检测[J].光学学报, 2020, 40(1): No.0111020. |
DAI Y, YI B S, XIAO J S, et al. Object detection of remote sensing image based on improved rotation region proposal network [J]. Acta Optica Sinica, 2020, 40(1): No.0111020. | |
32 | YANG X, YAN J. Arbitrary-oriented object detection with circular smooth label [C]// Proceedings of the 2020 European Conference on Computer Vision, LNCS 12353. Cham: Springer, 2020: 677-694. |
33 | 肖进胜,张舒豪,陈云华,等.双向特征融合与特征选择的遥感影像目标检测[J].电子学报, 2022, 50(2): 267-272. |
XIAO J S, ZHANG S H, CHEN Y H, et al. Remote sensing image object detection based on bidirectional feature fusion and feature selection [J]. Acta Electronica Sinica, 2022, 50(2): 267-272. | |
34 | LI C, LI L, JIANG H, et al. YOLOv6: a single-stage object detection framework for industrial applications [EB/OL]. [2023-03-03]. . |
35 | BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. [2023-02-20]. . |
[1] | 宋鹏程, 郭立君, 张荣. 利用局部-全局时间依赖的弱监督视频异常检测[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 240-246. |
[2] | 李烨恒, 罗光圣, 苏前敏. 基于改进YOLOv5的Logo检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2580-2587. |
[3] | 姬张建, 杜娜. 基于改进VariFocalNet的微小目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2200-2207. |
[4] | 刘越, 刘芳, 武奥运, 柴秋月, 王天笑. 基于自注意力机制与图卷积的3D目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1972-1977. |
[5] | 李鸿天, 史鑫昊, 潘卫国, 徐成, 徐冰心, 袁家政. 融合多尺度和注意力机制的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1437-1444. |
[6] | 吴宁, 罗杨洋, 许华杰. 基于多尺度特征融合的遥感图像语义分割方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 737-744. |
[7] | 蒋占军, 吴佰靖, 马龙, 廉敬. 多尺度特征和极化自注意力的Faster-RCNN水漂垃圾识别[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 938-944. |
[8] | 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. |
[9] | 王林, 刘景亮, 王无为. 基于空洞卷积融合Transformer的无人机图像小目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3595-3602. |
[10] | 李子怡, 曲婷婷, 崇乾鹏, 徐金东. 基于模糊多尺度特征的遥感图像分割网络[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3581-3586. |
[11] | 刘涛, 鞠事宏, 高一萌. 基于改进YOLOv8n的无人机视角下小目标检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3603-3609. |
[12] | 杨昊, 张轶. 基于上下文信息和多尺度融合重要性感知的特征金字塔网络算法[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2727-2734. |
[13] | 路琨婷, 费蓉蓉, 张选德. 融合卷积神经网络的遥感图像全色锐化[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2963-2969. |
[14] | 梁美佳, 刘昕武, 胡晓鹏. 基于改进YOLOv3的列车运行环境图像小目标检测算法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2611-2618. |
[15] | 郑帅, 张晓龙, 邓鹤, 任宏伟. 基于多尺度特征融合和网格注意力机制的三维肝脏影像分割方法[J]. 《计算机应用》唯一官方网站, 2023, 43(7): 2303-2310. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||