Journal of Jilin University(Engineering and Technology Edition) ›› 2024, Vol. 54 ›› Issue (4): 1105-1113.doi: 10.13229/j.cnki.jdxbgxb.20220715

Previous Articles    

Omnidirectional accurate detection algorithm for dense small objects in remote sensing images

Yun-zuo ZHANG1,2(),Wei GUO1,Wen-bo LI1   

  1. 1.School of Information Science and Technology，Shijiazhuang Tiedao University，Shijiazhuang 050043，China
    2.Hebei Key Laboratory of Electromagnetic Environmental Effects and Information Processing，Shijiazhuang 050043，China
  • Received:2022-06-07 Online:2024-04-01 Published:2024-05-17

RICH HTML

 3   

PDF (PC)

303

Abstract:

Due to the dense arrangement and different directions of objects in remote sensing images， the existing detection algorithms are difficult to locate the instance objects accurately. Therefore， this paper proposed an omnidirectional accurate detection algorithm for dense small objects in remote sensing images. In order to improve the ability of feature extraction， the meta-ACON activation function was introduced into the residual structure of the backbone network to adaptively learn the importance of channel features. A new strengthen tconnection feature pyramid network was proposed. The lateral connection part for deep and shallow feature fusion was redesigned， and a jump connection was added between the input and output of the same level feature map to enrich the feature semantic information. The angle prediction branch was introduced， and the circular smooth label method was used to transform the angle regression problem into a classification problem. While realizing the rotation of the object frame， the problem of sudden change of the boundary of the rotation frame was solved. A post-processing method （Rotate-Soft-NMS） for rotation detection frame was designed to remove adjacent repeated rotation detection frames by suppressing the confidence of the detection frame. The experimental results on DOTA dataset show that the mAP of the proposed algorithm is 76.15%， which is 5.22% higher than the benchmark model YOLOv5m， and has achieved the best detection results compared with other advanced algorithms. The algorithm in this paper has achieved better detection results for complex remote sensing images.

Key words: computer application, remote sensing object detection, Meta-ACON activation function, strengthen connection feature pyramid network, angle prediction, rotation detection box

CLC Number: 

  • TP751.1

Fig.1

Algorithm network structure diagram"

Fig.2

FPN structure diagram"

Fig.3

SC-FPN structure diagram"

Fig.4

Schematic diagram of lateral connection structure of SC-FPN"

Fig.5

Definition method of rotation frame angle"

Fig.6

Schematic diagram of CSL"

Fig.7

Sample DOTA dataset"

Table 1

Ablation experiments of components on DOTA dataset"

模型激活函数CSLSC-FPN后处理mAP/%FPS/（帧·s-1）
√Leaky ReLU//R-NMS70.9329.52
√Meta-ACON//R-NMS71.6129.81
√Meta-ACON√/R-NMS73.8528.34
√Meta-ACON√√R-NMS75.5427.40
√Meta-ACON√√RS-NMS76.1527.76

Table 2

Comparison of detection performance under different window radius"

r0246
mAP/%70.1673.8572.3371.64

Table 3

Comparison of results of different algorithm models on DOTA test set"

模型mAP

PL

BD

BR

GTF

SV

LV

SH

TC

BC

ST

SBF

RA

HA

SP

HC
RRPN［5］61.01

88.52

71.20

31.66

59.30

51.85

56.19

57.25

90.81

72.84

67.38

56.69

52.84

53.08

51.94

53.58
RoI Transformer［7］69.56

88.64

78.52

43.44

75.92

68.81

73.68

83.59

90.74

77.27

81.46

58.39

53.54

62.83

58.93

47.67
R3Det［17］71.69

89.54

81.99

48.46

62.52

70.48

74.29

77.54

90.80

81.39

83.54

61.97

59.82

65.44

67.46

60.05
SCRDet［10］72.61

89.98

80.65

52.09

68.36

68.36

60.32

72.41

90.85

87.94

86.86

65.02

66.68

66.25

68.24

65.21
CFC-Net［18］73.50

89.08

80.41

52.41

70.02

76.28

78.11

87.21

90.89

84.47

85.64

60.51

61.52

67.82

68.02

50.09
APE［11］75.75

89.96

83.62

53.42

76.03

74.01

77.16

79.45

90.83

87.15

84.51

67.72

60.33

74.61

71.84

65.55
DODet［19］75.89

89.61

83.10

51.43

72.02

79.16

81.99

87.71

90.89

86.53

84.56

62.21

65.38

71.98

70.79

61.93
R2-FRCNN［20］76.02

89.10

81.22

54.47

72.97

79.99

82.28

87.64

90.54

87.31

86.33

54.20

68.18

76.12

70.83

59.19
本文76.15

91.24

83.92

55.53

68.12

79.32

83.48

88.41

89.56

85.22

85.85

61.16

64.85

73.58

69.14

62.85

Fig.8

DOTA dataset test results"

1 曲优, 李文辉. 基于锚框变换的单阶段旋转目标检测方法[J]. 吉林大学学报: 工学版, 2022, 52(1): 162-173.
Qu You, Li Wen-hui. Single-stage rotated object detection network based on anchor transformation[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 162-173.
2 韩金辉, 魏艳涛, 彭真明, 等. 红外弱小目标检测方法综述[J]. 红外与激光工程, 2022, 51(4): 438-461.
Han Jin-hui, Wei Yan-tao, Peng Zhen-ming, et al. Infrared dim and small target detection: a review[J]. Infrared and Laser Engineering, 2022, 51(4): 438-461.
3 Li K, Wan G, Cheng G, et al. Object detection in optical remote sensing images: a survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296-307.
4 董超, 刘晶红, 徐芳, 等. 光学遥感图像舰船目标快速检测方法[J]. 吉林大学学报: 工学版, 2019, 49(4): 1369-1376.
Dong Chao, Liu Jing-hong, Xu Fang, et al. Fast ship detection in optical remote sensing images[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1369-1376.
5 Nabati R, Qi H R. RRPN: radar region proposal network for object detection in autonomous vehicles[C]∥IEEE International Conference on Image Processing, Piscataway, USA, 2019: 3093-3097.
6 Liu Z K, Hu J G, Weng L B, et al. Rotated region based cnn for ship detection[C]∥IEEE International Conference on Image Processing, Piscataway, USA, 2017: 900-904.
7 Ding J, Xue N, Long Y, et al. Learning roi transformer for oriented object detection in aerial images[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2019: 2849-2858.
8 Long H, Chung Y, Liu Z B, et al. Object detection in aerial images using feature fusion deep networks[J]. IEEE Access, 2019, 7: 30980-30990.
9 Wang Y S, Zhang Y, Zhang Y, et al. SARD: Towards scale-aware rotated object detection in aerial imagery[J]. IEEE Access, 2019, 7: 173855-173865.
10 Yang X, Yang J R, Yan J C, et al. SCRDet: Towards more robust detection for small, cluttered and rotated objects[C]∥IEEE/CVF International Conference on Computer Vision, Piscataway, USA, 2019: 8232-8241.
11 Zhu Y X, Du J, Wu X Q. Adaptive period embedding for representing oriented objects in aerial images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(10): 7247-7257.
12 Chen L C, Liu C S, Chang F L, et al. Adaptive multi-level feature fusion and attention-based network for arbitrary-oriented object detection in remote sensing imagery[J]. Neurocomputing, 2021,451:67-80.
13 Qian W, Yang X, Peng S L, et al. Learning modulated loss for rotated object detection[C]∥The 35th AAAI Conference on Artificial Intelligence, Palo Alto,USA, 2021: 2458-2466.
14 Ma N N, Zhang X Y, Liu M, et al. Activate or not: Learning customized activation[C]∥IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA, 2021: 8032-8042.
15 Bodla N, Singh B, Chellappa R, et al. Soft-NMS --improving object detection with one line of code[C]∥IEEE International Conference on Computer Vision, Piscataway, USA, 2017: 5561-5569.
16 Xia G S, Bai X, Ding J, et al. DOTA: A large-scale dataset for object detection in aerial images[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, USA, 2018: 3974-3983.
17 Yang X, Yan J C, Feng T H. R3Det: Refined single-stage detector with feature refinement for rotating object[C]∥The 35th AAAI Conference on Artificial Intelligence. Palo Alto,USA, 2021: 3163-3171.
18 Ming Q, Miao L J, Zhou Z Q, et al. CFC-Net: A critical feature capturing network for arbitrary-oriented object detection in remote-sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: No.3095186.
19 Cheng G, Yao Y Q, Li S Y, et al. Dual-Aligned oriented detector[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: No.3149780.
20 朱煜, 方观寿, 郑兵兵, 等. 基于旋转框精细定位的遥感目标检测方法研究[J]. 自动化学报, 2023, 49(2): 415-424.
Zhu Yu, Fang Guan-shou, Zheng Bing-bing, et al. Research on detection method of refined rotated boxes in remote sensing[J]. Journal of Automatica Sinica, 2023, 49(2): 415-424.
[1] Li-ming LIANG,Long-song ZHOU,Jiang YIN,Xiao-qi SHENG. Fusion multi-scale Transformer skin lesion segmentation algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 1086-1098.
[2] Guang HUO,Da-wei LIN,Yuan-ning LIU,Xiao-dong ZHU,Meng YUAN,Di GAI. Lightweight iris segmentation model based on multiscale feature and attention mechanism [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2591-2600.
[3] Ying HE,Zhuo-ran WANG,Xu ZHOU,Yan-heng LIU. Point of interest recommendation algorithm integrating social geographical information based on weighted matrix factorization [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2632-2639.
[4] Yun-zuo ZHANG,Xu DONG,Zhao-quan CAI. Multi view gait cycle detection by fitting geometric features of lower limbs [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2611-2619.
[5] Ming-yao XIAO,Xiong-fei LI,Rui ZHU. Medical image fusion based on pixel correlation analysis in NSST domain [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(9): 2640-2648.
[6] Ya-hui ZHAO,Fei-yu LI,Rong-yi CUI,Guo-zhe JIN,Zhen-guo ZHANG,De LI,Xiao-feng JIN. Korean⁃Chinese translation quality estimation based on cross⁃lingual pretraining model [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(8): 2371-2379.
[7] Xiang-jiu CHE,Huan XU,Ming-yang PAN,Quan-le LIU. Two-stage learning algorithm for biomedical named entity recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(8): 2380-2387.
[8] Lian-ming WANG,Xin WU. Method for 3D motion parameter measurement based on pose estimation [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 2099-2108.
[9] Ze-qiang ZHANG,Wei LIANG,Meng-ke XIE,Hong-bin ZHENG. Elite differential evolution algorithm for mixed⁃model two⁃side disassembly line balancing problem [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1297-1304.
[10] Zhen-hai ZHANG,Kun JI,Jian-wu DANG. Crack identification method for bridge based on BCEM model [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1418-1426.
[11] Pei-yong LIU,Jie DONG,Luo-feng XIE,Yang-yang ZHU,Guo-fu YIN. Surface defect detection algorithm of magnetic tiles based on multi⁃branch convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1449-1457.
[12] Yu JIANG,Jia-zheng PAN,He-huai CHEN,Ling-zhi FU,Hong QI. Segmentation-based detector for traditional Chinese newspaper [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1146-1154.
[13] Peng YU,Yan PIAO. New method for extracting person re-identification attributes based on multi-scale features [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1155-1162.
[14] Hong-yang PAN,Zhao LIU,Bo YANG,Geng SUN,Yan-heng LIU. Overview of swarm intelligence methods for unmanned aerial vehicle systems based on new⁃generation information technology [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 629-642.
[15] Ying HE,Jun-song FAN,Wei WANG,Geng SUN,Yan-heng LIU. Joint optimization of secure communication and trajectory planning in unmanned aerial vehicle air⁃to⁃ground [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(3): 913-922.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd