基于YOLOv5的光学遥感图像舰船目标检测算法

doi:10.12305/j.issn.1001-506X.2023.05.02

Abstract

Abstract:

When applied to the ship target detection task of optical remote sensing images, you only look once (YOLO)v5 algorithm suffered false positive and false negative a lot on small targets. An improved method based on YOLOv5 is proposed to deal with this situation. Firstly, a module named semantic information enhancement module aiming at extracting shallow features with more semantic information is designed and added into the path aggregation network, so as to enhance the expression ability of small target features. Then, the Swish function is used as the activation function to improve the network's ability to characterize the nonlinear characteristics of the data and accelerate the convergence speed of the model. Finally, according to the size characteristics of the ship, the large target detection head is removed to reduce the amount of inference calculation and optimize the effect of the detection end. The experiment on the test set shows that compared with the method before the improvement, the proposed method improves the detection accuracy by 5.2% and the inference time is reduced. At the same time of ensuring the real-time detection, the small target discrimination ability of the model is increased.

Key words: optical remote sensing image, ship target detection, YOLO(you only look once)v5, semantic information enhancement, activation function

CLC Number:

TP391.4

Qian CHENG, Jia LI, Juan DU. Ship target detection algorithm of optical remote sensing image based on YOLOv5[J]. Systems Engineering and Electronics, 2023, 45(5): 1270-1276.

Figures/Tables 7

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Fig.5

Fig.6

References 30

1	DONG Z , LIN B J . Learning a robust CNN-based rotation insensitive model for ship detection in VHR remote sensing ima-ges[J]. International Journal of Remote Sensing, 2020, 41 (9): 3614- 3626. doi: 10.1080/01431161.2019.1706781
2	ZHU C R , ZHOU H , WANG R S , et al. A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features[J]. IEEE Trans.on Geoscience and Remote Sensing, 2010, 48 (9): 3446- 3456. doi: 10.1109/TGRS.2010.2046330
3	董超. 可见光遥感图像海面舰船目标检测技术研究[D]. 长春: 中国科学院长春光学精密机械与物理研究所, 2020.
	DONG C. Research on the detection of ship targets on the sea surface in optical remote sensing image[D]. Changchun: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, 2020.
4	王保云, 张荣, 袁圆, 等. 可见光遥感图像中舰船目标检测的多阶阈值分割方法[J]. 中国科学技术大学学报, 2011, 41 (4): 293- 298.
	WANG B Y , ZHANG R , YUAN Y , et al. A new multi-level threshold segmentation method for ship targets detection in optical remote sensing images[J]. Journal of University of Science and Technology of China, 2011, 41 (4): 293- 298.
5	GAN L, LIU P, WANG L Z. Rotation sliding window of the HOG feature in remote sensing images for ship detection[C]//Proc. of the International Symposium on Computational Intelligence and Design, 2015: 401-404.
6	TAYARA H , CHONG K T . Object detection in very high-resolution aerial images using one-stage densely connected feature pyramid network[J]. Sensors, 2018, 18 (10): 3341. doi: 10.3390/s18103341
7	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proc. of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition, 2014: 580-587.
8	GIRSHICK R. Fast R-CNN[C]//Proc. of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition, 2015: 1440-1448.
9	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
10	HE K M , GKIOXARI G , DOLLAR P , et al. Mask R-CNN[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 386- 397. doi: 10.1109/TPAMI.2018.2844175
11	HE K M , ZHANG X Y , REN S Q , et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
12	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
13	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
14	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2021-11-21]. http://arxiv.org/abs/1804.02767.
15	BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2021-11-21]. https://arxiv.org/abs/2004.10934.
16	JOCHER G, STOKEN A, CHAURASIA A, et al. YOLOv5[EB/OL]. [2021-11-21]. http://github.com/ultralytics/yolov5.
17	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[M]//LEIBE B, MATAS J, SEBE N, et al. Lecture Notes in Computer Science, 2016.
18	FU C Y, LIU W, RANGA A, et al. DSSD: deconvolutional single shot detector[EB/OL]. [2021-11-21]. https://arxiv.org/abs/1701.06659.
19	XIAO D , SHAN F , LI Z , et al. A target detection model based on improved tiny-YOLOv3 under the environment of mining truck[J]. IEEE Access, 2019, 7, 123757- 123764. doi: 10.1109/ACCESS.2019.2928603
20	徐诚极, 王晓峰, 杨亚东. Attention-YOLO: 引入注意力机制的YOLO检测算法[J]. 计算机工程与应用, 2019, 55 (6): 13- 23.
	XU C J , WANG X F , YANG Y D . Attention-YOLO: YOLO detection algorithm that introduces attention mechanism[J]. Compu-ter Engineering and Applications, 2019, 55 (6): 13- 23.
21	郭进祥, 刘立波, 徐峰, 等. 基于YOLOv3的机场场面飞机检测方法[J]. 激光与光电子学进展, 2019, 56 (19): 111- 119.
	GUO J X , LIU L B , XU F , et al. Airport scene aircraft detection method based on YOLOv3[J]. Laser & Optoelectronics Progress, 2019, 56 (19): 111- 119.
22	GE Z, LIU S T, WANG F, et al. YOLOX: exceeding yolo series in 2021[EB/OL]. [2022-5-1]. http://arxiv.org/abs/2107.08430.
23	ZHANG S F, CHI C, YAO Y Q, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 9756-9765.
24	WANG C Y, MARKLIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020: 390-391.
25	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 8759-8769.
26	BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS-improving object detection with one line of code[C]//Proc. of the IEEE International Conference on Computer Vision, 2017: 5561-5569.
27	LIN T Y, DOLLAR P, GIRSHICK R, et al. Path aggregation network for instance segmentation[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 936-944.
28	PRAJIT R, BARRET Z, QUOC V, et al. Swish: a self-gated activation function[EB/OL]. [2021-11-21]. https://arxiv.org/abs/1710.05941v1.
29	KAGGLE. Dataset for airbus ship detection challenge[EB/OL]. [2021-11-21]. https://www.kaggle.com/c/airbus-ship-detection/data, 2018.
30	CHATTOPADHYAY A, SARKAR A, HOWLADER P, et al. Grad-CAM++: improved visual explanations for deep convolutional networks[C]//Proc. of the IEEE Winter Conference on Applications of Computer Vision, 2018: 839-847.

算法	P	R	AP_{_0.5}	时间/ms
YOLOv5s	79.91	73.65	79.19	15.4
YOLOv5s-SIEM	83.31	74.39	81.3	15.8
YOLOv5s-Swish	80.59	75.9	81.39	16.3
YOLOv5s-SS	85.09	77.96	83.64	15.9
YOLOv5s-SS-A	85.37	78.53	84.39	14.4

[1]	Chaofan PAN, Runsheng LI, Yan XU, Qing HU, Chaoyang NIU, Wei LIU. Ship detection of optical remote sensing images based on aware vectors [J]. Systems Engineering and Electronics, 2022, 44(12): 3631-3640.
[2]	Xiaoya JIA, Hongqiao WANG, Yadan YANG, Zhongma CUI, Bin XIONG. Anchor free SAR image ship target detection method based on the YOLO framework [J]. Systems Engineering and Electronics, 2022, 44(12): 3703-3709.

Ship target detection algorithm of optical remote sensing image based on YOLOv5

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 30

Related Articles 2

Recommended Articles

Metrics

Comments