Interested Small Target Detection Method Based on Improved SSD for Synthetic Aperture Sonar Image

被引：0

作者：

Li B.-Q. ^{[1
,2
]}

Huang H.-N. ^{[1
,2
,3
]}

Liu J.-Y. ^{[1
,2
]}

Liu Z.-J. ^{[1
,2
]}

Wei L.-Z. ^{[1
,2
,3
]}

机构：

[1] Institute of Acoustics, Chinese Academy of Sciences, Beijing

[2] Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing, Chinese Academy of Sciences, Beijing

[3] University of Chinese Academy of Sciences, Beijing

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2024年 / 52卷 / 03期

基金：

中国国家自然科学基金;

关键词：

attention mechanism; efficient object detection model; interested small target detection; secondary non maximum suppression; synthetic aperture sonar;

D O I：

10.12263/DZXB.20220925

中图分类号：

学科分类号：

摘要：

The efficient object detection model SSD-MV3 (Single Shot Detection-MobileNet V3) cannot directly detect the interested small targets in high-resolution SAS (Synthetic Aperture Sonar) images due to the input image size limit. To this end, this paper proposes a novel object detection method, HRSSD (High Resolution Single Shot Detection), which ensures the specification of SSD-MV3 input image size and the integrity of the interested small targets through redundant cutting algorithm, and guarantees the unique detection result by using secondary non-maximum suppression. Furthermore, an improved feature block with a combination of scale, space and channel attention mechanism is proposed, and the basic network and additional feature network of SSD-MV3 are redesigned as SSD-MV3P (Single Shot Detection-MobileNet V3 Pro). Thus, SSD-MV3P can more effectively perceive the feature information of interested small targets. The experimental results show that the mAP (mean Average Precision) of SSD-MV3P is 4.39% higher than that of SSD-MV3 on the interested small target detection dataset SST (Sonar Small Target). HRSSD realizes the detection of the interested small targets in high-resolution SAS images, and ensures the integrity and uniqueness of the detection result at the same location. © 2024 Chinese Institute of Electronics. All rights reserved.

引用

页码：762 / 771

页数：9

共 30 条

[1]

HAYES M P, GOUGH P T., Synthetic aperture sonar: A review of current status, IEEE Journal of Oceanic Engineering, 34, 3, pp. 207-224, (2009)

[2]

SYNNES S A V, HANSEN R E, SAEBO T O., Spatial coherence of speckle for repeat-pass synthetic aperture sonar micronavigation, IEEE Journal of Oceanic Engineering, 46, 4, pp. 1330-1345, (2021)

[3]

THOMAS B, HUNTER A, DUGELAY S., Phase wrap error correction by random sample consensus with application to synthetic aperture sonar micronavigation, IEEE Journal of Oceanic Engineering, 46, 1, pp. 221-235, (2021)

[4]

BROWN D C, GERG I D, BLANFORD T E., Interpolation kernels for synthetic aperture sonar along-track motion estimation, IEEE Journal of Oceanic Engineering, 45, 4, pp. 1497-1505, (2020)

[5]

FEI T, KRAUS D, ZOUBIR A M., Contributions to automatic target recognition systems for underwater mine classification, IEEE Transactions on Geoscience and Remote Sensing, 53, 1, pp. 505-518, (2015)

[6]

WILLIAMS D P., Fast target detection in synthetic aperture sonar imagery: A new algorithm and large-scale performance analysis, IEEE Journal of Oceanic Engineering, 40, 1, pp. 71-92, (2015)

[7]

WANG L, LI M H, YE X F, Et al., Specific target recognition and segmentation algorithm for real-time side scan sonar images, 2015 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 2649-2653, (2015)

[8]

FANDOS R, ZOUBIR A M., Optimal feature set for automatic detection and classification of underwater objects in SAS images, IEEE Journal of Selected Topics in Signal Processing, 5, 3, pp. 454-468, (2011)

[9]

LECUN Y, BENGIO Y, HINTON G., Deep learning, Nature, 521, 7553, pp. 436-444, (2015)

[10]

KWOK R., Deep learning Powers a motion-tracking revolution, Nature, 574, 7776, pp. 137-138, (2019)

← 1 2 3 →