|
|
论文:2020,Vol:38,Issue(4):747-754 |
|
|
引用本文： |
|
|
强伟, 贺昱曜, 郭玉锦, 李宝奇, 何灵蛟. 基于改进SSD的水下目标检测算法研究[J]. 西北工业大学学报 |
|
|
QIANG Wei, HE Yuyao, GUO Yujin, LI Baoqi, HE Lingjiao. Exploring Underwater Target Detection Algorithm Based on Improved SSD[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于改进SSD的水下目标检测算法研究 |
|
| 强伟1, 贺昱曜1, 郭玉锦2, 李宝奇3,4, 何灵蛟1 |
|
1. 西北工业大学 航海学院, 陕西 西安 710072;
2. 西安轻工业钟表研究所有限公司, 陕西 西安 710061;
3. 中国科学院 声学研究所, 北京 100190;
4. 中国科学院先进水下信息技术重点实验室, 北京 100190 |
| 摘要: |
| 随着人类对海洋的不断深入探索，准确、快速地检测水下环境中的鱼类、仿生体及其他智能体对完善水下防御体系显得越来越重要。针对水下复杂环境下目标检测准确率低、实时性差的问题，提出一种基于改进SSD的目标检测算法。该算法用ResNet卷积神经网络代替SSD的VGG卷积神经网络作为目标检测的基础网络，并在基础网络中利用所提出的深度分离可变形卷积模块进行特征提取，提高对水下复杂环境下目标检测的精度及速度。所提出的深度分离可变形卷积主要是在可变形卷积获取卷积核偏移量的过程中融合深度可分离卷积，以减少参数量来达到提升网络运行速度的目的，同时通过稀疏表示来提升网络的鲁棒性。实验结果显示，相比ResNet作为基础网络的SSD检测模型，利用深度分离可变形卷积改进的SSD检测模型检测水下目标的准确率提升了11个百分点，检测时间减少了3 ms，证明新算法的有效性。 |
| 关键词:
水下目标检测
SSD
深度可分离卷积
可变形卷积
|
|
| Exploring Underwater Target Detection Algorithm Based on Improved SSD |
|
| QIANG Wei1, HE Yuyao1, GUO Yujin2, LI Baoqi3,4, HE Lingjiao1 |
|
1. School of Marine engineering, Northwestern Polytechnical University, Xi'an 710072, China;
2. Xi'an Horological Research Institute or Light Industry Corporation Ltd., Xi'an 710061, China;
3. Institute of Acoustic, Chinese Academic of Sciences, Beijing 100190, China;
4. Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing, Beijing 100190, China |
| Abstract: |
| As the in-depth exploration of oceans continues, the accurate and rapid detection of fish, bionics and other intelligent bodies in an underwater environment is more and more important for improving an underwater defense system. Because of the low accuracy and poor real-time performance of target detection in the complex underwater environment, we propose a target detection algorithm based on the improved SSD. We use the ResNet convolution neural network instead of the VGG convolution neural network of the SSD as the basic network for target detection. In the basic network, the depthwise-separated deformable convolution module proposed in this paper is used to extract the features of an underwater target so as to improve the target detection accuracy and speed in the complex underwater environment. It mainly fuses the depthwise separable convolution when the deformable convolution acquires the offset of a convolution core, thus reducing the number of parameters and achieving the purposes of increasing the speed of the convolution neural network and enhancing its robustness through sparse representation. The experimental results show that, compared with the SSD detection model that uses the ResNet convolution neural network as the basic network, the improved SSD detection model that uses the depthwise-separated deformable convolution module improves the accuracy of underwater target detection by 11 percentage points and reduces the detection time by 3 ms, thus validating the effectiveness of the algorithm proposed in the paper. |
| Key words:
underwater target detection
SSD
depthwise-separated convolution
deformable convolutional
|
|
| 收稿日期: 2019-05-15
修回日期:
|
| DOI: 10.1051/jnwpu/20203840747 |
| 基金项目: 国家自然科学基金（61271143）资助 |
| 通讯作者:
Email： |
| 作者简介: 强伟(1986-),西北工业大学硕士研究生,主要从事深度学习、计算机视觉研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] CHANG R, WANG Y, HOU J, et al. Underwater Object Detection with Efficient Shadow-Removal for Side Scan Sonar Images[C]//Oceans, 2016:1-5
[2] FABIC J N, TURLA I E, CAPACILLO J A, et al. Fish Population Estimation and Species Classification from Underwater Video Sequences Using Blob Counting and Shape Analysis[C]//Underwater Technology Symposium, 2013:1-6
[3] OLIVER K, HOU W. Image Feature Detection and Matching in Underwater Conditions[C]//Proceeding of Society of Photo-Optical Instrumentation Engineers, 2010
[4] LI J, LIANG X, SHEN S M, et al. Scale-Aware Fast R-CNN for Pedestrian Detection[J]. IEEE Trans on Multimedia, 2018, 20(4):985-996
[5] PARKHI O M, VEDALDI A, ZISSERMAN A. Deep Face Recognition[C]//British Machine Vision Conference, 2015:1-12
[6] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs[J]. Computer Science, 2014(4):357-361
[7] WEIDEMANN A D, GRAY D J, ARNONE R A, et al. Comparison and Validation of Point Spread Models for Imaging in Natural Waters[J]. Optics Express, 2008, 16(13):9958-9965
[8] WANG S H, ZHAO J W, CHEN Y Q. Robust Tracking of Fish Schools Using CNN for Head Identification[J]. Multimedia Tools and Applications, 2017, 76(22):23679-23697
[9] DAI J, QI H, XIONG Y, et al. Deformable Convolutional Networks[C]//Proceedings of the IEEE International Conference on Computer Vision, 2017:764-773
[10] CHOLLET F. Xception:Deep Learning with Depthwise Separable Convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017:1251-1258
[11] HOWARD A G, ZHU M, CHEN B, et al. Mobilenets:Efficient Convolutional Neural Networks for Mobile Vision Applications[J/OL](2017-04-06)[2019-05-15]. http://arxiv.org/pdf/1704.04861.pdf
[12] LIU W, ANGUELOV D, ERHAN D, et al. SSD:Single Shot Multibox Detector[C]//European Conference on Computer Vision, 2016:21-37
[13] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once:Unified, Real-Time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788
[14] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Trans on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149
[15] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]//Conference on Computer Vision and Pattern Recognition, 2016:770-778 |
|
|
|
|
|
|
|
