基于SSD的小目标检测改进算法

摘要/Abstract

摘要： 目标检测算法因数据存在分辨率较低、噪声等干扰，不能有效利用特征图中目标的边缘纹理和语义信息，导致小目标检测效果较差。为此，本文提出一种基于SSD的小目标检测改进算法。首先，采用普通卷积和深度可分离卷积进行同步特征学习并融合，获得信息丰富的浅层特征。然后，在固有的5个尺度的特征层后添加通道和空间自适应权重分配网络，使得模型更关注通道和空间的重要特征信息。最后，将候选目标框进行非极大抑制筛选得到检测结果。通过将改进的方法与Faster RCNN、SSD等方法在VOC2007数据集上测试结果进行比较，该方法降低了小目标的误检率，提升了整体目标的精度，所提模型mAP达到了78.94%，比SSD网络提高了3.13%。

关键词: 小目标检测, 深度可分离卷积, 多尺度, 权重分配网络, SSD模型

Abstract: Target detection algorithms cannot effectively use the edge texture and semantic information of small targets in the feature map due to low data resolution and noise interference, resulting in poor detection results. To solve this problem, this paper proposes an improved algorithm for small target detection based on SSD. Firstly, common convolution and deep separable convolution are used for synchronous feature learning and fusion, and the information-rich shallow features are obtained. Then the channel and space adaptive weight distribution network is added after the inherent 5 scale feature layer, so that the model pays more attention to the important feature information of the channel and space. Finally, the candidate target frame is subjected to non-maximum suppression screening to obtain the detection result. By comparing the improved method with Faster RCNN, SSD and other methods on the VOC2007 data set, the method reduces the false detection rate of small targets and improves the accuracy of the overall target. The proposed model mAP reaches 78.94%. It is 3.13% higher than the SSD model.

Key words: small target detection, depth separable convolution, multi-scale, weight distribution network, SSD

程凯强, 张旭, 寇旭鹏. 基于SSD的小目标检测改进算法[J]. 计算机与现代化, 2021, 0(07): 77-82.

CHENG Kai-qiang, ZHANG Xu, KOU Xu-peng. An Improved Algorithm for Small Target Detection Based on SSD[J]. Computer and Modernization, 2021, 0(07): 77-82.

参考文献［23］

［1］	刘树艺,李静,胡春,等. 基于卷积神经网络与集成学习的交通标志识别［J］. 计算机与现代化, 2019(12):67-71.
［2］	赵静,王弦,王奔,等. 基于神经网络的多类别目标识别［J］. 控制与决策, 2020,35(8):2037-2041.
［3］	曹燕,李欢,王天宝. 基于深度学习的目标检测算法研究综述［J］. 计算机与现代化, 2020(5):63-69.
［4］	张轶岳. 基于深度学习和域自适应的图像语义分割［D］. 成都:电子科技大学, 2020.
［5］	姜世浩,齐苏敏,王来花,等. 基于Mask R-CNN和多特征融合的实力分割［J］. 计算机技术与发展, 2020(9):65-70.
［6］	蒋纪威,何明祥,孙凯. 基于改进YOLOv3的人脸实时检测方法［J］. 计算机应用与软件, 2020,37(5):200-204.
［7］	冯媛,李敬兆. 改进的卷积神经网络行人检测方法［J］. 计算机工程与设计, 2020,41(5):1452-1457.
［8］	朱信熙,张尤赛. 基于HOG特征的实景交通标志检测［J］. 计算机与数字工程, 2020,48(5):1217-1221.
［9］	LIENHART R, KURANOV A, PISAREVSKY V. Empirical analysis of detection cascades of boosted classifiers for rapid object detection［C］// Proceedings of the 25th DAGM Symposium on Pattern Recognition. 2003:297-304.
［10］	IRANI M, PELEG S. Improving resolution by image registration［J］. CVGIP: Graphical Models and Image Processing, 1991,53(3):231-239.
［11］	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classifiation with deep convolutional neural networks［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012:1097-1105.
［12］	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［J］. arXiv preprint arXiv:1409.1556, 2014.
［13］	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions［C］// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015:1-9.
［14］	ZHONG Z L, LI J, LUO Z M, et al. Spectral-spatial residual network for hyperspectral image classification: A 3-D deep learning framework［J］. IEEE Transactions on Geoscience and Remote Sensing, 2018,56(2):847-858.
［15］	FANG B, LI Y, ZHAGN H K, et al. Hyperspectral images classification based on dense convolutional networks with spectral-wise attention mechanism［J］. Remote Sensing, 2019,11(2). DOI: 10.3390/rs11020159.
［16］	GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016,38:142-158.
［17］	REN S Q, HE K M, 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.
［18］	UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al. Selective search for object recognition［J］. International Journal of Computer Vision, 2013,104:154-171.
［19］	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unifies, real-time object detection［C］// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:779-788.
［20］	LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multiBox detector［C］// Proceedings of the European Conference on Computer Vision. 2016:21-37.
［21］	CHOLLET F. Xception: Deep learning with depthwise separable convolutions［C］// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017:1800-1807.
［22］	LIN M, CHEN Q, YAN S C. Network in network［C］// Proceedings of the IEEE International Conference on Learning Representations. 2014.
［23］	EVERINGHAM M, ESLAMI S M A, VAN GOOL L, et al. The Pascal visual object classes challenge: A retrospective［J］. International Journal of Computer Vision, 2015,111:98-136.

[1]	叶思佳, 魏延, 杜韩宇, 邓金枝. 结合注意力机制的HRNet图像语义分割算法[J]. 计算机与现代化, 2023, 0(10): 65-69.
[2]	刘昱杉, 刘卫康, 刘庆华, 者甜甜, 王家晨. 基于YOLOX结合DeepSort的船载车辆行人检测算法[J]. 计算机与现代化, 2023, 0(08): 60-67.
[3]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[4]	李国鑫, 曲寒冰, 朱成博, 王鑫轩, 胡嘉宝. 基于联合网络的域适应行人重识别算法[J]. 计算机与现代化, 2023, 0(06): 48-55.
[5]	王艺成, 张国良, 张自杰, . 基于改进YOLOv5的小目标检测方法[J]. 计算机与现代化, 2023, 0(05): 100-105.
[6]	朱理清, 李祥, . 改进YOLOv5算法的遥感图像车辆检测[J]. 计算机与现代化, 2023, 0(05): 117-121.
[7]	邱地发, 于淑芳, 刘锦辉, 毕梦昭. 基于YOLOv5s的遥感图像的车辆小目标检测[J]. 计算机与现代化, 2023, 0(05): 122-126.
[8]	尹相臣, 陈思龙, 李振凯, 张文进, 李桂青. 多尺度密集感受域的GAN图像去雾算法[J]. 计算机与现代化, 2023, 0(03): 11-15.
[9]	梁科晋, 张海军, 刘雅情, 张昱, 王月阳. 混合多尺度卷积结合双层LSTM语音情感识别[J]. 计算机与现代化, 2023, 0(01): 63-68.
[10]	蒋思清, 陈潇俊, 高豪俊, 何佳晋, 吴健, . 基于对抗域适应的心电信号深度学习分类算法[J]. 计算机与现代化, 2023, 0(01): 81-87.
[11]	彭露露, 朱媛媛, 金文倩, 王笑梅. 基于改进YOLOv4的汽车钢铁零件表面缺陷检测[J]. 计算机与现代化, 2022, 0(09): 32-39.
[12]	任朝宇, 赵冬娥, 张斌, 杨学峰, 褚文博. 基于多尺度CLG光流法的多目标检测方法[J]. 计算机与现代化, 2022, 0(04): 33-37.
[13]	梁正友, 耿经邦, 孙宇. 基于改进残差网络的交通标志识别算法[J]. 计算机与现代化, 2022, 0(04): 52-57.
[14]	金文倩, 彭露露, 朱媛媛, 王笑梅. 基于ECA-SSD模型的汽车零件缺陷检测[J]. 计算机与现代化, 2022, 0(03): 82-90.
[15]	陈中杰, 田建辉, 胡光初, 丁锋, 郭钊, 韩兴本. 基于特征识别的多尺度构件网格自动生成算法[J]. 计算机与现代化, 2022, 0(03): 91-97.