融入特征融合与特征增强的SSD目标检测

doi:10.3778/j.issn.1002-8331.2010-0171

摘要/Abstract

摘要： 针对SSD算法在目标检测过程中对小目标检测的不足，提出了一种基于SSD算法的一阶段目标检测器——FIENet（feature integration and feature enhancement network）。在FIENet中设计了两个模块，一是特征融合模块，该模块对SSD浅层的特征映射信息进行融合以提高小目标检测能力；二是特征增强模块，该模块采用了残差网络（Res2Net）以及注意力机制（attention），对特征融合后的模块以及SSD中的深层特征映射进行增强。为了更好地检测小目标，还调整了浅层特征映射先验框的数量。为了评价FIENet的有效性，在PASCAL VOC2007以及MSCOCO数据集上进行了实验。实验结果表明，在PASCAL VOC2007数据集上检测精度（mAP）较SSD提高3.1个百分点，对小目标bird、bottle、chair、plant检测精度分别提升了3.6、9.5、5.4、5.5个百分点。在COCO数据集上达到29.4%的检测精度（mAP）。实验结果证明FIENet网络在保持实时性的同时可以达到较高的检测精度。

关键词: 小目标, 特征融合, SSD, 特征增强

Abstract: A one-stage target detector based on SSD algorithm is proposed, named the FIENet（feature integration and feature enhancement network）, to solve the deficiency of said SSD algorithm in detecting small targets. Two blocks are designed in FIENet. One is a feature integration block, which fuses the feature mapping information in the shallow layer of SSD to improve the detection ability of small targets. The other is a feature enhancement block, which adopts the residual network（Res2Net） and the attention mechanism to enhance the feature integration block and the deep feature mapping in SSD. In order to better detect small targets, the number of prior boxes for shallow feature mapping is adjusted. In order to evaluate the effectiveness of FIENet, experiments are carried out on the PASCAL VOC2007 and MS COCO data sets. The experimental results show that the mean average precision（mAP） of the PASCAL VOC2007 data is 3.1?percentage points higher than that of SSD, and the detection accuracy of birds, bottles, chairs, and plants is 3.6, 9.5, 5.4, and 5.5?percentage points higher than that of SSD. Meanwhile, a mAP of 29.4% is achieved on the COCO data set. These results indicate that the FIENet can achieve high detection accuracy while maintaining real-time performance.

Key words: small target, feature integration, SSD, feature enhancement

刘建政, 梁鸿, 崔学荣, 钟敏, 李传秀. 融入特征融合与特征增强的SSD目标检测[J]. 计算机工程与应用, 2022, 58(11): 150-159.

LIU Jianzheng, LIANG Hong, CUI Xuerong, ZHONG Min, LI Chuanxiu. SSD Visual Target Detector Based on Feature Integration and Feature Enhancement[J]. Computer Engineering and Applications, 2022, 58(11): 150-159.

参考文献

[1] 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.
[2] FU C Y，LIN W，RANGA A，et al.DSSD：deconvolutional single shot detector[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2881-2890.
[3] SHEN，Z，LIU Z，LI J，et al.DSOD：learning deeply supervised object detectors from scratch[C]//Proceedings of the International Conference on Computer Vision，2017：1937-1945.
[4] JISOO J，HYOJIN P，NOJUN K.Enhancement of SSD by concatenating feature maps for object detection[J].arXiv：1705.09587，2017.
[5] LI Z，ZHOU F.FSSD：feature fusion single shot multibox detector[J].arXiv：1712.00960，2017.
[6] 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.
[7] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2014：580-587.
[8] HE K，ZHANG X，REN S，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2014，37（9）：1904-1916.
[9] HE K，GKIOXARI G，DOLLAR P，et al.Mask R-CNN[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2980-2988.
[10] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：1440-1448.
[11] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems，2017：1137-1139.
[12] DAI J F，LI Y，HE K M，et al.R-FCN：object detection via region-based fully convolutional networks[C]//Neural Information Processing Systems，2016：379-387.
[13] RAHMAN S，KHAN S，PORIKLI F.Zero-shot object detection：learning to simultaneously recognize and localize novel concepts[C]//Proceedings of the Asian Conference on Computer Vision（ACCV），2018：547-563.
[14] SINGH B，DAVIS L B.An analysis of scale invariance in object detection-SNIP[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017.
[15] CAO G M，XIE X M，YANG W Z.Feature-fused SSD：fast detection for small objects[C]//Ninth International Conference on Graphic and Image Processing，2018.
[16] LIN T Y，DOLLAR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：936-944.
[17] LIU S，HUANG D，WANG Y.Receptive field block net for accurate and fast object detection[C]//Proceedings of the European Conference on Computer Vision，2018：404-419.
[18] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：6517-6525.
[19] ZHANG X，ZOU J，HE K，et al.Accelerating very deep convolutional networks for classification and detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，38（10）：1943.
[20] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：770-778.
[21] LI W，LI H，WU Q，et al.Simultaneously detecting and counting dense vehicles from drone images[J].IEEE Transactions on Industrial Electronics，2019：9651-9662.
[22] GAO S，CHENG M M，ZHAO K，et al.Res2net：a new multi-scale backbone architecture[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2021，43（2）：652-662.
[23] BAHDANAU D，CHO K，BENGIO Y.Neural machine translation by jointly learning to align and translate[C]//Proceedings of the 3rd International Conference on Learning Representations，2015.
[24] Torralba A.Contextual priming for object detection[J].International Journal of Computer Vision，2003，53：169-191.
[25] HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018：7132-7141.
[26] MISRA D.Mish：a self regularized non-monotonic neural activation function[J].arXiv：1908.08681，2019.
[27] GLOROT X，BORDES A，BENGIO Y.Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics（AISTATS），2011：315-323.
[28] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the Computer Vision and Pattern Recognition（CVPR），2018：8759-8768.
[29] EVERINGHAM M，GOOL L，WILLIAMS C，et al.The PASCAL visual object classes（VOC） challenge[J].International Journal of Computer Vision，2010，88：303-338.
[30] LIN T，MAIRE M，BELONGIE S，et al.Microsoft COCO：common objects in context[C]//Proceedings of the European Conference on Computer Vision，Zurich，Swizterland，2014：740-755.
[31] HE K，ZHUANG X，REN S，et al.Delving deep into rectifiers：surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1026-1034.