Object Detection Algorithm Based on Channel Separation Dual Attention Mechanism

doi:10.3778/j.issn.1673-9418.2109115

Abstract

Abstract: For the problems of low detection accuracy and high leakage rate of small targets in two-stage object detection algorithm, a target detection algorithm based on channel separation and dual attention mechanism is proposed to improve the detection accuracy of small targets by improving the Faster+FPN backbone network. Firstly, in response to the problem that neural networks can not automatically learn the importance between features, a dual-attention mechanism is proposed to build a deep neural network in the channel separation process, and other techniques such as group convolution and dilated convolution are combined to reduce network parameters. Secondly, to address the problem of information loss caused by high resolution features passing through a deep CNN, the detail extraction module and channel attention feature fusion module are added to extract more detailed features. Finally, considering that the general loss function cannot be focused on assessing the confidence level of the target’s location, the KL scatter is combined with the loss function optimization to make the prediction distribution closer to the real distribution through training, and the problems associated with the direct use of neural networks for object detection are effectively addressed. PASCAL VOC2007, KITTI and Pedestrian datasets are adopted to train the network, and the proposed model is compared with several object detection algorithms. Experimental results show that the proposed algorithm in this paper can recognize images efficiently and has high detection accuracy.

Key words: channel separation, dual attention mechanism, feature pyramid networks (FPN), KL divergence, object detection

摘要： 对于两阶段目标检测算法中模型存在检测精度低、小目标漏检率高等问题，提出通道分离双注意力机制的目标检测算法，通过改进Faster+FPN主干网络来提高小目标的检测精度。首先针对神经网络不能自动学习特征间的重要性问题，在通道分离过程中提出双注意力机制来构建深度神经网络，另结合分组卷积、空洞卷积等技术减少网络参数。其次针对高分辨率特征经过深度CNN后导致的信息丢失问题，通过添加细节提取模块以及通道注意力特征融合模块来提取更多的细节特征。最后考虑到一般损失函数不可重点评估目标物位置的置信度，结合KL散度进行损失函数优化，通过训练使得预测分布更接近真实分布，有效地解决了神经网络直接用于目标检测存在的问题。采用PASCAL VOC2007、KITTI以及Pedestrian三类数据集对网络进行训练，并将提出的模型与多个目标检测算法进行对比。实验结果表明，该算法能够高效地对图像进行识别，且具有较高的检测精度。

关键词: 通道分离, 双注意力机制, 特征金字塔网络（FPN）, KL散度, 目标检测

ZHAO Shan, ZHENG Ailing, LIU Zilu, GAO Yu. Object Detection Algorithm Based on Channel Separation Dual Attention Mechanism[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(5): 1112-1125.

赵珊, 郑爱玲, 刘子路, 高雨. 通道分离双注意力机制的目标检测算法[J]. 计算机科学与探索, 2023, 17(5): 1112-1125.

References

[1] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Jun 23-28, 2014. Washington: IEEE Computer Society, 2014: 580-587.
[2] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Jun 27-30, 2016. Washington: IEEE Computer Society, 2016: 779-788.
[3] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//LNCS 9905: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 21-37.
[4] DAI J, LI Y, HE K, et al. R-FCN: object detection via region- based fully convolutional networks[C]//Proceedings of the 29th Annual Conference on Neural Information Processing Systems, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 379-387.
[5] REN S, HE K, 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.
[6] 宋云博, 陈冬艳, 郝赟, 等. 基于级联卷积神经网络的高效目标检测方法[J]. 计算机工程与应用, 2021, 57(5): 139-145.
SONG Y B, CHEN D Y, HAO Y, et al. Efficient object detection method based on cascaded convolutional neural network[J]. Computer Engineering and Applications, 2021,57(5): 139-145.
[7] XU H, JIANG C H, LIANG X D, et al. Reasoning-RCNN: unifying adaptive global reasoning into large-scale object detection[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 6419-6428.
[8] WANG Y, CHEN Z, WU Q M J, et al. Deep mutual learning network for gait recognition[J]. Multimedia Tools and Applications, 2020, 79: 22653-22672.
[9] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Washington: IEEE Computer Society, 2018: 7132-7141.
[10] LI X, WANG W, HU X, et al. Selective kernel networks[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 15-20, 2019. Piscataway: IEEE, 2019: 510-519.
[11] 李文涛, 彭力. 多尺度通道注意力融合网络的小目标检测算法[J]. 计算机科学与探索, 2021, 15(12): 2390-2400.
LI W T, PENG L. Small objects detection algorithm with multi-scale channel attention fusion network[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(12): 2390-2400.
[12] 冀中, 孔乾坤, 王建. 一种双注意力模型引导的目标检测算法[J]. 激光与光电子学进展, 2020, 57(6): 115-122.
JI Z, KONG Q K, WANG J. Object detection algorithm guided by dual attention models[J]. Laser & Optoelectronics Progress, 2020, 57(6): 115-122.
[13] 陈维婧, 周萍, 杨海燕, 等. 通道-空间联合注意力机制的显著性检测模型[J]. 计算机工程与应用, 2021, 57(19): 214-219.
CHEN W J, ZHOU P, YANG H Y, et al. Salient detection model based on channel-spatial joint attention mechanism[J]. Computer Engineering and Applications, 2021, 57(19): 214-219.
[14] ZOU Z, LI C, ZHENG Y, et al. Two stages double attention convolutional neural network for crowd counting[J]. Multimedia Tools and Applications, 2020, 79(39): 29145-29159.
[15] HE Y H, ZHU C C, WANG J R, et al. Bounding box regression with uncertainty for accurate object detection[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 15-20, 2019. Piscataway: IEEE, 2019: 2888-2897.
[16] GIRSHICK R B. Fast R-CNN[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Dec 7-13, 2015. Washington: IEEE Computer Society, 2015: 1440-1448.
[17] LIN T Y, DOLLáR P, GIRSHICK R B, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 936-944.
[18] 陈飞, 章东平. 基于多尺度特征融合的Faster-RCNN道路目标检测[J]. 中国计量大学学报, 2018, 29(4): 393-397.
CHEN F, ZHANG D P. Road object detection based on multi-scale merged feature Faster-RCNN[J]. Journal of China University of Metrology, 2018, 29(4): 393-397.
[19] ZHAO X, ZHANG Y, ZHANG T, et al. Channel splitting network for single MR image super-resolution[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5649-5462.
[20] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//LNCS 11211: Proceedings of the 15th European Conference on Computer Vision, Munich, Sep 8-14, 2018. Cham: Springer, 2018: 3-19.
[21] FELZENSZWALB P F, GIRSHICK R, MCALLESTER D A. Cascade object detection with deformable part models[C]//Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, Jun 13-18, 2010. Washington: IEEE Computer Society, 2010: 2241-2248.
[22] WOO S, HWANG S, KWEON I S. StairNet: top-down semantic aggregation for accurate one shot detection[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, Mar 12-15, 2018. Piscataway: IEEE, 2018: 1093-1102.
[23] 陈彦如. 轻量级深度可分离混合卷积神经网络的目标检测算法[J]. 电子技术与软件工程, 2021(9): 156-159.
CHEN Y R. Lightweight deeply separable hybrid convolutional neural networks for target detection algorithms[J]. Electronic Technology and Software Engineering, 2021(9): 156-159.
[24] JUNEJO I N, AHMED N. A multi-branch separable convolution neural network for pedestrian attribute recognition[J]. Heliyon, 2020, 6(3): e03563.
[25] WOO S, HWANG S, JANG H D, et al. Gated bidirectional feature pyramid network for accurate one-shot detection[J]. Machine Vision and Applications, 2019, 30(4): 543-555.
[26] CHEN P Y, HSIEH J W, WANG C Y, et al. Residual bi-fusion feature pyramid network for accurate single-shot object detection[J]. arXiv:1911.12051, 2019.
[27] 吴天舒, 张志佳, 刘云鹏, 等. 基于改进SSD的轻量化小目标检测算法[J]. 红外与激光工程, 2018, 47(7): 37-43.
WU T S, ZHANG Z J, LIU Y P, et al. A lightweight small object detection algorithm based on improved SSD[J]. Infrared and Laser Engineering, 2018, 47(7): 37-43.
[28] 鞠默然, 罗江宁, 王仲博, 等. 融合注意力机制的多尺度目标检测算法[J]. 光学学报, 2020, 40(13): 126-134.
U M R, LUO J N, WANG Z B, et al. Multi-scale target detection algorithm fused with attention mechanism[J]. Acta Optica Sinica, 2020, 40(13): 126-134.
[29] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 6517-6525.