改进PSPNet的炮弹火焰分割算法及应用

doi:10.3778/j.issn.1002-8331.2206-0092

摘要/Abstract

摘要： 针对目前靶场炮弹火焰图像分割算法对火焰边界分割效果差而导致定位精度下降的问题，基于PSPNet算法，结合双向特征融合模块以及全注意力机制网络的特征金字塔转换模块，提出改进PSPNet的炮弹火焰分割PSP_FPT（pyramid scene parsing_feature pyramid with Transformer）算法，实现对炮弹火焰目标的高精度分割。利用双向特征融合模块对金字塔池化后的特征进行双向融合，增强各子区域以及全局目标空间和语义特征的相关性，提升炮弹火焰分割的准确性。为了避免火焰周围烟雾、扬尘对分割效果的影响，将特征金字塔转换模块与全注意力机制网络相结合，优化双向特征融合模块输出后的特征映射，提升区域内目标之间的空间结构关系；提高算法对炮弹火焰目标与背景干扰之间的辨别力，进一步提高算法的识别能力。将全局池化后的特征作为全注意力机制网络的输入，解决了由于图像输入序列过长导致全注意力机制网络参数量过大的问题，进而降低工程应用的实现难度。实验结果表明，该算法在炮弹火焰数据集上分割的平均交并比达98.01%，平均准确率达98.97%，对炮弹火焰分割有较强的鲁棒性和较高的准确率。

关键词: 炮弹目标识别定位, 火焰高精度分割, 双向特征融合, 全注意力机制, 金字塔池化特征

Abstract: For the current target range artillery flame image segmentation algorithm, there is a problem of poor segmentation effect on the flame boundary, which leads to a decrease in positioning accuracy. This paper proposes PSP_FPT（pyramid scene parsing feature pyramid with Transformer） algorithm based on PSPNet and combined with bi-directional feature fusion module and feature pyramid transformation module of full attention mechanism network. This algorithm can achieve high-precision segmentation of artillery fire targets. Firstly, the bi-directional feature fusion module is used to bi-directionally fuse the features after pyramid pooling. It enhances the spatial and semantic relevance of each sub-region as well as the global target to improve the accuracy of artillery fire segmentation. Secondly, in order to avoid the influence of smoke and dust around the flame on the segmentation effect, it designs the feature pyramid conversion module. It is combined with the full-attention mechanism network, which is able to optimize the feature mapping. To be more specific, the module can pay more attention to the region of interest in feature extraction, and enhance the spatial structure relationship between targets in the region simultaneously. At the same time, it improves the algorithm’s discriminative power between the artillery flame target and the background interference. In addition, the features after global pooling are used as the input of the full attention mechanism network, which solves the problem that there are a amount of parameters caused by full attention mechanism network since the long image input sequence. Additionally, it reduces the implementation difficulty of engineering applications. The experimental results show that the mIOU and mAcc of the algorithm achieves 98.01% and 98.97% respectively for segmentation on the artillery flame dataset, and has strong robustness and high accuracy for artillery flame segmentation.

Key words: artillery shell target identification and localization, high accuracy flame segmentation, bi-directional feature fusion, full attention mechanism, pyramid pooling feature

张雯玮, 傅启凡, 王营冠, 傅衡成, 魏智, 丁华泽. 改进PSPNet的炮弹火焰分割算法及应用[J]. 计算机工程与应用, 2023, 59(23): 154-164.

ZHANG Wenwei, FU Qifan, WANG Yingguan, FU Hengcheng, WEI Zhi, DING Huaze. Improved PSPNet Artillery Flame Segmentation Algorithm and Applications[J]. Computer Engineering and Applications, 2023, 59(23): 154-164.

参考文献

[1] 屈秉男，蒋平，赵鲁阳，等.基于短基线传感器阵列的炮弹被动测向算法[J].航空学报，2022，43（3）：392-406.
QU B N，JIANG P，ZHAO L Y，et al.Passive direction finding algorithm of projectile based on short baseline sensor array[J].Acta Aeronauticaet Astronautica Sinica，2022，43（3）：392-406.
[2] 卢胜男，冯建利，段沛沛.视频火灾识别方法研究综述[J].电视技术，2013，37（3）：179-184.
LU S N，FENG J L，DUAN P P.Survey of fire recognition methods research based on video[J].Television Technology，2013，37（3）：179-184.
[3] TOULOUSE T，ROSSI L，AKHLOUFI M，et al.Benchmarking of wildland fire colour segmentation algorithms[J].IET Image Processing，2015，9（12）：1064-1072.
[4] 卢英，王慧琴，柴茜，等.基于多尺度LBP与GBP特征的火焰识别[J].计算机科学，2015，42（10）：316-320.
LU Y，WANG H Q，CHAI Q，et al.Fire image detection based on LBP and GBP features with multi-scales[J].Computer Science，2015，42（10）：316-320.
[5] 熊国良，苏兆熙，刘举平，等.火焰特性识别的 Matlab 实现方法[J].计算机工程与科学，2013，35（7）：131-136.
XIONG G L，SU Z X，LIU J P，et al.Matlab implementation of flame characterization[J].Computer Engineering and Science，2013，35（7）：131-136.
[6] HORNG W B，PENG J W，CHEN C Y.A new image-based real-time flame detection method using color analysis[C]//Proceedings 2005 IEEE Networking，Sensing and Control，2005：100-105.
[7] KO B C，CHEONG K H，NAM J Y.Fire detection based on vision sensor and support vector machines[J].Fire Safety Journal，2009，44（3）：322-329.
[8] 刘一方，刘兆广，王娅芳，等.一种基于定点DSP的YCbCr到HSV的快速转换算法[J].计算机应用研究，2012，29（2）：741-743.
LIU Y F，LIU Z G，WANG Y F，et al.Fast algorithm for YCbCr to HSV conversion based on fix-point DSP[J].Application Research of Computers，2012，29（2）：741-743.
[9] ZHAO H，SHI J，QI X，et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2881-2890.
[10] CHEN L C，PAPANDREOU G，KOKKINOS I，et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[J].arXiv：1412.7062，2014.
[11] CHEN L C，PAPANDREOU G，KOKKINOS I，et al.Deeplab：semantic image segmentation with deep convolutional nets，atrous convolution，and fully connected crfs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，40（4）：834-848.
[12] CHEN L C，PAPANDREOU G，SCHROFF F，et al.Rethinking atrous convolution for semantic image segmentation[J].arXiv：1706.05587，2017.
[13] CHEN L C，ZHU Y，PAPANDREOU G，et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：801-818.
[14] YUAN Y，CHEN X，WANG J.Object-contextual representations for semantic segmentation[C]//European Conference on Computer Vision.Cham：Springer，2020：173-190.
[15] ZHENG S，LU J，ZHAO H，et al.Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：6881-6890.
[16] XIE E，WANG W，YU Z，et al.SegFormer：simple and efficient design for semantic segmentation with transformers[C]//Advances in Neural Information Processing Systems，2021.
[17] KIRILLOV A，WU Y，HE K，et al.Pointrend：image segmentation as rendering[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：9799-9808.
[18] YU C，GAO C，WANG J，et al.Bisenet v2：bilateral network with guided aggregation for real-time semantic segmentation[J].International Journal of Computer Vision，2021，129（11）：3051-3068.
[19] BOCHKOV V S，KATAEVA L Y.WUUNet：advanced fully convolutional neural network for multiclass fire segmentation[J].Symmetry，2021，13（1）：98.
[20] CHOI H S，JEON M，SONG K，et al.Semantic fire segmentation model based on convolutional neural network for outdoor image[J].Fire Technology，2021，57（6）：3005-3019.
[21] 朱红，王海雷，张昊轩，等.基于深度学习的火焰分割模型对比研究[J].消防科学与技术，2022，41（1）：25-30.
ZHU H，WANG H L，ZHANG H X，et al.Comparative research on flame segmentation models based on deep learning[J].Fire Science and Technology，2022，41（1）：25-30.
[22] 谷世举，卜雄洙，靳建伟，等.基于改进Unet网络的炮口火焰分割方法[J].国外电子测量技术，2021，40（4）：16-21.
GU S J，BU X Z，JIN J W，et al.Muzzle flame segmentation method based on improved Unet network[J].Foreign Electronic Measurement Technology，2021，40（4）：16-21.
[23] RONNEBERGER O，FISCHER P，BROX T.U-net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham：Springer，2015：234-241.
[24] 宁阳，杜建超，韩硕，等.改进 DeeplabV3+的火焰分割与火情分析方法[J].西安电子科技大学学报，2021，48（5）：38-46.
NING Y，DU J C，HAN S，et al.Fire segmentation based on the improved DeeplabV3+ and the analytical method for fire development[J].Journal of Xidian University，2021，48（5）：38-46.
[25] 路茗，谭锦钢，张质懿，等.基于显著性目标检测的改进火焰检测算法[J].激光与光电子学进展，2022，59（4）：162-171.
LU M，TAN J G，ZHANG Z Y，et al.Improved flame detection algorithm based on salient target detection[J].Laser & Optoelectronics Progress，2022，59（4）：162-171.
[26] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems，2017.
[27] LIN T Y，DOLLáR P，GIRSHICK R，et al.Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2117-2125.