
浏览全部资源
扫码关注微信
辽宁科技大学 计算机与软件工程学院, 辽宁 鞍山 114051
[ "王雨夕,女,硕士研究生,2019年于辽宁科技大学获得学士学位,主要从事显著性目标检测方面的算法研究。E-mail: 2692769200@qq.com" ]
[ "徐杨,女,博士,教授,2012年于东北大学获得博士学位,主要从事计算机视觉及数字图像处理方面的研究。E-mail: xuyang@ustl.edu.cn" ]
收稿日期:2024-08-13,
修回日期:2024-09-10,
纸质出版日期:2025-04-05
移动端阅览
王雨夕, 徐杨, 袁旭祥. RGB深度图像显著性目标检测方法设计[J]. 液晶与显示, 2025,40(4):607-616.
WANG Yuxi, XU Yang, YUAN Xuxiang. Design of salience target detection method for RGB depth images[J]. Chinese journal of liquid crystals and displays, 2025, 40(4): 607-616.
王雨夕, 徐杨, 袁旭祥. RGB深度图像显著性目标检测方法设计[J]. 液晶与显示, 2025,40(4):607-616. DOI: 10.37188/CJLCD.2024-0230. CSTR: 32172.14.CJLCD.2024-0230.
WANG Yuxi, XU Yang, YUAN Xuxiang. Design of salience target detection method for RGB depth images[J]. Chinese journal of liquid crystals and displays, 2025, 40(4): 607-616. DOI: 10.37188/CJLCD.2024-0230. CSTR: 32172.14.CJLCD.2024-0230.
为了高效利用深度特征信息辅助显著性检测,实现对不同尺度特征信息的融合,本文提出了一种基于CDINet算法改进的RGB-D图像显著性目标检测算法。首先,添加了多尺度特征融合模块用来加强编码器和解码器之间特征信息的传输,有效减少浅层特征丢失,通过辅助解码器的跳跃连接获得更多的显著物体的特征信息。接着,在CDINet的网络结构尾部连接了一个循环注意力模块,通过使用面向记忆的场景理解功能,逐渐优化局部细节。最后,对损失函数进行调整,使用一致性增强损失(CEL)处理因为不同尺度特征融合产生的空间一致性等问题,并在不增加参数的情况下均匀突出显著区域。实验结果表明,改进后的模型与原CDINet算法模型相比,在LFSD数据集上的F-measure提高了0.6%,MAE下降了0.4%;在STERE数据集上的F-measure提高了0.4%,S-measure提升了0.5%。相对于其他算法模型,本模型基本满足检测性能更好、适应性更高等要求。
In order to efficiently use depth feature information to assist salient object detection, the fusion of different scale feature information is realized. In this paper, an improved salient object detection algorithm for RGB-D image saliency based on CDINet algorithm is proposed. Firstly, a multi-scale feature fusion module is added to enhance the transmission of feature information between encoder and decoder, so as to effectively reduce shallow feature loss, and obtain more feature information of salient objects through the jump connection of auxiliary decoder. Next, a circular attention module is connected at the tail of the CDINet’s network structure, which gradually optimizes local details by using memory-oriented scene understanding. Finally, the loss function is adjusted, and the consistency enhanced loss (CEL) is used to deal with the spatial consistency caused by the fusion of different scale features, and the salient areas are uniformly highlighted without increasing parameters. The experimental results show that compared with the original CDINet algorithm model, the improved model has an F-measure increase of 0.6% and a MAE decrease of 0.4% on LFSD data set, and an F-measure increase of 0.4% and a S-measure decrease of 0.5% on STERE data set. Compared with other algorithm models, this model basically meets the requirements of better detection performance and higher adaptability.
王健 . 基于RGB-D图像的显著目标检测方法研究 [D]. 南京 : 南京信息工程大学 , 2023 .
WANG J . Research on salient object detection based on RGB-D images [D]. Nanjing : Nanjing University of Information Science & Technology , 2023 . (in Chinese)
ACHINEK D N , SHEHU I S , ATHUMAN A M , et al . DAF-Net: dense attention feature pyramid network for multiscale object detection [J]. International Journal of Multimedia Information Retrieval , 2024 , 13 ( 2 ): 18 . doi: 10.1007/s13735-024-00323-x http://dx.doi.org/10.1007/s13735-024-00323-x
夏晨星 , 王晶晶 , 葛斌 . 基于互学习和促进分割的RGB-D显著性目标检测 [J]. 通化师范学院学报 , 2024 , 45 ( 6 ): 52 - 58 .
XIA C X , WANG J J , GE B . Mutual learning and boosting segmentation for RGB-D salient object detection [J]. Journal of Tonghua Normal University , 2024 , 45 ( 6 ): 52 - 58 . (in Chinese)
ZHANG C , CONG R M , LIN Q W , et al . Cross-modality discrepant interaction network for RGB-D salient object detection [C]// Proceedings of the 29th ACM International Conference on Multimedia . New York : ACM , 2021 : 2094 - 2102 . doi: 10.1145/3474085.3475364 http://dx.doi.org/10.1145/3474085.3475364
丛润民 , 杨宁 , 张晨 , 等 . 一种RGB-D图像显著性目标检测方法 : 中国 , CN202110872457.1 [P]. 2023-04-30 .
CONG R M , YANG N , ZHANG C , et al . RGB-D image saliency target detection method : CN , CN202110872457.1 [P]. 2023-07-30 . (in Chinese)
PANG Y W , ZHAO X Q , ZHANG L H , et al . Multi-scale interactive network for salient object detection [C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle : IEEE , 2020 : 9410 - 9419 . doi: 10.1109/cvpr42600.2020.00943 http://dx.doi.org/10.1109/cvpr42600.2020.00943
WOO S , PARK J , LEE J Y , et al . CBAM: convolutional block attention module [C]// Proceedings of the 15th European Conference on Computer Vision . Munich : Springer , 2018 : 3 - 19 . doi: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1
LI H , LIANG J Y , WU R Q , et al . Stereo superpixel segmentation via decoupled dynamic spatial-embedding fusion network [J]. IEEE Transactions on Multimedia , 2024 , 26 : 367 - 378 . doi: 10.1109/tmm.2023.3265843 http://dx.doi.org/10.1109/tmm.2023.3265843
PENG H , LI B , XIONG W H , et al . RGBD salient object detection: a benchmark and algorithms [C]// Proceedings of the 13th European Conference on Computer Vision . Zurich : Springer , 2014 : 92 - 109 . doi: 10.1007/978-3-319-10578-9_7 http://dx.doi.org/10.1007/978-3-319-10578-9_7
CHENG Y P , FU H Z , WEI X X , et al . Depth enhanced saliency detection method [C]// Proceedings of International Conference on Internet Multimedia Computing and Service . Xiamen : ACM , 2014 : 23 - 27 . doi: 10.1145/2632856.2632866 http://dx.doi.org/10.1145/2632856.2632866
WANG X X , WANG X , JIANG B , et al . MutualFormer: multi-modal representation learning via cross-diffusion attention [J]. International Journal of Computer Vision , 2024 , 132 ( 9 ): 3867 - 3888 . doi: 10.1007/s11263-024-02067-x http://dx.doi.org/10.1007/s11263-024-02067-x
ZHOU T , FAN D P , CHENG M M , et al . RGB-D salient object detection: a survey [J]. Computational Visual Media , 2021 , 7 : 37 - 69 . doi: 10.1007/s41095-020-0199-z http://dx.doi.org/10.1007/s41095-020-0199-z
ZHANG D D , WANG C P , FU Q . A new benchmark for camouflaged object detection: RGB-D camouflaged object detection dataset [J]. Open Physics , 2024 , 22 ( 1 ): 20240060 . doi: 10.1515/phys-2024-0060 http://dx.doi.org/10.1515/phys-2024-0060
袁旭祥 . 基于深度学习的显著性目标检测算法研究 [D]. 鞍山 : 辽宁科技大学 , 2023 .
YUAN X X . Research on saliency object detection algorithm based on deep learning [D]. Anshan : University of Science and Technology Liaoning , 2023 . (in Chinese)
0
浏览量
52
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621