Salient target detection algorithm based on dual-channel multi-scale pyramid pooling model

MA Shaobin; ZHANG Chengwen

doi:10.5768/JAO202142.0602007

Journal of Applied Optics > 2021 > 42(6): 1056-1061. > DOI: 10.5768/JAO202142.0602007

MA Shaobin, ZHANG Chengwen. Salient target detection algorithm based on dual-channel multi-scale pyramid pooling model[J]. Journal of Applied Optics, 2021, 42(6): 1056-1061. DOI: 10.5768/JAO202142.0602007

Citation:

PDF (1017 KB)

Salient target detection algorithm based on dual-channel multi-scale pyramid pooling model

MA Shaobin^{1, 2,},
ZHANG Chengwen^{1, 2}

1.
School of Digital Media, Lanzhou University of Arts and Science, Lanzhou 730010, China
2.
VR Technology R & D and Promotion Center, Lanzhou University of Arts and Science, Lanzhou 730010, China

More Information

Received Date: December 27, 2020
Revised Date: October 10, 2021
Available Online: October 18, 2021

Graphical Abstract

Abstract

Abstract

To improve the detection accuracy for armored targets in complex environment, a salient target detection algorithm was proposed. The low-level features and multi-scale pooling semantic features constrained by visual attention mechanism were respectively obtained by visual attention mechanism and joint pyramid upsampling module. Then the aggregation strategy was used to fuse, so as to improve the ability of target representation in low contrast or occlusion conditions. The experimental results show that the proposed algorithm obtains good detection results for multi-scale targets in complex scenes, the precision, recall rate and mean average precision (mAP) are 72.2%, 71.4% and 77.1%, respectively, which can meet the practical application requirements.
- target detection,
- pooling semantics,
- attention mechanism,
- partial occlusion,
- aggregation strategy

FullText(HTML)

References (16)

References

[1]	尹宏鹏, 陈波, 柴毅,等. 基于视觉的目标检测与跟踪综述[J]. 自动化学报,2016,42(10):1466-1489. YIN Hongpeng, CHEN Bo, CHAI Yi, et al. Vision-based object detection and tracking[J]. Acta Automatica Sinica,2016,42(10):1466-1489.
[2]	CHEN S, REN M, DONG C. Target recognition of ground armor based on combinatorial part model[C].IEEE 9th International conference on communication software and networks (ICCSN), GuangZhou, China: IEEE,2017: 6-8.
[3]	顾佼佼, 王磊. 多尺度特征融合的Anchor-Free轻量化舰船要害检测算法[J]. 北京航空航天大学学报,2021,12(9):1-16. GU Jiaojiao, WANG Lei . Anchor free lightweight ship key detection algorithm based on multi-scale feature fusion[J]. Journal of Beijing University of Aeronautics and Astronautics,2021,12(9):1-16.
[4]	孙皓泽, 常天庆, 张雷, 等. 基于轻量级网络的装甲目标快速检测[J]. 计算机辅助设计与图形学学报,2019,31(7):1110-1121. doi: 10.3724/SP.J.1089.2019.17467 SUN Haoze, CHANG Tianqing, ZHANG Lei, et al. Rapid detection of armored target based on lightweight network[J]. Journal of computer aided design and graphics,2019,31(7):1110-1121. doi: 10.3724/SP.J.1089.2019.17467
[5]	WANG C L, CHEN Z B, XUE M X. A detecting algorithm of infrared armor target under complex ground background based on morphological wavelet[C].International Society for Optics and Photonics, 2011: 8193-8206.
[6]	吴加莹, 杨赛, 堵俊, 等. 自底向上的显著性目标检测研究综述[J]. 计算机科学,2019,46(3):48-52. doi: 10.11896/j.issn.1002-137X.2019.03.006 WU Jiaying, YANG Sai, DU Jun, et al. A review of bottom-up salient target detection[J]. Computer science,2019,46(3):48-52. doi: 10.11896/j.issn.1002-137X.2019.03.006
[7]	KANSAL K, VENKATA S, PRASAD D K, et al. CARF-Net: CNN attention and RNN fusion network for video-based person reidentification[J]. Journal of Electronic imaging,2019,28(2):023036.1-023036.12.
[8]	AN F P, LIU J E, BAI L. Pedestrian reidentification algorithm based on deconvolution network feature extraction-multilayer attention mechanism convolutional neural network[J]. Journal of Sensors,2021,21(3):1-12. doi: 10.1109/JSEN.2020.3045950
[9]	HEDEYA M A, EID A H, ABDEL K R F. A super-learner ensemble of deep networks for vehicle-type classification[J]. IEEE Access,2020,24(9):1-17.
[10]	KIM S, SONG W J, KIM S H. Infrared variation optimized deep convolutional neural network for robust automatic ground target recognition[C]. IEEE conference on computer vision and pattern recognition workshops (CVPRW), Honolulu, HI, USA:IEEE, 2017: 195-202.
[11]	REDMON J , DIVVALA S , GIRSHICK R , et al. You only look once: unified, real-time object detection[C].IEEE Computer Vision & Pattern Recognition, Las Vegas, USA: IEEE, 2016: 2859-2895.
[12]	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multiBox detector[J]. Springer, Cham,2016,12(9):987-1002.
[13]	ZHU Y , ZHAO C , WANG J , et al. CoupleNet: coupling global structure with local parts for object detection[C].2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy: 2017: 25-68.
[14]	MISHRA S , LIANG P , CZAJKA A , et al. CC-net: image complexity guided network compression for biomedical image segmentation[C].2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, 2019: 655-663.
[15]	KAI C, PANG J, WANG J, et al. Hybrid task cascade for instance segmentation[J]. IEEE Transcations on ImageProcessing,2019,75(12):122-139.
[16]	SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning[C].Thirty-first AAAI conference on artificial intelligence, San Francisco, USA: AAAI, 2017: 2359-2367.

Cited By

Get Citation

PDF

XML

Article views (527) PDF downloads (50)

Turn off MathJax

Article Contents

Abstract

References

Salient target detection algorithm based on dual-channel multi-scale pyramid pooling model

Abstract

References

Catalog

Related Databases

Advertising cooperation

Links

Help Center

Salient target detection algorithm based on dual-channel multi-scale pyramid pooling model

Abstract

References

Catalog

Related Databases

Advertising cooperation

Links

Help Center

Export File

Citation

Format

Content