Abstract
Deep learning-based target detection for optical remote sensing images is a significant research direction in the field of image processing. Different from natural images, remote sensing images are characterized by complex backgrounds, similarity of characteristics between various classes and diverse target scales. In this paper, we propose an adaptive multi-feature fusion YOLOv3 remote sensing small target detection algorithm to cope with these features. In the proposed algorithm, the shallow semantic information is extracted by the accessory feature extraction network, and fused with the deep features extracted by Darknet-53 down-sampling to enrich the semantic and spatial information of the feature layers on the auxiliary network. In addition, the shallow features are filtered using the adaptive feature selection module to refine the effective feature information. A cross-layer feature fusion module is proposed to fuse different feature layers to enhance the connection between the semantic information of feature contexts to obtain more information about the characteristics of small targets. To test the effectiveness of the proposed algorithm, it is validated on the Pascal voc2007 dataset. The experimental results show that the detection accuracy of the proposed algorithm could achieve 88.3%, and evidently superior to the original YOLOv3 algorithm. Finally, the proposed algorithm is applied to detect the small target in remote sensing images. The detection results show that compared with the original YOLOv3 algorithm, the mean average precision(mAP) of the proposed algorithm is improved by 2.6%, which can effectively detect more small targets and significantly improve the detection accuracy of small targets than other classical algorithms.
Similar content being viewed by others
Availability of data and material
This paper shows the experimental results of the proposed algorithm. Code availability: Not applicable.
References
Tondewad MPS, Dale MMP (2020) Remote sensing image registration methodology: review and discussion. Proc Comput Sci 171:2390–2399. https://doi.org/10.1016/j.procs.2020.04.259 (third International Conference on Computing and Network Communications (CoCoNet’19))
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE conference on computer vision and pattern recognition vol 2014, pp 580–587. https://doi.org/10.1109/CVPR.2014.81
Śmieja M, Tabor J, Spurek P (2019) Svm with a neutral class. Pattern Anal Appl. https://doi.org/10.1007/s10044-017-0654-3
Girshick R (2015) Fast r-cnn. In: IEEE international conference on computer vision (ICCV), vol 2015, pp 1440–1448. https://doi.org/10.1109/ICCV.2015.169
Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: IEEE conference on computer vision and pattern recognition (CVPR) vol 2016, pp 779–788. https://doi.org/10.1109/CVPR.2016.91
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single shot multibox detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision—ECCV 2016. Springer International Publishing, Cham, pp 21–37
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR) vol 2016, pp 770–778. https://doi.org/10.1109/CVPR.2016.90
Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651. https://doi.org/10.1109/TPAMI.2016.2572683
Fu C-Y, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd : deconvolutional single shot detector. ar**v:1701.06659
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: IEEE conference on computer vision and pattern recognition (CVPR) vol 2017, pp 6517–6525. https://doi.org/10.1109/CVPR.2017.690
**anbao C, Guihua Q, Yu J, Zhaomin Z (2021) An improved small object detection method based on yolo v3. Pattern Anal Appl. https://doi.org/10.1007/s10044-021-00989-7
Seferbekov S, Iglovikov V, Buslaev A, Shvets A (2018) Feature pyramid network for multi-class land segmentation. In: IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW) vol 2018, pp 272–2723. https://doi.org/10.1109/CVPRW.2018.00051
Pang J, Li C, Shi J, Xu Z, Feng H (2019) ¡inline-formula¿ ¡tex-math notation=“latex’’¿\(\cal{R}2\) ¡/tex-math¿¡/inline-formula¿-cnn: Fast tiny object detection in large-scale remote sensing images. IEEE Trans Geosci Remote Sens 57(8):5512–5524. https://doi.org/10.1109/TGRS.2019.2899955
Yang X, Yang J, Yan J, Zhang Y, Zhang T, Guo Z, Sun X, Fu K (2019) Scrdet: Towards more robust detection for small, cluttered and rotated objects. In: IEEE/CVF international conference on computer vision (ICCV) vol 2019, pp 8231–8240. https://doi.org/10.1109/ICCV.2019.00832
Jiang W, Zhang C, Zhang S, Liu W, University LT, School G, University LT (2019) Multiscale feature map fusion algorithm for target detection. J Image Graph. https://doi.org/10.11834/jig.190021
Wang P, Sun X, Diao W, Fu K (2020) Fmssd: feature-merged single-shot detection for multiscale objects in large-scale remote sensing imagery. IEEE Trans Geosci Remote Sens 58(5):3377–3390. https://doi.org/10.1109/TGRS.2019.2954328
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2015) Object detectors emerge in deep scene cnns. ar**v:1412.6856
Herout A, Hradiš M, Zemčík P (2012) Enms: early non-maxima suppression. Pattern Anal Appl. https://doi.org/10.1007/s10044-011-0213-2
Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In: IEEE/CVF conference on computer vision and pattern recognition (CVPR) vol 2019, pp 510–519. https://doi.org/10.1109/CVPR.2019.00060
Li K, Wan G, Cheng G, Meng L, Han J (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm Remote Sens 159:296–307. https://doi.org/10.1016/j.isprsjprs.2019.11.023
Law H, Deng J (2019) Cornernet: detecting objects as paired keypoints. ar**v:1808.01244
Lin T-Y, Goyal P, Girshick R, He K, Dollár P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318–327. https://doi.org/10.1109/TPAMI.2018.2858826
Cheng G, Si Y, Hong H, Yao X, Guo L (2021) Cross-scale feature fusion for object detection in optical remote sensing images. IEEE Geosci Remote Sens Lett 18(3):431–435. https://doi.org/10.1109/LGRS.2020.2975541
Acknowledgements
This work was under the funding of the National Natural Science Foundation of China (61973264) and the Natural Science Foundation of Hebei Province (F2020203003).
Funding
This work was under the funding of the National Natural Science Foundation of China (61973264) and the Natural Science Foundation of Hebei Province (F2020203003).
Author information
Authors and Affiliations
Contributions
(1) We propose an improved YOLOv3 algorithm based on adaptive multi-feature fusion adaptive multi-feature fusion. (2) An accessory feature extraction network is introduced into the side branch of the DarkNet-53 backbone network. (3) An adaptive feature selection module, which assigns weights to feature maps with different sensory field sizes and extracts discriminative features, is proposed. (4) A cross-layer feature fusion module is introduced into the feature pyramid network to enhance the connection between feature contextual information. (5) Experimental results illustrate the effectiveness of the proposed method. The proposed method can detect more small targets and obtain higher confidence scores than original yolov3 algorithm.
Corresponding author
Ethics declarations
Conflicts of interest
The authors declared that they have no conflicts of interest in this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, G., Hao, X., Zha, L. et al. An outstanding adaptive multi-feature fusion YOLOv3 algorithm for the small target detection in remote sensing images. Pattern Anal Applic 25, 951–962 (2022). https://doi.org/10.1007/s10044-022-01072-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-022-01072-5