Abstract
Visual sensors are widely deployed in many promising detection fields, such as precision measurement, visual object detection and search. Instance search is a special object search method based on visual sensor, which is of fundamental importance to many applications, including the area of civil and military. Although a quantity of instance search solutions has been proposed, it remains a critical challenge to provide a real-time, lightweight labeling, easy to deploy and able to simultaneous-object-positioning-and-classification method. To address the challenge, a novel instance search method named Faster-FIIS-GMS is described in this paper. The improved Faster R-CNN with the MRFR (Multi-Receptive Field Residual module) and the APM (Adaptive Proposals Mechanism) is proposed to achieve more accurate and time-saving object detection and background information elimination simultaneously. Next, a novel image matching method named Fast Intensity Initial Screening Algorithm (FIIS) is introduced to filter foreground information in an image preliminarily and then combined with Grid-based Motion Statistics (GMS) to achieve the final searching. The performance of Faster-FIIS-GMS is analyzed and validated by experimental tests in a dataset annotated by manual, and the experimental results demonstrate that the proposed method has great potential in instance search for real scene environment, as it achieves high accuracy and satisfactory real time performance using the general computer. We also provide the comparison to state-of-the-arts to investigate the superiority of the proposed scheme at the end of the work.
Similar content being viewed by others
Data availability
The INSTRE datasets analyzed during the current study are available at https://pan.baidu.com/s/1gdEfJ9L
References
Bay H, Ess A, Tuytelaars T et al (2007) Speeded-Up Robust Features (SURF). Comput Vis Image Underst 110(3):346–359
Bian JW, Lin WY, Liu Y et al (2020) GMS: Grid-Based Motion Statistics for fast, ultra-robust feature correspondence. Int J Comput Vis 128(6):1580–1593. https://doi.org/10.1007/s11263-019-01280-3
Christian S, Liu W, Jia YQ et al (2015) Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR.2015.7298594
Lowe DG (2004) Distinctive Image Features from Scale-Invariant Key-points. Int J Comput Vision 60:91–110
Dou JF, Qin Q, Tu ZM (2018) Robust image matching based on the information of SIFT. Optik 171:850–861
Eva M, Kevin M and Xavier G.i.N, et al, (2018) Saliency weighted convolutional features for instance search. Proceedings of the International Conference on Content-Based Multimedia Indexing 1–6
Huang X, Wan X and Peng DF, (2020) “Robust Feature Matching with Spatial Smoothness Constraints,” Remote Sensing 12 https://doi.org/10.3390/rs12193158
Huang YF and Hsieh YS, “Image retrieval based on AND/OR-construction models,” Multimedia Tools and Applications 79 37–38 27293–27320
Jimenez A, Jose MA, Xavier G.i.N (2017) Class-weighted convolutional features for visual instance search. arXiv: 1707 02581
Leng JX, Liu Y (2019) An enhanced SSD with feature fusion and visual reasoning for object detection. Neural Comput Appl 31(10):6459–6558
Li ZL, Xu K, Xie JF et al (2020) Deep Multiple Instance Convolutional Neural Networks for Learning Robust Scene Representations. IEEE Trans Geosci Remote Sens 58(5):3685–3702
Lin J, Zhu Y, Zhao WL (2021) Instance search based on weakly supervised feature learning Neurocomputing 424 117 124
Mei SH, Min WQ, Duan H et al (2019) Instance-level object retrieval via deep region CNN. Multimedia tools and applications 78(10):132471–213261
Nair LR, Subramaniam K and Venkatesan GKDP, et al., “An effective image retrieval system using machine learning and fuzzy c- means clustering approach,” Multimedia Tools and Applications 79 15–16 10123–10140
Redmon J and Farhadi A, (2017) “YOLO9000: Better, Faster, Stronger,” 30th IEEE Conference on Computer Vision and Pattern Recognition 6517–6525 https://doi.org/10.1109/CVPR.2017.690
Ren SQ, He KM, Girshick R et al (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6):1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Rublee E, Rabaud V, Konolige K et al (2011) ORB: An efficient alternative to SIFR or SURF. Procceedings 58(11):2564–2571
Saleem S, Bais A, Sablatnig R (2016) Towards feature points-based image matching between satellite imagery and aerial photographs of agriculture land. Computers and electronics agriculture 126:12–20. https://doi.org/10.1016/j.compag.2016.05.005
Salvador A, Giro-I-Nieto X, Marques F, et al. (2016) Faster R-CNN features for instance search. IEEE Conference on Computer Vision and Pattern Recognition Workshops 394–401
Uzyildrim FE, Ozuysal M (2016) Instance detection by keypoint matching beyond the nearest neighbor. SIViP 10(8):1527–1534
Wan JW, Niu L, Bai B et al (2020) Graph Regularized Deep Discrete Hashing for Multi-Label Image Retrieval. IEEE Signal Process Lett 27:1994–1998
Yannis K, Clayton M and Simon O, (2016) “Cross-Dimensional Weighting for Aggregated Deep Convolutional Features,” Proceedings of the European Conference on Computer Vision 9–16
Yang Y, Chen Z, Li XL et al (2020) Robust template matching with large angle localization. Neurocomputing 395:495–504
Zhang LG (2020) Shen Zhou and Li YB et al, “Image object detection and semantic segmentation based on convolutional neural network.” Neural Comput Appl 32(7):1949–1958
Zhang SZ, Cheng D, Gong YH et al (2018) Pedestrian search in surveillance videos by learning discriminative deep features. Neurocomputing 283:120–128
Zhang Y, Feng Y and Liu D et al, (2020) “FRWCAE: joint Faster R-CNN and Wasserstein convolutional auto-encoder for instance retrieval,” Applied Intelligence 50 7 1 14
Zhou JM, Cheng X and Han RZ, et al, (2020) “Image Precise Matching With Illumination Robust in Vehicle Visual Navigation,” IEEE Access 8 0.1109/ACCESS.2020.2994542
Funding
This work was supported in part by Key R&D program of Jiangsu Province under Grant BE2021679, Key R & D and Transformation program of Qinghai Province under Grant 2022-QY-208, National Disabled Persons' Federation project under Grant 2021CDPFAT-26.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Confict of interest
The authors declare that they have no conficts of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, X., Zhang, T. & Shen, C. Faster-FIIS-GMS: a novel object detection framework for instance search. Multimed Tools Appl 82, 46939–46960 (2023). https://doi.org/10.1007/s11042-023-15616-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15616-2