Improved object reidentification via more eﬀicient embeddings

Bayraktar, Ertugrul

doi:10.55730/1300-0632.3984

Improved object reidentification via more eﬀicient embeddings

ERTUĞRUL BAYRAKTAR (Yıldız Teknik Üniversitesi, Mekatronik Mühendisliği Bölümü, İstanbul, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

1 0

Yıl: 2023 Cilt: 31 Sayı: 2 Sayfa Aralığı: 282 - 294 Metin Dili: İngilizce DOI: 10.55730/1300-0632.3984 İndeks Tarihi: 12-06-2023

Improved object reidentification via more eﬀicient embeddings

Öz:

Object reidentification (ReID) in cluttered rigid scenes is a challenging problem especially when same-looking objects coexist in the scene. ReID is accepted to be one of the most powerful tools for matching the correct identities to each individual object when issues such as occlusion, missed detections, multiple same-looking objects coexisting in the same scene, and disappearance of objects from the view and/or revisiting the same region arise. We propose a novel framework towards more eﬀicient object ReID, improved object reidentification (IO-ReID), to perform object ReID in challenging scenes with real-time processing in mind. The proposed approach achieves distinctive and eﬀicient object embedding via training with the triplet loss, with input from both the foreground/background split by bounding box, and the full input image. With extensive experiments on two datasets serving for Object ReID, we demonstrate that the proposed method, IO-ReID, obtains a higher ReID accuracy and runs faster compared to the state-of-the-art methods on object ReID.

Anahtar Kelime: Object reidentification image retrieval triplet loss embedding generation ranking

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Suljagic H, Bayraktar E, Celebi N. Similarity based person re-identification for multi-object tracking using deep Siamese network. Neural Computing and Applications 2022; 34 (20): 18171-18182. https://doi.org/10.1007/s00521- 022-07456-2
[2] Rubino C, Crocco M, Del Bue A. 3D Object Localisation from Multi-View Image Detections. IEEE Transactions On Pattern Analysis And Machine Intelligence 2017; 40 (6): 1281-1294. https://doi.org/10.1109/TPAMI.2017.2701373
[3] Nicholson L, Milford M, Sünderhauf N. QuadricSLAM: Dual Quadrics From Object Detections as Land- marks in Object-Oriented SLAM. IEEE Robotics And Automation Letters 2018; 4 (1): 1-8. 4, 1-8 (2019). https://doi.org/10.1109/LRA.2018.2866205
[4] Zhu X, Zhu X, Li M, Moreiro P, Murino V et al. Intra-Camera Supervised Person Re-Identification. International Journal of Computer Vision 2019; 129 (5): 1580-1595. https://doi.org/10.1007/s11263-021-01440-4
[5] Bergmann P, Meinhardt T, Leal-Taixe L. Tracking without bells and whistles. In: Proceedings Of The IEEE International Conference On Computer Vision (ICCV); Seoul, Korea; 2019. pp. 941-951.
[6] Ye M, Shen J, Lin G, Xiang T, Shao L et al. Deep Learning for Person Re-identification: A Survey and Outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence 2021; 44 (6): 2872-93. https://doi.org/10.1109/TPAMI.2021.3054775
[7] Bansal V, James S, Del Bue A. re-OBJ: Jointly learning the foreground and background for object instance re- identification. In: Proceedings Of International Conference On Image Analysis And Processing (ICIAP); Trento, Italy; 2019. pp. 402-413.
[8] Bansal V, Foresti G, Martinel N. Where Did I See It? Object Instance Re-Identification with Attention. In: Proceedings Of The IEEE/CVF International Conference On Computer Vision; Virtual, Online; 2021. pp. 298-306.
[9] He K, Gkioxari G, Dollár P, Girshick R. Mask r-cnn. In: Proceedings Of The IEEE International Conference On Computer Vision; Venice, Italy; 2017. pp. 2961-2969.
[10] Gengec N, Eker O, Cevikalp H, Yazici A, Yavuz H. Visual object detection for autonomous transport vehicles in smart factories. Turkish Journal Of Electrical Engineering And Computer Sciences 2021; 29 (4): 2101-2115. http://doi.org/10.3906/elk-2008-62
[11] Özbek M, Syed M, Öksüz I. Subjective analysis of social distance monitoring using YOLOv3 architecture and crowd tracking system. Turkish Journal of Electrical Engineering and Computer Sciences 2021; 29 (2): 1157-1170. https://doi.org/10.3906/elk-2008-66
[12] Liang T, Chu X, Liu Y, Wang Y, Tang Z et al. Cbnet: A composite backbone network architecture for object de- tection. IEEE Transactions On Image Processing. 2022; 31: 6893 - 6906. https://doi.org/10.1109/TIP.2022.3216771
[13] Cheng G, Wang J, Li K, Xie X, Lang C et al. Anchor-free oriented proposal generator for object detection. IEEE Transactions On Geoscience And Remote Sensing. 2022; 60: 1-11. https://doi.org/10.1109/TGRS.2022.3183022
[14] Bian J, Mei X, Xue Y, Wu L, Ding Y. Eﬀicient hierarchical temporal segmentation method for facial expres- sion sequences. Turkish Journal Of Electrical Engineering And Computer Sciences 2019; 27 (3): 1680-1695. https://doi:10.3906/elk-1809-75
[15] Ayanzadeh A, Özuysal Ö, Okvur D, Önal S, Töreyin B et al. Improved cell segmentation using deep learning in label-free optical microscopy images. Turkish Journal Of Electrical Engineering And Computer Sciences 2021; 29 (8): 2855-2868. https://doi.org/10.3906/elk-2105-244
[16] Cheng B, Parkhi O, Kirillov A. Pointly-supervised instance segmentation. In: Proceedings Of The IEEE/CVF Conference On Computer Vision And Pattern Recognition; New Orleans, LA, USA; 2022. pp. 2617-2626.
[17] Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In: Advances In Neural Information Processing Systems; Lake Tahoe, NV, USA; 2012. pp. 1097-1105.
[18] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations; San Diego, CA, USA; 2015. pp. 1-14.
[19] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S et al. Going deeper with convolutions. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Boston, MA, USA; 2015. pp. 1-9.
[20] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. pp. 770-778.
[21] Redmon J, Farhadi A. Yolov3: An incremental improvement. ArXiv TechReport ArXiv:1804.02767, 2018.
[22] Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances In Neural Information Processing Systems; Montreal, Canada; 2015. pp. 91-99.
[23] Bolya D, Zhou C, Xiao F, Lee Y. YOLACT++: Better Real-time Instance Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022; 44 (2): 1108-1121. https://doi.org/10.1109/TPAMI.2020.3014297
[24] Gordo A, Almazán J, Revaud J, Larlus D. Deep image retrieval: Learning global representations for image search. In: Proceedings Of European Conference On Computer Vision (ECCV); Amsterdam, Netherlands; 2016. pp. 241-257.
[25] Radenović F, Tolias G, Chum O. Fine-tuning CNN image retrieval with no human annotation. IEEE Transactions On Pattern Analysis And Machine Intelligence. 2018; 41 (7): 1655-1668. https://doi.org/10.1109/TPAMI.2018.2846566
[26] Revaud J, Almazán J, Rezende R, Souza C. Learning with average precision: Training image retrieval with a listwise loss. In: Proceedings Of The IEEE International Conference On Computer Vision (ICCV); Seoul, Korea; 2019. pp. 5107-5116.
[27] Wei X, Luo J, Wu J, Zhou Z. Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE Transactions On Image Processing 2017; 26 (6): 2868-2881. https://doi.org/10.1109/TIP.2017.2688133
[28] Jimenez A, Alvarez J, Nieto X. Class-weighted convolutional features for visual instance search. In: 28th British Machine Vision Conference (BMVC); London, UK; 2017. pp. 1-12.
[29] Salvador A, Nieto X, Marqués F, Satoh S. Faster r-cnn features for instance search. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition Workshops (CVPRW); Las Vegas, NV, USA; 2016. pp. 9-16.
[30] Teichmann M, Araujo A, Zhu M, Sim J. Detect-to-retrieve: Eﬀicient regional aggregation for image search. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Long Beach, CA, USA; pp. 5109-5118.
[31] Le T, Nguyen K, Nguyen-Phan M, Ton T, Nguyen T et al. Others Instance re-identification flow for video object segmentation. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition Workshops (CVPRW); Honolulu, HI, USA; 2017. pp. 1-6.
[32] Tao R, Gavves E, Smeulders A. Siamese instance search for tracking. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. pp. 1420-1429.
[33] Li X, Qi Y, Wang Z, Chen K, Liu Z et al. Video object segmentation with re-identification.In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. pp. 1-6.
[34] Li X, Change-Loy C. Video object segmentation with joint re-identification and attention-aware mask propagation. In: Proceedings Of The European Conference On Computer Vision (ECCV); Munich, Germany; 2018. pp. 90-105.
[35] Farenzena M, Bazzani L, Perina A, Murino V, Cristani M. Person re-identification by symmetry-driven accumulation of local features. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); San Francisco, CA, USA; 2010. pp. 2360-2367.
[36] Ahmed E, Jones M, Marks T. An improved deep learning architecture for person re-identification. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Boston, MA, USA; 2015. pp. 3908-3916.
[37] Paisitkriangkrai S, Shen C, Van Den Hengel A. Learning to rank in person re-identification with metric ensembles. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Boston, MA, USA; 2015. pp. 1846-1855.
[38] Bazzani L, Cristani M, Murino V. Symmetry-driven accumulation of local features for human char- acterization and re-identification. Computer Vision And Image Understanding 2013; 117 (2): 130-144. https://doi.org/10.1016/j.cviu.2012.10.008
[39] Bazzani L, Cristani M, Perina A, Murino V. Multiple-shot person re-identification by chromatic and epitomic analyses. Pattern Recognition Letters 2012; 33 (7): 898-903. https://doi.org/10.1016/j.patrec.2011.11.016
[40] Kingma D, Ba J. Adam: A method for stochastic optimization. In: 3rd International Conference on Learning Representations; San Diego, CA, USA; 2015. pp. 1-15.
[41] Dai A, Chang A, Savva M, Halber M, Funkhouser T et al. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In: Proceedings Of The IEEE Conference On Computer Vision And Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. pp. 5828-5839.
[42] Viola R, Gautheron L, Habrard A, Sebban M. MetaAP: A meta-tree-based ranking algorithm optimiz- ing the average precision from imbalanced data. Pattern Recognition Letters 2022; 161 (1): 161-167. https://doi.org/10.1016/j.patrec.2022.07.019
[43] Henderson P, Ferrari V. End-to-end training of object class detectors for mean average precision. In: Asian Conference On Computer Vision; Taipei, Taiwan; 2016. pp. 198-213.

APA	Bayraktar E (2023). Improved object reidentification via more eﬀicient embeddings. , 282 - 294. 10.55730/1300-0632.3984
Chicago	Bayraktar Ertugrul Improved object reidentification via more eﬀicient embeddings. (2023): 282 - 294. 10.55730/1300-0632.3984
MLA	Bayraktar Ertugrul Improved object reidentification via more eﬀicient embeddings. , 2023, ss.282 - 294. 10.55730/1300-0632.3984
AMA	Bayraktar E Improved object reidentification via more eﬀicient embeddings. . 2023; 282 - 294. 10.55730/1300-0632.3984
Vancouver	Bayraktar E Improved object reidentification via more eﬀicient embeddings. . 2023; 282 - 294. 10.55730/1300-0632.3984
IEEE	Bayraktar E "Improved object reidentification via more eﬀicient embeddings." , ss.282 - 294, 2023. 10.55730/1300-0632.3984
ISNAD	Bayraktar, Ertugrul. "Improved object reidentification via more eﬀicient embeddings". (2023), 282-294. https://doi.org/10.55730/1300-0632.3984

APA	Bayraktar E (2023). Improved object reidentification via more eﬀicient embeddings. Turkish Journal of Electrical Engineering and Computer Sciences, 31(2), 282 - 294. 10.55730/1300-0632.3984
Chicago	Bayraktar Ertugrul Improved object reidentification via more eﬀicient embeddings. Turkish Journal of Electrical Engineering and Computer Sciences 31, no.2 (2023): 282 - 294. 10.55730/1300-0632.3984
MLA	Bayraktar Ertugrul Improved object reidentification via more eﬀicient embeddings. Turkish Journal of Electrical Engineering and Computer Sciences, vol.31, no.2, 2023, ss.282 - 294. 10.55730/1300-0632.3984
AMA	Bayraktar E Improved object reidentification via more eﬀicient embeddings. Turkish Journal of Electrical Engineering and Computer Sciences. 2023; 31(2): 282 - 294. 10.55730/1300-0632.3984
Vancouver	Bayraktar E Improved object reidentification via more eﬀicient embeddings. Turkish Journal of Electrical Engineering and Computer Sciences. 2023; 31(2): 282 - 294. 10.55730/1300-0632.3984
IEEE	Bayraktar E "Improved object reidentification via more eﬀicient embeddings." Turkish Journal of Electrical Engineering and Computer Sciences, 31, ss.282 - 294, 2023. 10.55730/1300-0632.3984
ISNAD	Bayraktar, Ertugrul. "Improved object reidentification via more eﬀicient embeddings". Turkish Journal of Electrical Engineering and Computer Sciences 31/2 (2023), 282-294. https://doi.org/10.55730/1300-0632.3984