Abstract
Person re-identification (ReID) is a popular area of research in the field of computer vision. Despite the significant advancements achieved in recent years, most of the current methods rely on datasets containing subjects captured with good lighting under static conditions. ReID presents a significant challenge in real-world sporting scenarios, such as long-distance races that take place over varying lighting conditions, ranging from bright daylight to night-time. Unfortunately, increasing the exposure time on the capture devices to mitigate low-light environments is not a feasible solution, as it would result in blurry images due to the motion of the runners. This paper surveys several low-light image enhancement methods and finds that including an image pre-processing step in the ReID pipeline before extracting the distinctive body features of the subjects can lead to significant improvements in performance.
This work is partially funded by the ULPGC under project ULPGC2018-08, by the Spanish Ministry of Science and Innovation under project PID2021-122402OB-C22, and by the ACIISI-Gobierno de Canarias and European FEDER funds under projects ProID2020010024, ProID2021010012, ULPGC Facilities Net, and Grant EIS 2021 04.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cai, J., Gu, S., Zhang, L.: Learning a deep single image contrast enhancer from multi-exposure images. IEEE Trans. Image Process. 27(4), 2049–2062 (2018). https://doi.org/10.1109/TIP.2018.2794218
Cheng, Z., Zhu, X., Gong, S.: Face re-identification challenge: are face recognition models good enough? Pattern Recogn. 107, 107422 (2020). https://doi.org/10.1016/j.patcog.2020.107422
Dietlmeier, J., Antony, J., McGuinness, K., O’Connor, N.E.: How important are faces for person re-identification? In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 6912–6919. IEEE Computer Society, Los Alamitos (2021). https://doi.org/10.1109/ICPR48806.2021.9412340
Freire-Obregón, D., Lorenzo-Navarro, J., Castrillón-Santana, M.: Decontextualized I3D convnet for ultra-distance runners performance analysis at a glance. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) ICIAP 2022. LNCS, vol. 13233, pp. 242–253. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06433-3_21
Freire-Obregón, D., Lorenzo-Navarro, J., Santana, O.J., Hernández-Sosa, D., Castrillón-Santana, M.: Towards cumulative race time regression in sports: I3d convnet transfer learning in ultra-distance running events. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 805–811 (2022). https://doi.org/10.1109/ICPR56361.2022.9956174
Fu, X., Zeng, D., Huang, Y., Liao, Y., Ding, X., Paisley, J.: A fusion-based enhancing method for weakly illuminated images. Sig. Process. 129, 82–96 (2016). https://doi.org/10.1016/j.sigpro.2016.05.031
Guo, X., Li, Y., Ling, H.: LIME: low-light image enhancement via illumination map estimation. IEEE Trans. Image Process. 26(2), 982–993 (2017). https://doi.org/10.1109/TIP.2016.2639450
Hao, S., Han, X., Guo, Y., Wang, M.: Decoupled low-light image enhancement. ACM Trans. Multimedia Comput. Commun. Appl. 18(4), 1–19 (2022). https://doi.org/10.1145/3498341
He, W., Liu, Y., Feng, J., Zhang, W., Gu, G., Chen, Q.: Low-light image enhancement combined with attention map and U-Net network. In: 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education (ICISCAE), pp. 397–401 (2020). https://doi.org/10.1109/ICISCAE51034.2020.9236828
Hernández-Carrascosa, P., Penate-Sanchez, A., Lorenzo-Navarro, J., Freire-Obregón, D., Castrillón-Santana, M.: TGCRBNW: a dataset for runner bib number detection (and recognition) in the wild. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9445–9451 (2021). https://doi.org/10.1109/ICPR48806.2021.9412220
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3296–3297. IEEE Computer Society, Los Alamitos (2017). https://doi.org/10.1109/CVPR.2017.351
Jobson, D., Rahman, Z., Woodell, G.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans. Image Process. 6(7), 965–976 (1997). https://doi.org/10.1109/83.597272
Kim, M.: Improvement of low-light image by convolutional neural network. In: 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 189–192 (2019). https://doi.org/10.1109/MWSCAS.2019.8885098
Land, E.H.: The retinex theory of color vision. Sci. Am. 237(6), 108–129 (1977). http://www.jstor.org/stable/24953876
Leng, H., Fang, B., Zhou, M., Wu, B., Mao, Q.: Low-light image enhancement with contrast increase and illumination smooth. Int. J. Pattern Recogn. Artif. Intell. 37(03), 2354003 (2023). https://doi.org/10.1142/S0218001423540034
Li, C., et al.: Low-light image and video enhancement using deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9396–9416 (2022). https://doi.org/10.1109/TPAMI.2021.3126387
Li, M., Liu, J., Yang, W., Sun, X., Guo, Z.: Structure-revealing low-light image enhancement via robust retinex model. IEEE Trans. Image Process. 27(6), 2828–2841 (2018). https://doi.org/10.1109/TIP.2018.2810539
Liu, J., Xu, D., Yang, W., Fan, M., Huang, H.: Benchmarking low-light image enhancement and beyond. Int. J. Comput. Vis. 129(4), 1153–1184 (2021). https://doi.org/10.1007/s11263-020-01418-8
Liu, S., Long, W., Li, Y., Cheng, H.: Low-light image enhancement based on membership function and gamma correction. Multimedia Tools Appl. 81, 22087–22109 (2022). https://doi.org/10.1007/s11042-021-11505-8
Luo, H., Jiang, W., Zhang, X., Fan, X., Qian, J., Zhang, C.: AlignedReID++: dynamically matching local information for person re-identification. Pattern Recogn. 94, 53–61 (2019). https://doi.org/10.1016/j.patcog.2019.05.028
Lv, F., Lu, F., Wu, J., Lim, C.: MBLLEN: low-light image/video enhancement using CNNs. In: British Machine Vision Conference (BMVC) (2018)
Ma, F., Zhu, X., Zhang, X., Yang, L., Zuo, M., Jing, X.Y.: Low illumination person re-identification. Multimedia Tools Appl. 78, 337–362 (2019). https://doi.org/10.1007/s11042-018-6239-3
Ning, X., Gong, K., Li, W., Zhang, L., Bai, X., Tian, S.: Feature refinement and filter network for person re-identification. IEEE Trans. Circ. Syst. Video Technol. 31(9), 3391–3402 (2021). https://doi.org/10.1109/TCSVT.2020.3043026
Park, S., Yu, S., Kim, M., Park, K., Paik, J.: Dual autoencoder network for retinex-based low-light image enhancement. IEEE Access 6, 22084–22093 (2018). https://doi.org/10.1109/ACCESS.2018.2812809
Penate-Sanchez, A., Freire-Obregón, D., Lorenzo-Melián, A., Lorenzo-Navarro, J., Castrillón-Santana, M.: TGC20ReId: a dataset for sport event re-identification in the wild. Pattern Recogn. Lett. 138, 355–361 (2020). https://doi.org/10.1016/j.patrec.2020.08.003
Rahman, Z., Pu, Y.F., Aamir, M., Wali, S.: Structure revealing of low-light images using wavelet transform based on fractional-order denoising and multiscale decomposition. Vis. Comput. 37(5), 865–880 (2021). https://doi.org/10.1007/s00371-020-01838-0
Santana, O.J., Freire-Obregón, D., Hernández-Sosa, D., Lorenzo-Navarro, J., Sánchez-Nielsen, E., Castrillón-Santana, M.: Facial expression analysis in a wild sporting environment. Multimedia Tools Appl. 82(8), 11395–11415 (2023). https://doi.org/10.1007/s11042-022-13654-w
Santana, O.J., Lorenzo-Navarro, J., Freire-Obregón, D., Hernández-Sosa, D., Isern-González, J., Castrillón-Santana, M.: Exploiting temporal coherence to improve person re-identification. In: De Marsico, M., Sanniti di Baja, G., Fred, A. (eds.) ICPRAM 2021, ICPRAM 2022: Pattern Recognition Applications and Methods. LNCS, vol. 13822, pp. 134–151. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-24538-1_7
Santana, O.J., Lorenzo-Navarro, J., Freire-Obregón, D., Hernández-Sosa, D., Castrillón-Santana, M.: Evaluating the impact of low-light image enhancement methods on runner re-identification in the wild. In: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM, pp. 641–648. INSTICC, SciTePress (2023). https://doi.org/10.5220/0011652000003411
Wang, R., Zhang, Q., Fu, C.W., Shen, X., Zheng, W.S., Jia, J.: Underexposed photo enhancement using deep illumination estimation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6842–6850 (2019). https://doi.org/10.1109/CVPR.2019.00701
Wang, S., Zheng, J., Hu, H.M., Li, B.: Naturalness preserved enhancement algorithm for non-uniform illumination images. IEEE Trans. Image Process. 22(9), 3538–3548 (2013). https://doi.org/10.1109/TIP.2013.2261309
Wei, C., Wang, W., Yang, W., Liu, J.: Deep retinex decomposition for low-light enhancement. In: 2018 British Machine Vision Conference (BMVC), pp. 1–12 (2018)
Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645–3649. IEEE Press (2017). https://doi.org/10.1109/ICIP.2017.8296962
Ying, Z., Li, G., Ren, Y., Wang, R., Wang, W.: A new low-light image enhancement algorithm using camera response model. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 3015–3022 (2017). https://doi.org/10.1109/ICCVW.2017.356
Zhai, G., Sun, W., Min, X., Zhou, J.: Perceptual quality assessment of low-light image enhancement. ACM Trans. Multimedia Comput. Commun. Appl. 17(4), 1–24 (2021). https://doi.org/10.1145/3457905
Zhang, Q., Nie, Y., Zheng, W.S.: Dual illumination estimation for robust exposure correction. Comput. Graph. Forum 38(7), 243–252 (2019). https://doi.org/10.1111/cgf.13833
Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1116–1124 (2015). https://doi.org/10.1109/ICCV.2015.133
Acknowledgements
We would like to thank Arista Eventos SLU and Carlos Díaz Recio for granting us the use of Transgrancanaria media. We would also like to thank the volunteers and researchers who have taken part in the data collection and annotation, as well as the previous papers of this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Santana, O.J., Lorenzo-Navarro, J., Freire-Obregón, D., Hernández-Sosa, D., Castrillón-Santana, M. (2024). Improving Person Re-identification Through Low-Light Image Enhancement. In: De Marsico, M., Di Baja, G.S., Fred, A. (eds) Pattern Recognition Applications and Methods. ICPRAM 2023. Lecture Notes in Computer Science, vol 14547. Springer, Cham. https://doi.org/10.1007/978-3-031-54726-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-54726-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54725-6
Online ISBN: 978-3-031-54726-3
eBook Packages: Computer ScienceComputer Science (R0)