浏览全部资源
扫码关注微信
Published： 16 May 2023 ，
移动端阅览
杨露露， 蓝龙， 孙冬婷， 滕霄， 贲晛烨， 沈肖波. 2023. 低分辨率行人重识别数据集及其基准方法. 中国图象图形学报， 28(05):1346-1359
Yang Lulu， Lan Long， Sun Dongting， Teng Xiao， Ben Xianye， Shen Xiaobo. 2023. Newly low-resolution pedestrian re-identification-relevant dataset and its benched method. Journal of Image and Graphics， 28(05):1346-1359
目的
2
行人重识别旨在解决多个非重叠摄像头下行人的查询和识别问题。在很多实际的应用场景中，监控摄像头获取的是低分辨率行人图像，而现有的许多行人重识别方法很少关注真实场景中低分辨率行人相互匹配的问题。为研究该问题，本文收集并标注了一个新的基于枪球摄像头的行人重识别数据集，并基于此设计了一种低分辨率行人重识别模型来提升低分辨率行人匹配性能。
方法
2
该数据集由部署在3个不同位置的枪机摄像头和球机摄像头收集裁剪得到，最终形成包含200个有身份标签的行人和320个无身份标签的行人重识别数据集。与同类其他数据集不同，该数据集为每个行人同时提供高分辨率和低分辨率图像。针对低分辨率下的行人匹配难题，本文提出的基准模型考虑了图像超分、行人特征学习以及判别3个方面因素，并设计了相应的超分模块、特征学习模块和特征判别器模块，分别完成低分辨率图像超分、行人特征学习以及行人特征判断。
结果
2
提出的基准模型在枪球行人重识别数据集上的实验表明，对比于经典的行人重识别模型，新基准模型在平均精度均值（mean average precision，mAP）和Rank-1指标上分别提高了3.1%和6.1%。
结论
2
本文构建了典型的低分辨率行人重识别数据集，为研究低分辨率行人重识别问题提供了重要的数据来源，并基于该数据集研究了低分辨率下行人重识别基础方法。研究表明，提出的基准方法能够有效地解决低分辨行人匹配问题。
Objective
2
Pedestrian re-identification is focused on multiview non-overlapping-derived problem of querying and identifying the same identity pedestrian. However， such real-world application scenarios are challenged to some camera-relevant factors like 1） hardware， 2） shooting distance， 3） angle of view， 4） background clutters， and 5） occlusions. Current surveillance camera-based images can be captured and it is still challenged for its low resolution （LR） as well. In real scenes， pedestrian re-identification （re-id） methods are required to resolve multiple pedestrians-oriented heterogeneous problem for low resolution image further. To deal with the mismatch problem between high resolution （HR） images and LR images， conventional re-id methods are mainly concerned of the cross-resolution matching problem. It is essential to richer mutual-benefited ability between low-resolution gallery images and query images. To improve the low-resolution pedestrian matching performance， we develop a novel of gun-ball camera-based pedestrian re-identification benchmark dataset and a low-resolution pedestrian re-identification benchmark model is designed as well.
Method
2
This data collection is acquired by the gun and ball system， which is deployed at three intersections. To capture LR images， two of three cameras are placed at each intersection， and the gun camera has a fixed direction and focal length. To obtain high-resolution images more， the other ball camera can be used to tune the focal length and the direction of view according to the target pedestrian position. And， a pedestrian re-identification dataset can be built and sampled by 200 pedestrians-identified categories （the same pedestrian is captured and identified at different locations）， and a sample of 320 pedestrian-unidentified categories （pedestrians can be captured under a certain camera only）. Each of these pedestrians-related images are all in related to the two aspects of high resolution and low resolution. A pedestrian-identified image can be captured by at least 2 different gun-ball cameras from different places， and a pedestrian-unidentified image can be captured by one gun-ball camera only and it is required to be searched and matched across cameras further. Pedestrian-unidentified images are in relevance to both of LR
&
HR as well. Some optimal factors are illustrated as mentioned below： 1） a richer and more diverse pedestrian dataset： the gun-ball camera-based pedestrian re-identification dataset can be used to acquire various pedestrian images from intersections. 2） The pedestrian dynamics： each pedestrian image has its temporal information because the gun-ball camera-based pedestrian dataset is captured and cropped from the video stream. Such temporal-based pedestrian images can be used for video-related pedestrian re-identification as well. 3） Other potentials： some pedestrians-unidentified images can be focused on， which can be used to study pedestrian re-identification algorithms in semi-supervised or unsupervised domains， as well as the ground truth of identification systems. That is， given an unknown identity of a pedestrian， its identification system can automatically detect the similar one in the surveillance screen or database. To strengthen the matching problem of LR images of pedestrians， we consider 1） image super-resolution， 2） pedestrian-related feature learning， and 3） discrimination as three key factors in our baseline. Specifically， to optimize each aspect of resolution， pedestrian feature-related learning and discrimination， the baseline is involved of a super-resolution module， a pedestrian re-identification module， and a pedestrian feature discriminator. Therefore， we design a baseline pedestrian re-identification model and it is benched on the 5 following aspects： generator
G
， image discriminator
D
s
， gradient discriminator
D
g
， pedestrian feature extractor
F
， and pedestrian feature discriminator
D
f
. To resolve the problem of low-resolution pedestrian re-identification in real scenes， our proposed model can be used to optimize both of the resolution of pedestrian image and pedestrian discrimination features.
Result
2
The low-resolution pedestrian re-identification baseline model is demonstrated and experimentally validated on the gun-ball pedestrian re-identification dataset. The mean average precision （mAP） and Rank-1 metrics are improved by 3.1% and 6.1%.
Conclusion
2
LR-related pedestrian recognition in natural scenes can be facilitated， and its pixel misalignment-derived problem of low quality of generated super-resolved images can be resolved to a certain extent. The dataset and benchmark model are proposed and its potential is in related to pedestrian re-identification and image super-resolution. It provides a data source for the field of low-resolution pedestrian re-identification. Also， the proposed baseline model can be predicted to tackle the low-resolution pedestrian matching problem further.
行人重识别基准数据集低分辨率（LR）超分辨率（SR）判别器
pedestrian re-identificationbenchmark datasetlow-resolution（LR）super-resolution（SR）discriminator
Adil M， Mamoon S， Zakir A， Manzoor M A and Lian Z C. 2020. Multi scale-adaptive super-resolution person re-identification using GAN. IEEE Access， 8： 177351-177362 ［DOI： 10.1109/ACCESS.2020.3023594http://dx.doi.org/10.1109/ACCESS.2020.3023594］
Arjovsky M， Chintala S and Bottou L. 2017. Wasserstein GAN ［EB/OL］. ［2022-11-04］. httpshttps： https：//arxiv.org/pdf/1701.07875.pdfhttps://arxiv.org/pdf/1701.07875.pdf
Ben X Y， Xu S and Wang K J. 2012. Review on pedestrian gait feature expression and recognition. Pattern Recognition and Artificial Intelligence， 25（1）： 71-81
贲晛烨， 徐森， 王科俊. 2012. 行人步态的特征表达及识别综述. 模式识别与人工智能， 25（1）： 71-81 ［DOI： 10.3969/j.issn.1003-6059.2012.01.010http://dx.doi.org/10.3969/j.issn.1003-6059.2012.01.010］
Chen T L， Ding S J， Xie J Y， Yuan Y， Chen W Y， Yang Y， Ren Z and Wang Z Y. 2019a. ABD-Net： attentive but diverse person re-identification//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）： IEEE： 8350-8360 ［DOI： 10.1109/ICCV.2019.00844http://dx.doi.org/10.1109/ICCV.2019.00844］
Chen Y C， Li Y J， Du X F and Wang Y C F. 2019b. Learning resolution-invariant deep representations for person re-identification. Proceedings of 2019 AAAI Conference on Artificial Intelligence， 33（1）： 8215-8222 ［DOI： 10.1609/AAAI.v33i01.33018215http://dx.doi.org/10.1609/AAAI.v33i01.33018215］
Cheng Z Y， Dong Q， Gong S H and Zhu X T. 2020. Inter-task association critic for cross-resolution person re-identification//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， USA： IEEE： 2602-2612 ［DOI： 10.1109/CVPR42600.2020.00268http://dx.doi.org/10.1109/CVPR42600.2020.00268］
Chollet F. 2017. Xception： deep learning with depthwise separable convolutions//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， USA： IEEE： 1800-1807 ［DOI： 10.1109/CVPR.2017.195http://dx.doi.org/10.1109/CVPR.2017.195］
Dong C， Loy C C， He K M and Tang X O. 2014. Learning a deep convolutional network for image super-resolution//Proceedings of the 13th European Conference on Computer Vision （ECCV）. Zurich， Switzerland： Springer： 184-199 ［DOI： 10.1007/978-3-319-10593-2_13http://dx.doi.org/10.1007/978-3-319-10593-2_13］
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
Jing X Y， Zhu X K， Wu F， Hu R M， You X G， Wang Y H， Feng H and Yang J Y. 2017. Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning. IEEE Transactions on Image Processing， 26（3）： 1363-1378 ［DOI： 10.1109/TIP.2017.2651364http://dx.doi.org/10.1109/TIP.2017.2651364］
Kalayeh M M， Basaran E， Gökmen M， Kamasak M E and Shah M. 2018. Human semantic parsing for person re-identification//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Salt Lake City， USA： IEEE： 1062-1071 ［DOI： 10.1109/CVPR.2018.00117http://dx.doi.org/10.1109/CVPR.2018.00117］
Kim T， Cha M， Kim H， Lee J K and Kim J. 2017. Learning to discover cross-domain relations with generative adversarial networks//Proceedings of the 34th International Conference on Machine Learning. Sydney， Australia： IMLS： 1857-1865 ［DOI： 10.48550/arXiv.1703.05192http://dx.doi.org/10.48550/arXiv.1703.05192］
Lan L， Wang X C， Hua G， Huang T S and Tao D C. 2020. Semi-online multi-people tracking by re-identification. International Journal of Computer Vision， 128（7）： 1937-1955 ［DOI： 10.1007/s11263-020-01314-1http://dx.doi.org/10.1007/s11263-020-01314-1］
Li H J， Wu G J and Zheng W S. 2021b. Combined depth space-based architecture search for person re-identification//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， USA： IEEE： 6725-6734 ［DOI： 10.1109/ CVPR46437.2021.00666http://dx.doi.org/10.1109/CVPR46437.2021.00666］
Li Y J， Chen Y C， Lin Y Y， Du X F and Wang Y C F. 2019. Recover and identify： a generative dual model for cross-resolution person re-identification//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）： IEEE： 8089-8098 ［DOI： 10.1109/ICCV.2019.00818http://dx.doi.org/10.1109/ICCV.2019.00818］
Li Y L， He J F， Zhang T Z， Liu X， Zhang Y D and Wu F. 2021a. Diverse part discovery： occluded person re-identification with part-aware transformer//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Nashville， USA： IEEE： 2897-2906 ［DOI： 10.1109/CVPR46437.2021.00292http://dx.doi.org/10.1109/CVPR46437.2021.00292］
Liang J Y， J. Cao J Z， Sun G L， K. Zhang K， Van Gool L and Timofte R. 2021b. SwinIR： image restoration using swin transformer//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）， Montreal， Canada： IEEE： 1833-1844 ［DOI： 10.1109/ICCVW54120.2021.00210http://dx.doi.org/10.1109/ICCVW54120.2021.00210］
Liang T Y， Lan L， Zhang X and Luo Z G. 2021a. A generic MOT boosting framework by combining cues from SOT， tracklet and re-identification. Knowledge and Information Systems， 63（8）： 2109-2127 ［DOI： 10.1007/s10115-021-01576-2http://dx.doi.org/10.1007/s10115-021-01576-2］
Liu J X， Ni B B， Yan Y C， Zhou P， Cheng S and Hu J G. 2018. Pose transferrable person re-identification//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 4099-4108 ［DOI： 10.1109/CVPR.2018.00431http://dx.doi.org/10.1109/CVPR.2018.00431］
Liu Y Q， Zhang X F， Wang S S， Ma S W and Gao W. 2020. Progressive multi-scale residual network for single image super-resolution ［EB/OL］. ［2022-11-04］. https：//arxiv.org/pdf/2007.09552.pdfhttps://arxiv.org/pdf/2007.09552.pdf
Luo H， Gu Y Z， Liao X Y， Lai S Q and Jiang W. 2019. Bag of tricks and a strong baseline for deep person re-identification//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach， USA： IEEE： 1487-1495 ［DOI： 10.1109/CVPRW.2019.00190http://dx.doi.org/10.1109/CVPRW.2019.00190］
Makhzani A， Shlens J， Jaitly N， Goodfellow I and Frey B. 2015. Adversarial autoencoders ［EB/OL］. ［2022-11-04］. https：//arxiv.org/pdf/1511.05644.pdfhttps://arxiv.org/pdf/1511.05644.pdf
Munir A， Lyu C， Goossens B， Philips W and Micheloni C. 2021. Resolution based feature distillation for cross resolution person re-identification//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal， Canada： IEEE： 281-289 ［DOI： 10.1109/ICCVW54120.2021.00036http://dx.doi.org/10.1109/ICCVW54120.2021.00036］
Shen Q， Tian C， Wang J B， Jiao S S and Du L. 2020. Multi-resolution feature attention fusion method for person re-identification. Journal of Image and Graphics， 25（5）： 946-955
沈庆， 田畅， 王家宝， 焦珊珊， 杜麟. 2020. 多分辨率特征注意力融合行人再识别. 中国图象图形学报， 25（5）： 946-955 ［DOI： 10.11834/jig.190237http://dx.doi.org/10.11834/jig.190237］
Shi W D， Zhang Y Z， Liu S W， Zhu S D and Bao J N. 2020. Person re-identification based on deformation and occlusion mechanisms. Journal of Image and Graphics， 25（12）： 2530-2540
史维东， 张云洲， 刘双伟， 朱尚栋， 暴吉宁. 2020. 针对形变与遮挡问题的行人再识别. 中国图象图形学报， 25（12）： 2530-2540 ［DOI： 10.11834/jig.200016http://dx.doi.org/10.11834/jig.200016］
Sun D T， Yang L L， Lan L and Luo Z G. 2022. Toward to real low-resolution person re-identification： a new dataset and baseline//Proceedings of 2022 IEEE International Conference on Multimedia and Expo （ICME）. Taipei， China： IEEE： #9860022 ［DOI： 10.1109/ICME52920.2022.9860022http://dx.doi.org/10.1109/ICME52920.2022.9860022］
Szegedy C， Ioffe S， Vanhoucke V and Alemi A. 2016. Inception-v4， Inception-ResNet and the impact of residual connections on learning//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco， USA： AAAI： 4278-4284 ［DOI： 10.1609/aaai.v31i1.11231http://dx.doi.org/10.1609/aaai.v31i1.11231］
Wang H C， Shen J Y， Liu Y T， Gao Y and Gavves E. 2022. NFormer： robust person re-identification with neighbor transformer//Proceedings of 2022 IEEE Conference on Computer Vision and Pattern Recognition. New Orleans， USA： IEEE： 7287-7297 ［DOI： 10.48550/ arXiv.2204.09331http://dx.doi.org/10.48550/arXiv.2204.09331］
Wang Z， Ye M， Yang F， Bai X and Satoh S. 2018. Cascaded SR-GAN for scale-adaptive low resolution person re-identification//Proceedings of the 27th International Joint Conference on Artificial Intelligence （IJCAI）. Stockholm， Sweden： AAAI Press： 3891-3897
Wu Z Z， Yu X C， Zhu D L， Pang Q W， Shen S T， Ma T and Zheng J. 2022. SR-DSFF and FENet-ReID： a two-stage approach for cross resolution person re-identification. Computational Intelligence and Neuroscience， 2022： #4398727 ［DOI： 10.1155/2022/4398727http://dx.doi.org/10.1155/2022/4398727］
Ye M， Shen J B， Lin G J， Xiang T and Hoi S C H. 2022. Deep learning for person re-identification： a survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence， 44（6）： 2827-2893 ［DOI： 10.1109/TPAMI.2021.3054775http://dx.doi.org/10.1109/TPAMI.2021.3054775］
Zhang G Q， Ge Y， Dong Z C， Wang H， Zheng Y H and Chen S Y. 2021b. Deep high-resolution representation learning for cross-resolution person re-identification. IEEE Transactions on Image Processing， 30： 8913-8925 ［DOI： 10.1109/TIP.2021.3120054http://dx.doi.org/10.1109/TIP.2021.3120054］
Zhang P， Xu J S， Wu Q， Huang Q and Ben X Y. 2021a. Learning spatial-temporal representations over walking tracklet for long-term person re-identification in the wild. IEEE Transactions on Multimedia， 23： 3562-3576 ［DOI： 10.1109/TMM.2020.3028461http://dx.doi.org/10.1109/TMM.2020.3028461］
Zhang Y L， Li K P， Li K， Wang L C， Zhong B N and Fu Y. 2018.Image super-resolution using very deep residual channel attention networks//Proceedings of the 15th European Conference on Computer Vision （ECCV）. Munich， Germany： Springer： 294-310 ［DOI： 10.1007/978-3-030-01234-2_18http://dx.doi.org/10.1007/978-3-030-01234-2_18］
Zheng W S， Hong J C， Jiao J N， Wu A C， Zhu X T， Gong S G， Qin J Y and Lai J H. 2022. Joint bilateral-resolution identity modeling for cross-resolution person re-identification. International Journal of Computer Vision， 130（1）： 136-156 ［DOI： 10.1007/s11263-021-01518-zhttp://dx.doi.org/10.1007/s11263-021-01518-z］
Zheng X， Lin L， Ye M， Wang L and He C L. 2020. Improving person re-identification by attention and multi-attributes. Journal of Image and Graphics， 25（5）： 936-945
郑鑫， 林兰， 叶茂， 王丽， 贺春林. 2020. 结合注意力机制和多属性分类的行人再识别. 中国图象图形学报， 25（5）： 936-945 ［DOI： 10.11834/jig.190185http://dx.doi.org/10.11834/jig.190185］
Zhou K Y， Yang Y X， Cavallaro A and Xiang T. 2019. Omni-scale feature learning for person re-identification//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）： IEEE： 3701-3711 ［DOI： 10.1109/ICCV.2019.00380http://dx.doi.org/10.1109/ICCV.2019.00380］
相关文章
相关作者
相关机构
京公网安备11010802024621