Low illumination person re-identification

Ma, Fei; Zhu, Xiaoke; Zhang, Xinyu; Yang, Liang; Zuo, Mei; Jing, Xiao‐Yuan

doi:10.1007/s11042-018-6239-3

Cited by 17 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Camera and illumination are important factors in person ReID task [22,24,43]. However, from the above experiments, we find that adding multiple camera parameters and illumination conditions does not bring obvious improvement.…”

Section: Ablation Study On Target-aware Renderingmentioning

confidence: 83%

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Chen¹,

He²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

Nowadays, real data in person re-identification (ReID) task is facing privacy issues, e.g., the banned dataset DukeMTMC-ReID. Thus it becomes much harder to collect real data for ReID task. Meanwhile, the labor cost of labeling ReID data is still very high and further hinders the development of the ReID research. Therefore, many methods turn to generate synthetic images for ReID algorithms as alternatives instead of real images. However, there is an inevitable domain gap between synthetic and real images. In previous methods, the generation process is based on virtual scenes, and their synthetic training data can not be changed according to different target real scenes automatically. To handle this problem, we propose a novel Target-Aware Generation pipeline to produce synthetic person images, called TAGPerson. Specifically, it involves a parameterized rendering method, where the parameters are controllable and can be adjusted according to target scenes. In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain. In our experiments, our target-aware synthetic images can achieve a much higher performance than the generalized synthetic images on MSMT17, i.e. 47.5% vs. 40.9% for rank-1 accuracy. We will release this toolkit 1 for the ReID community to generate synthetic images at any desired taste.

show abstract

Section: Ablation Study On Target-aware Renderingmentioning

confidence: 83%

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

Chen¹,

He²,

Du³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Previously little attention has been paid to these scenarios for the lack of abundant training data. For evaluation on indoor ReID and low illumination ReID tasks, we use GRID [7] and LIPS [28] dataset, respectively. GRID is a dataset collected in an underground station, where the cameras are located at high angles of view.…”

Section: Task-specific Adaptation For Corner Scenariosmentioning

confidence: 99%

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

TianYu

Xie

Zhuang

et al. 2020

Preprint

View full text Add to dashboard Cite

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a novel pipeline that makes full use of unreal image data to decrease the costs in both the training and deployment stages. Its fundamental part is a system that can generate synthesized images of high-quality and from controllable distributions. Instance-level annotation goes with the synthesized data and is almost free. We point out some details in image synthesis that largely impact the data quality. With 3,000 IDs and 120,000 instances, our method achieves a 38.5% rank-1 accuracy when being directly transferred to MSMT17. It almost doubles the former record using synthesized data and even surpasses previous direct transfer records using real data. This offers a good basis for unsupervised domain adaption, where our pre-trained model is easily plugged into the state-of-the-art algorithms towards higher accuracy. In addition, the data distribution can be flexibly adjusted to fit some corner ReID scenarios, which widens the application of our pipeline. We will publish our data synthesis toolkit and synthesized data in https: //github.com/FlyHighest/UnrealPerson.

show abstract

“…Wang et al [23] designed a feature projection matrix to project image features of one camera to the feature space of another camera. Ma et al [19] just focused on the low illumination problem. They transformed all the images to a uniform low illumination, and proposed a metric learning method to address the low illumination.…”

Section: Illumination Problem In Reidmentioning

confidence: 99%

Illumination-Adaptive Person Re-identification

Zeng,

Wang,

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

Most person re-identification (ReID) approaches assume that person images are captured under relatively similar illumination conditions. In reality, long-term person retrieval is common and person images are captured under different illumination conditions at different times across a day. In this situation, the performances of existing ReID models often degrade dramatically. This paper addresses the ReID problem with illumination variations and names it as Illumination-Adaptive Person Re-identification (IA-ReID). We propose an Illumination-Identity Disentanglement (IID) network to separate different scales of illuminations apart, while preserving individuals' identity information. To demonstrate the illumination issue and to evaluate our network, we construct two large-scale simulated datasets with a wide range of illumination variations. Experimental results on the simulated datasets and real-world images demonstrate the effectiveness of the proposed framework.

show abstract

Low illumination person re-identification

Cited by 17 publications

References 44 publications

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification

UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification

Illumination-Adaptive Person Re-identification

Contact Info

Product

Resources

About