VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild

Lou, Yihang; Bai, Yan; Liu, Jun; Wang, Shiqi; Duan, Ling-Yu

doi:10.1109/cvpr.2019.00335

Cited by 259 publications

(179 citation statements)

References 21 publications

Supporting

Mentioning

175

Contrasting

Unclassified

Order By: Relevance

“…Veri-Wild [28] is the largest dataset as of CVPR 2019. The dataset is captured from a large CCTV surveillance system consisting of 174 cameras across one month (30 24h) under unconstrained scenarios.…”

Section: Veri-wildmentioning

confidence: 99%

Vehicle Re-identification: an Efficient Baseline Using Triplet Embedding

Kuma

Weill

Aghdasi

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

1 In this paper we tackle the problem of vehicle reidentification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for reidentification involve (deep) learning an embedding space such that the vehicles of same identities are projected closer to one another, compared to the vehicles representing different identities. Popular loss functions for learning an embedding (space) include contrastive or triplet loss. In this paper we provide an extensive evaluation of these losses applied to vehicle re-identification and demonstrate that using the best practices for learning embeddings outperform most of the previous approaches proposed in the vehicle reidentification literature. Compared to most existing stateof-the-art approaches, our approach is simpler and more straightforward for training utilizing only identity-level annotations, along with one of the smallest published embedding dimensions for efficient inference. Furthermore in this work we introduce a formal evaluation of a triplet sampling variant (batch sample) into the re-identification literature.

show abstract

Section: Veri-wildmentioning

confidence: 99%

Vehicle Re-identification: an Efficient Baseline Using Triplet Embedding

Kuma

Weill

Aghdasi

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Liu et al [12] released the VeRi-776 dataset, in which there exist more view variants. And they proposed a new mathod named FDA-net [14]. They use visual features, license plates and spatio-temporal information to explore Re-ID tasks.…”

Section: Vehicle Re-identificationmentioning

confidence: 99%

“…3, our vehicle Re-ID framework with BIR outperforms state-of-the-art methods and compared baselines, which demonstrates the effectiveness of our overall framework and individual components. Compared with FDA-net [14], BIR has a gain of 15% in terms of mAP and 6% in terms of top-1 accuracy. Such a performance increase shows that the batch hard triplet loss does provide vital priors for robustly estimating the vehicle similarities.…”

Section: Effect Of Background Segmentationmentioning

confidence: 99%

Background Segmentation for Vehicle Re-identification

Ming-jie

Zhang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Vehicle re-identification (Re-ID) is very important in intelligent transportation and video surveillance. Prior works focus on extracting discriminative features from visual appearance of vehicles or using visual-spatio-temporal information. However, background interference in vehicle re-identification have not been explored. In the actual large-scale spatio-temporal scenes, the same vehicle usually appears in different backgrounds while different vehicles might appear in the same background, which will seriously affect the re-identification performance. To the best of our knowledge, this paper is the first to consider the background interference problem in vehicle re-identification. We construct a vehicle segmentation dataset and develop a vehicle Re-ID framework with a background interference removal (BIR) mechanism to improve the vehicle Re-ID performance as well as robustness against complex background in large-scale spatio-temporal scenes. Extensive experiments demonstrate the effectiveness of our proposed framework, with an average 9% gain on mAP over state-of-the-art vehicle Re-ID algorithms.

show abstract

“…The naturally induced sparsity of the re-id task lies in high inter-class similarity, since we observe that the interclass similarity problem is precisely due to the underlying manufacturing process; some examples of inter-class similarity clusters include groups of Toyota Corollas, black SUVs, or red vehicles. Conversely, existing vehicle re-id datasets such as VeRi-776 [35] and VeRi-Wild [36] primarily focus on intraclass variability. Current approaches in vehicle re-id attempt to address inter-class similarity and intra-class variability in the same end-to-end model [16], [17], [18], [20].…”

Section: B Research Issues In Teamed Classifiersmentioning

confidence: 99%

Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking in Multi-Camera Networks

Suprem

Lima

Padilha

et al. 2019

2019 IEEE First International Conference on Cognitive Machine Intelligence (CogMI)

View full text Add to dashboard Cite

As camera networks have become more ubiquitous over the past decade, the research interest in video management has shifted to analytics on multi-camera networks. This includes performing tasks such as object detection, attribute identification, and vehicle/person tracking across different cameras without overlap. Current frameworks for management are designed for multi-camera networks in a closed dataset environment where there is limited variability in cameras and characteristics of the surveillance environment are well known. Furthermore, current frameworks are designed for offline analytics with guidance from human operators for forensic applications. This paper presents a teamed classifier framework for video analytics in heterogeneous many-camera networks with adversarial conditions such as multi-scale, multi-resolution cameras capturing the environment with varying occlusion, blur, and orientations. We describe an implementation for vehicle tracking and vehicle re-identification (re-id), where we implement a zero-shot learning (ZSL) system that performs automated tracking of all vehicles all the time. Our evaluations on VeRi-776 and Cars196 show the teamed classifier framework is robust to adversarial conditions, extensible to changing video characteristics such as new vehicle types/brands and new cameras, and offers real-time performance compared to current offline video analytics approaches.

show abstract

VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild

Cited by 259 publications

References 21 publications

Vehicle Re-identification: an Efficient Baseline Using Triplet Embedding

Vehicle Re-identification: an Efficient Baseline Using Triplet Embedding

Background Segmentation for Vehicle Re-identification

Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking in Multi-Camera Networks

Contact Info

Product

Resources

About