Beyond the Parts: Learning Multi-view Cross-part Correlation for Vehicle Re-identification

Liu, Xinchen; Liu, Wu; Zheng, Jinkai; Yan, Chenggang; Mei, Tao

doi:10.1145/3394171.3413578

Cited by 75 publications

(46 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we can conclude that if the interval of the times of capturing the same vehicle is large, the negative effects of variable features on re-identification will be obvious. In order to reduce the impact of variable features, we will assign different weights to the variable features according to the time difference of image acquisitions as shown in (10), where the capturing time can be obtained through surveillance camera, (11) and the differences between the variable features of all pairs of vehicle face images can be obtained through (12).…”

Section: Fig 2 Vehicle Face Segmentation Resultsmentioning

confidence: 99%

“…Nowadays, the existing vehicle recognition methods mainly include the following two categories, one is based on artificial extracted features, the other is based on the features which are obtained automatically through deep learning. The artificial features can be divided into the low-level features and the high-level features, where the low-level image features include color feature [2][3], edge feature [4], texture feature [5], and shape feature [6], et al; and scale key point features [7][8] and 3D model feature [9][10][11][12] can be considered as the high-level features. However, the artificial features depend on human experience to a large extent, and the deep information of image is not easy to be mined, so the effectiveness of artificial features is hard to be ensured.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

2021

KSII TIIS

View full text Add to dashboard Cite

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

show abstract

Section: Fig 2 Vehicle Face Segmentation Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

2021

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Recently, various research efforts [24-27, 48, 49] combine CNN with graph network (GN) based reasoning for re-identification since GN can extract the regional/node feature of the graph structure. For example, the parsing-guided cross-part reasoning network (PCRNet) [24] extracted regional features for each part from CNN and propagated local information among parts based on graph convolutional networks. Wang et al [50] constructed a global structure graph from the features generated by the CNN and guidance to produce effective representations of vehicles.…”

Section: A Vehicle Re-identificationmentioning

confidence: 99%

“…Third, to consider relationships among part regions, vehicle re-identification methods enter the third stage, combining graph network (GN) with CNNs. As shown in Figure 1 (c), in this stage, vehicle re-identification models [24][25][26][27] usually have a CNN branch for learning global features and a GN branch for exploring the relationship among local features extract from part regions. However, first, the CNN's downsampling and convolution operations reduce the resolution of feature maps, greatly affecting the ability to recognize vehicle with similar appearances [28,29].…”

Section: Introductionmentioning

confidence: 99%

GiT: Graph Interactive Transformer for Vehicle Re-identification

Shen¹,

Xie²,

Zhu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, a suitable vehicle re-identification method should consider both robust global features and discriminative local features. In this paper, we propose a graph interactive transformer (GiT) for vehicle re-identification. On the whole, we stack multiple GiT blocks to build a competitive vehicle re-identification model, in where each GiT block employs a novel local correlation graph (LCG) module to extract discriminative local features within patches and uses a transformer layer to extract robust global features among patches. In detail, in the current GiT block, the LCG module learns local features from local and global features resulting from the LCG module and transformer layer of the previous GiT block. Similarly, the transformer layer learns global features from the global features generated by the transformer layer of the previous GiT block and the new local features outputted via the LCG module of the current GiT block. Therefore, LCG modules and transformer layers are in a coupled status, bringing effective cooperation between local and global features. This is the first work to combine graphs and transformers for vehicle re-identification to the best of our knowledge. Extensive experiments on three large-scale vehicle reidentification datasets demonstrate that our method is superior to state-of-the-art approaches. The code will be available soon.

show abstract

“…. [42] explores vehicle parsing to learn discriminative part-level features an build a part-neighboring graph to model the correlation between every part features. To alleviate the influence of the drastic appearance variation, [43] further introduces a novel multicenter metric learning framework which models the latent views from the vehicle visual appearance directly without the need for extra labels.…”

Section: B Vehicle Reidmentioning

confidence: 99%

DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification

Chen¹,

Zhang²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Vehicle re-identification, which seeks to match query vehicle images with tremendous gallery images , has been gathering proliferating momentum. Conventional methods generally perform re-identification tasks by representing vehicle images as real-valued feature vectors and then ranking the gallery images by computing the corresponding Euclidean distances. Despite achieving remarkable retrieval accuracy, these methods require tremendous memory and computation when the gallery set is large, making them inapplicable in real-world scenarios.In light of this limitation, in this paper, we make the very first attempt to investigate the integration of deep hash learning with vehicle re-identification. We propose a deep hash-based vehicle re-identification framework, dubbed DVHN, which substantially reduces memory usage and promotes retrieval efficiency while reserving nearest neighbor search accuracy. Concretely, DVHN directly learns discrete compact binary hash codes for each image by jointly optimizing the feature learning network and the hash code generating module. Specifically, we directly constrain the output from the convolutional neural network to be discrete binary codes and ensure the learned binary codes are optimal for classification. To optimize the deep discrete hashing framework, we further propose an alternating minimization method for learning binary similarity-preserved hashing codes. Extensive experiments on two widely-studied vehicle re-identification datasets-VehicleID and VeRi-have demonstrated the superiority of our method against the state-of-the-art deep hash methods. DVHN of 2048 bits can achieve 13.94% and 10.21% accuracy improvement in terms of mAP and Rank@1 for VehicleID (800) dataset. For VeRi, we achieve 35.45% and 32.72% performance gains for Rank@1 and mAP, respectively.

show abstract

Beyond the Parts: Learning Multi-view Cross-part Correlation for Vehicle Re-identification

Cited by 75 publications

References 16 publications

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

GiT: Graph Interactive Transformer for Vehicle Re-identification

DVHN: A Deep Hashing Framework for Large-scale Vehicle Re-identification

Contact Info

Product

Resources

About