Vehicle Re-Identification Using Distance-Based Global and Partial Multi-Regional Feature Learning

Chen, Xu; Sui, Haigang; Fang, Jian; Feng, Wenqing; Zhou, Mingting

doi:10.1109/tits.2020.2968517

Cited by 28 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with SoftMax loss and distance-based classification [ 28 ], the multi-proxy constraint loss has a different optimization process, as illustrated in Figure 2 . SoftMax loss aims to pull all the positive samples within the boundaries of the class.…”

Section: The Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Proxy Constraint Loss for Vehicle Re-Identification

Chen

Sui

Fang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Vehicle re-identification plays an important role in cross-camera tracking and vehicle search in surveillance videos. Large variance in the appearance of the same vehicle captured by different cameras and high similarity of different vehicles with the same model poses challenges for vehicle re-identification. Most existing methods use a center proxy to represent a vehicle identity; however, the intra-class variance leads to great difficulty in fitting images of the same identity to one center feature and the images with high similarity belonging to different identities cannot be separated effectively. In this paper, we propose a sampling strategy considering different viewpoints and a multi-proxy constraint loss function which represents a class with multiple proxies to perform different constraints on images of the same vehicle from different viewpoints. Our proposed sampling strategy contributes to better mine samples corresponding to different proxies in a mini-batch using the camera information. The multi-proxy constraint loss function pulls the image towards the furthest proxy of the same class and pushes the image from the nearest proxy of different class further away, resulting in a larger margin between decision boundaries. Extensive experiments on two large-scale vehicle datasets (VeRi and VehicleID) demonstrate that our learned global features using a single-branch network outperforms previous works with more complicated network and those that further re-rank with spatio-temporal information. In addition, our method is easy to plug into other classification methods to improve the performance.

show abstract

Section: The Proposed Methodsmentioning

confidence: 99%

“…However, these center clustering methods require multiple computational processes. Chen et al [ 28 ] designed the distance-based classification to maintain the consistency among criteria for similarity evaluation, but it does not solve the problem of intra-class variance.…”

Section: Related Workmentioning

confidence: 99%

Multi-Proxy Constraint Loss for Vehicle Re-Identification

Chen

Sui

Fang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Huynh et al [4] presented a model for vehicle reID that introduces the concept of multi-head attention combined with Supervised Contrastive Loss [17]. Chen et al [18] introduced an end-to-end distance-learning deep network for vehicle reID. This network integrates global features and local features at a more detailed level, aiming to improve the performance of vehicle reID systems.…”

Section: Re-identificationmentioning

confidence: 99%

“…The details of these datasets is given in Table 2. The Rank-1 accuracy and the mean average precision (mAP) [18] are considered in this work for the evaluation of reID task. The mean average precision (mAP) is widely used to evaluate the performance of the convolutional networks for reID.…”

Section: Datasetsmentioning

confidence: 99%

MNASreID: Grasshopper Optimization based Neural Architecture Search for Motorcycle re-IDentification

Rampavan

Ijjina

2023

Preprint

View full text Add to dashboard Cite

Object re-IDentification (reID) is the process of matching the same object across multiple cameras. An approach for object reID is crucial for identifying objects like people, cars, motorcycles etc., in video surveillance systems. This is an active area of research in both industry and academia due to the ever-growing population and need for smart surveillance, public safety and traffic management. This work proposes an approach for automatically designing a deep convolutional neural network, named MNASreID, for motorcycle re-identification task. Most current reID methods use deep convolutional neural networks as the backbone that are manually designed, which does not have the optimum settings as the network complexity increases. MNASreID uses Neural Architecture Search (NAS) to search for the backbones of the Deep Neural Network (DNN) model. In addition, the designed search space includes parameters of the architecture and its hyperparameters to find the optimum architecture for the reID task. This work uses Grasshopper Optimization Algorithm (GOA) based NAS to find the optimal DNN model. The outcomes of experiments on two motorcycle datasets demonstrate that our method can automatically find the efficient DNN model for motorcycle reID.

show abstract

“…[32] introduces to disentangle the feature representation into orientation-specific and orientation-invariant features and, in the later stage, use the orientation-invariant feature to perform vehicle ReID task. [40] proposes to extract quadruple directional deep features for vehicle-re identification while [41] proposes an end-to-end distance-based deep neural network combining multi-regional features to learn to distinguish local and global differences of a vehicle image. .…”

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

Vehicle Re-Identification Using Distance-Based Global and Partial Multi-Regional Feature Learning

Cited by 28 publications

References 35 publications

Multi-Proxy Constraint Loss for Vehicle Re-Identification

Multi-Proxy Constraint Loss for Vehicle Re-Identification

MNASreID: Grasshopper Optimization based Neural Architecture Search for Motorcycle re-IDentification

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

Contact Info

Product

Resources

About