Vehicle Re-identification Research Articles

Enhanced Vehicle Re-Identification for Smart City Applications Using Zone Specific Surveillance

Vehicle re-identification is an important feature of an intelligent transportation system as part of a smart city application. Vehicle re-identification aims at matching vehicles from images acquired by surveillance cameras at different locations. During rush hours, vehicles are densely occupied across regions such as entry/exit of gated campuses, railways, airports, educational institutions, etc. Due to this uneven flow of traffic, there is a possibility of violation of traffic rules by the vehicles that lead to a security breach. In such scenarios to speed up the re-identification process, it is justified to look into a specific group of surveillance cameras to detect and re-identify vehicles on day to day basis in near real-time. However, the existing vehicle re-identification datasets do not contain zone specific information and therefore can not be used to evaluate the performance of re-identification algorithms in different zones. In the proposed work for re-identification, a framework is developed that performs vehicle re-identification across a group of cameras that monitors varying traffic movements over an area. These areas defined as “strategic zones” comprise a subset of non-overlapping cameras that are installed to monitor non-uniform vehicle movements. The re-identification framework is evaluated on a novel dataset developed to understand the performance of vehicle re-identification across strategic zones. The dataset consists of videos of vehicles captured through 20 CCTV surveillance cameras that are grouped into four different zones. Various experiments are conducted to study the performance of re-identification across four zones using a deep neural network with triplet loss, L2 regularization, and re-ranking. The experiments conducted with an image dimension of 224 × 224 have demonstrated an overall mAP of 77.22%. Also, for each of the four zones a mAP of 82.16%, 69.1%, 66.5%, and 75.76% is achieved. The experimental results demonstrate huge variations in the accuracy of vehicle re-identification method across different zones. Therefore, the study assess the possible measures that can be taken to improve the performance in individual zones for an accurate vehicle re-identification in intelligent transport system.

GiT: Graph Interactive Transformer for Vehicle Re-identification.

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, pure transformers are not entirely suitable for vehicle re-identification because vehicle re-identification requires both robust global features and discriminative local features. For that, a graph interactive transformer (GiT) is proposed in this paper. In the macro view, a list of GiT blocks are stacked to build a vehicle re-identification model, in where graphs are to extract discriminative local features within patches and transformers are to extract robust global features among patches. In the micro view, graphs and transformers are in an interactive status, bringing effective cooperation between local and global features. Specifically, one current graph is embedded after the former level's graph and transformer, while the current transform is embedded after the current graph and the former level's transformer. In addition to the interaction between graphs and transforms, the graph is a newly-designed local correction graph, which learns discriminative local features within a patch by exploring nodes' relationships. Extensive experiments on three large-scale vehicle re-identification datasets demonstrate that our GiT method is superior to state-of-the-art vehicle re-identification approaches.

HAZMAT Vehicle Reidentification in Road Tunnels Based on the Fusion of Appearance and Spatiotemporal Information.

Vehicles transporting hazardous material (HAZMAT) pose a severe threat to highway safety, especially in road tunnels. Vehicle reidentification is essential for identifying and warning abnormal states of HAZMAT vehicles in road tunnels. However, there is still no public dataset for benchmarking this task. To this end, this work releases a real-world tunnel HAZMAT vehicle reidentification dataset, VisInt-THV-ReID, including 10,048 images with 865 HAZMAT vehicles and their spatiotemporal information. A method based on multimodal information fusion is proposed to realize vehicle reidentification by fusing vehicle appearance and spatiotemporal information. We design a spatiotemporal similarity determination method for vehicles based on the spatiotemporal law of vehicles in tunnels. Compared with other reidentification methods based on multimodal information fusion, i.e., PROVID, Visual + ST, and Siamese-CNN, experimental results show that our approach significantly improves the vehicle reidentification recognition precision.

Passing Vehicle Road Occupancy Detection Using the Magnetic Sensor Array

The increasing presence of vehicles on roads necessitates intelligent traffic management solutions in areas where video cameras cannot be utilized. Currently, there are limited choices for depersonalized vehicle reidentification systems. This paper introduces a system that later will be used for vehicle reidentification. The system uses anisotropic magnetoresistive sensors and is based on the hypothesis that each vehicle leaves unique magnetic signatures which can be used for comparison and matching. Vehicle location on the road perpendicular to sensor array detection methodology is presented in this work. An array of magnetic sensors is installed in asphalt across the vehicle’s driving direction. The system continuously measures Earth’s natural magnetic field and detects distortions when vehicles pass an array of a sensors and then logs magnetic signatures. Useful parameters from raw sensor axes are calculated– modules and derivatives. Applying signal-to-noise ratio calculation for module derivatives between ambient noise and signal gives important features for neural network input. Different types of neural network architectures and output result interpretation techniques are investigated. Further, after evaluating network output it is possible to label sensor nodes that are directly beneath the vehicle. Experiment results show that implemented algorithm is highly sufficient for valid sensors under the vehicle selection. Correct sensor selection is important for further re-identification algorithms.

Moving Towards Centers: Re-Ranking With Attention and Memory for Re-Identification

Re-ranking utilizes contextual information to optimize the initial ranking list of person or vehicle re-identification (re-ID), which boosts the retrieval performance at post-processing steps. This paper proposes a re-ranking network to predict the correlations between the probe and top-ranked neighbor samples. Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serves as discriminative combination weights. The combination process is equivalent to moving independent embeddings toward the identity centers, improving cluster compactness. For correlation prediction, we first aggregate the contextual information for probes k-nearest neighbors via the Transformer encoder. Then, we distill and refine the probe-related features into the Contextual Memory cell via attention mechanism. Like humans that retrieve images by not only considering probe images but also memorizing the retrieved ones, the Contextual Memory produces multiview descriptions for each instance. Finally, the neighbors are reconstructed with features fetched from the Contextual Memory, and a binary classifier predicts their correlations with the probe. Experiments on six widely-used person and vehicle re-ID benchmarks demonstrate the effectiveness of the proposed method. Especially, our method surpasses the state-of-the-art re-ranking approaches on large-scale datasets by a significant margin, i.e., with an average 3.08% CMC@1 and 7.46% mAP improvements on VERI-Wild, MSMT17, and VehicleID datasets.

Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric.

Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from the same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID. The codes and dataset are available at: https://github.com/zhangchaobin001/VCNet.

Self-Aligned Spatial Feature Extraction Network for UAV Vehicle Reidentification

Compared with existing vehicle reidentification (VeID) tasks conducted with datasets collected by fixed surveillance cameras, VeID for an unmanned aerial vehicle (UAV) is still under-explored and could be more challenging. Vehicles with the same color and type show extremely similar appearances from the UAV’s perspective so that mining fine-grained characteristics becomes necessary. Recent works tend to extract distinguishing information by regional features and component features. The former requires input images to be aligned and the latter entails detailed annotations, both of which are difficult to meet in UAV application. To extract efficient fine-grained features and avoid tedious annotating work, this letter develops an unsupervised self-aligned network consisting of three branches. The network introduced a self-alignment module to convert the input images with variable orientations to a uniform orientation, which is implemented under the constraint of a triple loss function designed with spatial features. On this basis, spatial features, obtained by vertical and horizontal segmentation methods, and global features are integrated to improve the representation ability in embedded space. Extensive experiments are conducted on UAV-VeID dataset, and our method achieves the best performance compared with recent reidentification (ReID) works.

Viewpoint Alignment and Discriminative Parts Enhancement in 3D Space for Vehicle ReID

Vehicle Re-Identification is to find the same vehicle from images captured in different views under cross-camera scenarios. Traditional methods focus on depicting the holistic appearance of a vehicle, but they suffer from the hard samples with the same vehicle type and color. Recent works leverage the discriminative visual cues to solve this problem, where three challenges exist as follows. First, vehicle features are misaligned and distorted because of the viewpoint variance. Second, the discriminative visual cues are usually subtle, which is easy to be diluted by the large area of non-discriminative regions in subsequent average pooling modules. Third, these discriminative visual cues are dynamic for the same image when it compares with different vehicle images. To tackle the above problems, we project the vehicle images from 2D to 3D space and rotate them to the same view, and leverage the viewpoint aligned features to enhance the discriminative parts for vehicle ReID. In detail, our method consists of three sub-modules, 1) The 3D viewpoint alignment module restores the 3D information of the vehicle from a single vehicle image, and then rotates and re-renders it under fixed viewpoints. It enables fine-grained viewpoint alignment and relieves the distortion of the vehicle caused by the viewpoint variation. 2) The discriminative parts enhancement module performs feature enhancement guided by the prior distribution of distinctive parts. 3) The adaptive duplicated parts suppression module guides the network to focus on the most discriminative parts, which not only prevents the dilution of the high responses but also provides explainable evidence. The experimental results reveal our method achieves new state-of-the-art on large scale vehicle ReID dataset.

A Dual-Branch Network for Few-Shot Vehicle Re-Identification With Enhanced Global and Local Features

Traditional vehicle Re-Identification (Re-ID) methods mainly rely on large-size training samples to achieve better results. However, obtaining abundant training samples is challenging for applications of these methods to few-shot vehicle Re-ID in real-world traffic scenes. To address this challenge, we propose a dual-branch network (DB-Net) for few-shot vehicle Re-ID with enhanced global and local features. Our proposed method reduces the dependence of vehicle Re-ID network on a large number of training samples by improving its feature expression ability and feature quality, rather than synthesizing vehicle images in traditional methods. The proposed DB-Net, composed of global and local branches, extracts global appearance features and local detail features of the vehicle. A global feature optimization module in the DB-Net mines and maintains more global semantic information using convolution and concat operations. And a feature screening module selects the most relevant local features based on Mutual Information and Shell Sorting to enhance local features. Additionally, a local attention module assigns adaptive weights to enhance salient local regions. Our approach is evaluated on a new dataset (Veri-FS) with small sample sizes and poor illumination conditions. It outperforms state-of-the-art methods on VehicleID, VeRi-776, and Veri-FS datasets, demonstrating its effectiveness in few-shot vehicle Re-ID.

Multi-branch mutual learning net for vehicle re-identification

Multi-branch mutual learning net for vehicle re-identification

Global and spatial multi-scale contexts fusion for vehicle re-identification

Global and spatial multi-scale contexts fusion for vehicle re-identification

Exploiting Multi-View Part-Wise Correlation via an Efficient Transformer for Vehicle Re-Identification

Exploiting Multi-View Part-Wise Correlation via an Efficient Transformer for Vehicle Re-Identification

Global–Local Discriminative Representation Learning Network for Viewpoint-Aware Vehicle Re-Identification in Intelligent Transportation

Global–Local Discriminative Representation Learning Network for Viewpoint-Aware Vehicle Re-Identification in Intelligent Transportation

Modality and Camera Factors Bi-Disentanglement for NIR-VIS Object Re-Identification

Aiming to match object identities across different modalities of images, the challenging task namely cross-modality object re-identification (NIR-VIS object Re-ID), has attracted increasing attention due to its wide application in low-light scenes. However, dramatic modality-dependent and camera-related discrepancies between Near-InfraRed-spectrum (NIR) and VISible-spectrum (VIS) images lead to a considerable intra-class gap in feature space. To address the problem, we propose a novel Modality and Camera factors Bi-Disentanglement (MCBD) model to learn modality-independent and camera-unrelated features for NIR-VIS object Re-ID. Our model consists of three key modules, including Confused Modality Generation (CMG), Modality-independent Information Distillation (MID), and Cameras Factor Disentanglement (CFD). Firstly, aiming at aligning image style between NIR and VIS data, the CMG utilizes a designed channel-interactive generator to generate confused modality images which preserves the structure information of original images. Besides, CMG is trained with confused adversarial learning which bridges the modality gap at the image level. Nevertheless, training the model with the confused modality images discards identity-related information such as color and contrast, which is not conducive to the extraction of distinctive features. To solve this problem, the MID is presented to distill out modality-independent information by feeding the original images to the model and reconstructing corresponding NIR and VIS modalities features to the confused modality images. Finally, due to the complexity of camera-related information in images, identity representation inevitably contains camera-related elements such as background and perspective information, which may interfere the matching process. To address this issue, the CFD is introduced to disentangle camera-related factors by the designed three-streams network and two factor decoupling losses, i.e., Camera-Camera Factor loss (CCF) and Identity-Camera Factor (ICF) loss. Comprehensive experiments are carried out on two cross-modality pedestrian Re-ID datasets and a cross-modality vehicle Re-ID dataset to demonstrate that the MCBD is effective in cross-modality object Re-ID task.

Robust Wheel Detection for Vehicle Re-Identification.

Vehicle re-identification is a demanding and challenging task in automated surveillance systems. The goal of vehicle re-identification is to associate images of the same vehicle to identify re-occurrences of the same vehicle. Robust re-identification of individual vehicles requires reliable and discriminative features extracted from specific parts of the vehicle. In this work, we construct an efficient and robust wheel detector that precisely locates and selects vehicular wheels from vehicle images. The associated hubcap geometry can hence be utilized to extract fundamental signatures from vehicle images and exploit them for vehicle re-identification. Wheels pattern information can yield additional information about vehicles in questions. To that end, we utilized a vehicle imagery dataset that has thousands of side-view vehicle collected under different illumination conditions and elevation angles. The collected dataset was used for training and testing the wheel detector. Experiments show that our approach could detect vehicular wheels accurately for 99.41% of the vehicles in the dataset.

Two-phase self-supervised pretraining for object re-identification

Self-supervised pretraining (e.g., MAE) based on reconstructing masked image patches has become increasingly popular in recent months. It commonly pretrains models on the large-scale ImageNet dataset with a considerably wider range of image categories, and then finetunes on downstream tasks such as classification, detection, segmentation, etc. However, we discover that for finetuning domain-specific tasks usually with a few or limited semantic spaces (e.g., object re-identification (ReID)), the model pretrained on a wider variety of sources (e.g., ImageNet) fails to be a good initialization. To address the problem, we propose a second-phase self-supervised pretraining on the specific domain, based on the self-supervised ImageNet pretraining models in the first phase. We perform studies on 2 domains of object ReID, i.e., person and vehicle ReID, where person ReID domain involves four datasets (Market-1501, DukeMTMC, MSMT17, Occluded-Duke) and vehicle ReID domain contains 2 datasets (VeRi-776, VehicleID). Through extensive experiments, we observe significant improvements in every single dataset based on the second-phase self-supervised pretraining over the entire unlabeled domain data. Specifically in person ReID task, compared to the self-supervised model in the first phase, our approach achieves +8.5%/+11.5%/+13.3%/+17.2% mAP improvements in Market-1501, DukeMTMC, MSMT17 and Occluded-Duke datasets, respectively. Furthermore, it also outperforms the supervised pretraining baselines, achieving improved performance by +1.5%/+4.3%/+3.9%/+4.2% mAP. We observe similar inspiring improvements in vehicle ReID tasks. Additionally, we also perform the second-phase pretraining on the specific tasks using its own unlabeled data, namely task-specific pretraining (TSP), which also consistently shows encouraging results across object ReID tasks.

A Dual Self-Attention mechanism for vehicle re-Identification

Vehicle re-identification has attracted tremendous attention from computer vision communities for its extensive applications in intelligent transportation and public security, while the high inter-class similarity and the large intra-class difference between vehicles bring out great challenges for re-identification (re-ID). To tackle these challenges, we learn from the self-attention mechanism in Natural Language Processing and propose a dual self-attention module to learn different regional dependencies: static self-attention for selectively refining semantic features and dynamic self-attention (called cross-region attention) for enhancing the spatial awareness of local feature. The static self-attention refines attended pixels within the entire image and salient regions, while the cross-region attention creatively captures the position-related regional dependencies for pixels within the windscreen area. These attention modules capture long-range dependencies and relative position information between different pixels or regions for vehicle feature learning globally and locally, realizing an efficient vehicle feature embedding by concatenating these augmented features for vehicle re-ID. Extensive experiments demonstrate the effectiveness and promising performance of our approach against the state-of-the-arts.

Complete solution for vehicle Re-ID in surround-view camera system

Vehicle re-identification (Re-ID) is a critical component of the autonomous driving perception system, and research in this area has accelerated in recent years. However, there is yet no perfect solution to the vehicle re-identification issue associated with the car’s surround-view camera system. Our analysis identifies two significant issues in the aforementioned scenario: (1) It is difficult to identify the same vehicle in many picture frames due to the unique construction of the fisheye camera. (2) The appearance of the same vehicle when seen via the surround vision system’s several cameras is rather different. To overcome these issues, we suggest an integrative vehicle Re-ID solution method. On the one hand, we provide a technique for determining the consistency of the tracking box drift with respect to the target. On the other hand, we combine a Re-ID network based on the attention mechanism with spatial limitations to increase performance in situations involving multiple cameras. Finally, our approach combines state-of-the-art accuracy with real-time performance. We will soon make the source code and annotated fisheye dataset available.

Learning for Data Synthesis: Joint Local Salient Projection and Adversarial Network Optimization for Vehicle Re-Identification

The problem of vehicle re-identification in surveillance scenarios has grown in popularity as a research topic. Deep learning has been successfully applied in re-identification tasks in the last few years due to its superior performance. However, deep learning approaches require a large volume of training data, and it is particularly crucial in vehicle re-identification tasks to have a sufficient amount of varying image samples for each vehicle. To collect and construct such a large and diverse dataset from natural environments is labor intensive. We offer a novel image sample synthesis framework to automatically generate new variants of training data by augmentation. First, we use an attention module to locate a local salient projection region in an image sample. Then, a lightweight convolutional neural network, the parameter agent network, is responsible for generating further image transformation states. Finally, an adversarial module is employed to ensure that the images in the dataset are distorted, while retaining their structural identities. This adversarial module helps to generate more appropriate and difficult training samples for vehicle re-identification. Moreover, we select the most difficult sample and update the parameter agent network accordingly to improve the performance. Our method draws on the adversarial networks strategy and the self-attention mechanism, which can dynamically decide the region selection and transformation degree of the synthesis images. Extensive experiments on the VeRi-776, VehicleID, and VERI-Wild datasets achieve good performance. Specifically, our method outperforms the state-of-the-art in MAP accuracy on VeRi-776 by 2.15%. Moreover, on VERI-Wil, a significant improvement of 7.15% is achieved.

Vehicle Re-identification method based on Swin-Transformer network

Vehicle Re-identification is to find out the exact vehicle captured by other cameras given a vehicle image. In natural traffic surveillance systems, vehicle re-identification can play a role in target vehicles localization, supervision, and criminal investigation. While current convolutional neural network-based approaches have been very successful, most studies consider learning representations from individual images, ignoring potential interactions between them. The Swin Transformer method currently shows excellent advantages in image classification. It can handle features at different scales like convolutional neural networks and make elements more closely related to each other, enhancing the learning of robust features and improving feature robustness and discrimination compared to convolutional neural nets. Therefore, this paper adopts the Swin Transformer method for vehicle re-identification and conducts experimental validation on two large vehicle datasets, VeRi-776, and VehicleID. The experimental results show that the recognition effect of this method is significantly better than existing vehicle re-identification methods, such as VAM, FDA-Net, TransReID, etc.