Vehicle Re-identification Research Articles

Attention Mask-Based Network With Simple Color Annotation for UAV Vehicle Re-Identification

Vehicle re-identification (VeID) has attracted a growing research interest in recent years, and excellent performance has been shown with fixed traffic cameras. However, vehicle ReID in aerial images taken by unmanned aerial vehicles (UAVs), possessing both variable locations and special viewpoints, is still under-explored. Recent works tend to extract meaningful local features by careful annotation, which are effective but time-consuming. In order to extract discriminative features and avoid tedious annotating work, this letter develops an attention mask (AM)-based network with simple color annotation for object enhancement and background reduction. The network makes full use of deep features obtained by a pretrained color classification network and then utilizes principal component analysis (PCA) as a mapping function to achieve AMs without partial annotation. Besides, we introduce weighted triplet loss (WTL) function to deal with the problem of great similarity between classes caused by overlook views of UAVs. The loss function concentrates more on negative pairs to facilitate the identification ability of network. Rich experiments are conducted on both UAV dataset and surveillance dataset, and our method achieves competitive performance compared with recent ReID works.

V2I-CARLA: A Novel Dataset and a Method for Vehicle Reidentification-Based V2I Environment

Vehicle to infrastructure (V2I) is the current development trend for modern-day intelligent transportation systems and corresponds to an emerging topic in the field of automatic driving. In the perceptual task of road vehicle collaboration, vehicle cross-camera matching plays a key role in achieving automatic driving vehicles overview blind zone perception. Existing reidentification (REID) methods for vehicles cross-camera matching ignore the vehicle detailed characteristics. Considering the shortage of vision distance and a single perspective overlapping problem from the existing datasets, this article builds a vehicle REID dataset V2I-CARLA based on an automatic driving simulator, thereby matching the same vehicle successfully when the common feature is few at different perspectives. For the REID task, this article proposes a method for vehicle REID by introducing a pyramid method, which tends to obtain multiscale features of the vehicle under different cameras, capturing subtle features difference between the vehicles with a similar appearance. Simultaneously, circle loss is used in this work for network optimization, and the network is more distinguished. We evaluated our method on the V2I-CARLA and VeRi776 datasets. The experimental results show the superiority of our method, which renders significant improvement over the baseline on different datasets. The dataset V2I-CARLA is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Yx1322441675/V2I-CARLA</uri> .

Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond.

Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to use pseudo-labels generated by clustering algorithms to iteratively optimize the model on the target domain. However, a drawback to this is that noisy pseudo-labels generally cause trouble in learning. To address this problem, a mutual learning method by dual networks has been developed to produce reliable soft labels. However, as the two neural networks gradually converge, their complementarity is weakened and they likely become biased towards the same kind of noise. This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels. Specifically, we first introduce a parameter-free module, the WaveBlock, which creates a difference between features learned by two networks by waving blocks of feature maps differently. Then, an attention mechanism is leveraged to enlarge the difference created and discover more complementary features. Furthermore, two kinds of combination strategies, i.e. pre-attention and post-attention, are explored. Experiments demonstrate that the proposed method achieves state-of-the-art performance with significant improvements on multiple UDA person re-identification tasks. We also prove the generality of the proposed method by applying it to vehicle re-identification and image classification tasks. Our codes and models are available at: AWB.

Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-Identification.

Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsupervised Re-ID is clustering-based, which generates pseudo labels by clustering and uses the pseudo labels to train a Re-ID model iteratively. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the intra-cluster variance mainly caused by the change of cameras. To address this issue, we propose to split each single cluster into multiple proxies according to camera views. The camera-aware proxies explicitly capture local structures within clusters, by which the intra-ID variance and inter-ID similarity can be better tackled. Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results. The offline association directly associates proxies according to the clustering and splitting results, while the online strategy dynamically associates proxies in terms of up-to-date features to reduce the noise caused by the delayed update of pseudo labels. The combination of two losses enables us to train a desirable Re-ID model. Extensive experiments on three person Re-ID datasets and one vehicle Re-ID dataset show that our proposed approach demonstrates competitive performance with state-of-the-art methods. Code will be available at: https://github.com/Terminator8758/O2CAP.

Trends in Vehicle Re-Identification Past, Present, and Future: A Comprehensive Review

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan cities, it gained significant attention. Vehicle re-id matches targeted vehicle over non-overlapping views in multiple camera network. However, it becomes more difficult due to inter-class similarity, intra-class variability, viewpoint changes, and spatio-temporal uncertainty. In order to draw a detailed picture of vehicle re-id research, this paper gives a comprehensive description of the various vehicle re-id technologies, applicability, datasets, and a brief comparison of different methodologies. Our paper specifically focuses on vision-based vehicle re-id approaches, including vehicle appearance, license plate, and spatio-temporal characteristics. In addition, we explore the main challenges as well as a variety of applications in different domains. Lastly, a detailed comparison of current state-of-the-art methods performances over VeRi-776 and VehicleID datasets is summarized with future directions. We aim to facilitate future research by reviewing the work being done on vehicle re-id till to date.

Multi‐label based view learning for vehicle re‐identification

Due to the high similarity of different vehicles with similar appearances and the great diversity of camera viewpoints, vehicle re-identification (ReID) is still a challenging task. It commonly maps query set image into a high dimensional embedding space and then retrieve gallery vehicle images according to the distance. In this letter, a multi-label based view learning (MLVL) model to enhance the distinguishability of intra-class and inter-class through multiple labels learning, and decrease the distance of intra-class features caused by multi-view appearances of vehicles. Specifically, the model includes two main parts. First, the vehicle orientation estimation module is responsible for detecting key-points of the vehicle and predicting its orientation, which provides the orientation label for the multi-label based learning network to enhance view-invariant representation. Second, a novel dual-triplet and quadruplet loss function is designed to optimise intra-class and inter-class distance with the help of multi-label information, i.e. vehicle colour, type and orientation. In particular, a multi-label based sampler is proposed to generate training mini-batches instead of random sampler. Extensive experiments results show that the proposed MLVL model achieves 5.6 % $\%$ mAP improvement on VeRi-776 and 1.9 % $\%$ on VERI-Wild datasets compared with baseline model.

Efficient but lightweight network for vehicle re-identification with center-constraint loss

Efficient but lightweight network for vehicle re-identification with center-constraint loss

Learning latent features with local channel drop network for vehicle re-identification

Vehicle re-identification targets to find the target vehicle images in a large dataset which is composed of vehicle images from multiple non-overlapping cameras. Due to the various illumination, viewpoints and resolutions, it is challenging to find the right vehicle images accurately. Most existing works put emphasis on learning strong features by exploiting the attention parts in vehicle images, which leads to some small important cues being suppressed by these significant parts. Hence, a local channel drop network (LCDNet) is proposed in this paper, which focuses on seeking the latent features by releasing the constraint of most attentive features. Specially, besides the normal local feature learning network, LCDNet consists of an attentive local feature learning branch that drops some regions to promote learning the attentive features of local regions. Besides, the batch ranking loss is introduced to split the samples into two groups in a batch and regularize them by enforcing a margin, which ensures the model to learn meaningful features to distinct vehicles. Moreover, to further calculate the similarity of various images, the paper proposes a multi-distance based ranking method to achieve more accurate results. Experiments on several benchmark datasets validate the effectiveness of the proposed method.

Manifold-based aggregation clustering for unsupervised vehicle re-identification

Most vehicle re-identification (V-reID) approaches are based on supervised learning methods which require a considerable amount of tedious and impractical annotations. In this paper, we propose a novel unsupervised V-reID approach based on Manifold-based Aggregation Clustering (MAC) with the unknown number of clusters. The proposed MAC is implemented by alternatively conducting two modules, i.e., deep feature learning module and aggregation clustering module. Specifically, deep feature learning module is responsible for training a convolutional neural network to encourage deep features to be close to the centroids of corresponding clusters which are yielded by an aggregation clustering mechanism based on manifold distance in the feature space. Moreover, the classification-agglomeration loss and manifold-based seeds searching criterion are proposed to improve the discriminative power of the learned features and deal with the problem of varied visual appearance respectively. Note that both annotations and even the certain number of vehicle identities are unknown for the proposed method, which is totally consistent with the real-world unsupervised V-reID condition. Extensive experiments on VehicleID and Veri-776 benchmark datasets show that the proposed method outperforms the state-of-the-art unsupervised V-reID approaches.

A vehicle re-identification framework based on the improved multi-branch feature fusion network

Vehicle re-identification (re-id) aims to solve the problems of matching and identifying the same vehicle under the scenes across multiple surveillance cameras. For public security and intelligent transportation system (ITS), it is extremely important to locate the target vehicle quickly and accurately in the massive vehicle database. However, re-id of the target vehicle is very challenging due to many factors, such as the orientation variations, illumination changes, occlusion, low resolution, rapid vehicle movement, and amounts of similar vehicle models. In order to resolve the difficulties and enhance the accuracy for vehicle re-id, in this work, we propose an improved multi-branch network in which global–local feature fusion, channel attention mechanism and weighted local feature are comprehensively combined. Firstly, the fusion of global and local features is adopted to obtain more information of the vehicle and enhance the learning ability of the model; Secondly, the channel attention module in the feature extraction branch is embedded to extract the personalized features of the targeting vehicle; Finally, the background and noise information on feature extraction is controlled by weighted local feature. The results of comprehensive experiments on the mainstream evaluation datasets including VeRi-776, VRIC, and VehicleID indicate that our method can effectively improve the accuracy of vehicle re-identification and is superior to the state-of-the-art methods.

Dual attention granularity network for vehicle re-identification

Dual attention granularity network for vehicle re-identification

Lightweight Method for Vehicle Re-identification Using Reranking Algorithm Based on Topology Information of Surveillance Network

Lightweight Method for Vehicle Re-identification Using Reranking Algorithm Based on Topology Information of Surveillance Network

AttributeNet: Attribute enhanced vehicle re-identification

Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints. Many works explore attribute clues to enhance V-ReID; however, there is usually a lack of effective interaction between the attribute-related modules and final V-ReID objective. In this work, we propose a new method to efficiently explore discriminative information from vehicle attributes (for instance, color and type). We introduce AttributeNet (ANet) that jointly extracts identity-relevant features and attribute features. We enable the interaction by distilling the ReID-helpful attribute feature and adding it into the general ReID feature to increase the discrimination power. Moreover, we propose a constraint, named Amelioration Constraint (AC), which encourages the feature after adding attribute features onto the general ReID feature to be more discriminative than the original general ReID feature. We validate the effectiveness of our framework on three challenging datasets. Experimental results show that our method achieves the state-of-the-art performance.

Vehicle Reidentification Based on MAPANet and k-Reciprocal Encoding

Vehicle reidentification has important applications in intelligent monitoring systems. However, due to many factors, such as inaccurate vehicle image detection and viewing angle changes, distinguishing features cannot be effectively obtained when the vehicle is reidentified. To improve the recognition ability and robustness of vehicle reidentification, this study proposes a new multiattention part alignment network (MAPANet). The network uses different channels in the feature map to perceive different characteristics of the image clustering of the channels and achieves fine-grained attention to the vehicle. It can automatically locate the distinguishing subregions in the vehicle image and avoid the need for a large number of additional manual pretreatment steps. Moreover, an unsupervised reranking method based on multiple metrics is proposed. The k-reciprocal encoding algorithm can optimize the performance of the sorted list in the reordering problem, recalculate the interclass and intraclass distances of vehicle pictures, and improve sorting results. The experiments in this paper are carried out on the VeRi-776 and VehicleID datasets, and the mean average precision (mAP) results on the two datasets are 72.83% and 75.25%, respectively.

A deep neural network-based vehicle re-identification method for bridge load monitoring

The accurate tracking of vehicle loads is essential for the condition assessment of bridge structures. In recent years, a computer vision method that is based on multiple sources of data from monitoring cameras and weight-in-motion (WIM) systems has become a promising strategy in bridge vehicle load identification for structural health monitoring (SHM) and has attracted increasing attention. The implementation of vehicle re-identification, namely, the identification of the same vehicle from images that were captured at different locations or time instants, is the key topic of this study. In this study, a vehicle re-identification method that is based on HardNet, a deep convolutional neural network (CNN) specialized in picking up local image features, is proposed. First, we obtain the vehicle point feature positions in the image through feature detection. Then, the HardNet is employed to encode the point feature image patches into deep learning feature descriptors. Re-identification of the target vehicle is achieved by matching the encoded descriptors between two images, which are robust toward scaling, rotation, and other types of noises. A comparison study of the proposed method with three published vehicle re-identification methods is performed using vehicle image data from a real bridge, and the superior performance of our proposed method is demonstrated.

Vehicle re-identification method based on global and local feature fusion

Vehicle re-identification is still an issue worth discussing due to change of view, light and angle changes. At present, the key of vehicle reidentification research is to solve the problems that the difference between the same class is big and the difference between different classes is small. For the study, a vehicle re-identification method ground on view classification is proposed.The vehicle images are divided into four views, namely, front, rear, top and side, and local features are extracted by the segmented view information. Using the CNN feature extractor, the global feature representation with car ID attribute is learned. We have done experiments with the VERI-776 data sets. The mean average accuracy of 78.13% is obtained, which proves the effectiveness of the method.

LABNet: Local graph aggregation network with class balanced loss for vehicle re-identification

Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints. Recent methods based on deep learning utilize a global average pooling layer after the backbone feature extractor, however, this ignores any spatial reasoning on the feature map. In this paper, we propose local graph aggregation on the backbone feature map, to learn associations of local information and hence improve feature learning as well as reduce the effects of partial occlusion and background clutter. Our local graph aggregation network considers spatial regions of the feature map as nodes and builds a local neighborhood graph that performs local feature aggregation before the global average pooling layer. We further utilize a batch normalization layer to improve the system effectiveness. Additionally, we introduce a class balanced loss to compensate for the imbalance in the sample distributions found in the most widely used vehicle re-identification datasets. Finally, we evaluate our method in three popular benchmarks and show that our approach outperforms many state-of-the-art methods.

Automating Road Traffic Monitoring Using Computer Vision

The objective of the article is to describe application of computer vision and artificial intelligence technologies for solving the problems of road infrastructure design.The article evaluates the traditional methods of quantitative and qualitative analysis of traffic flows in terms of labour intensity and accuracy using the method of comparative analysis, the advantages and disadvantages of the considered methods are indicated. A new method of traffic flow analysis using unmanned aerial vehicles and computer vision technology based on convolutional neural networks is proposed. The considered method makes it possible to fully automate collection and analysis of data on traffic flows. The article describes the first application of the proposed method when performing transport and economic surveys within the framework of the design of «Northern bypass of the city of Perm». The advantages of the applied method in relation to the traditional ones are described. To implement this project, software was developed for analysing traffic flows using video materials.Further, traffic monitoring is considered, its goals and objectives are described, the necessary functionality of the road traffic monitoring automation system is indicated, the traffic parameters that it should determine are listed. The methodology for implementation of an automated traffic monitoring system based on video materials on a section of the road is considered.A presented project of a traffic monitoring system makes it possible to extend the previously considered approach to the entire road network. Technologies are described that make it possible to implement this system based on video analytics of materials from CCTV cameras. A method for vehicle re-identification is proposed, and the implementation of this method is demonstrated. The method allows building a correspondence matrix of vehicles recorded by CCTV cameras located on different segments of the road network, as well as determining all traffic parameters for the entire street and road network.The conclusions outline the prospects for development of the developed software in terms of application in intelligent transport systems.

Viewpoint robust knowledge distillation for accelerating vehicle re-identification

Vehicle re-identification is a challenging task that matches vehicle images captured by different cameras. Recent vehicle re-identification approaches exploit complex deep networks to learn viewpoint robust features for obtaining accurate re-identification results, which causes large computations in their testing phases to restrict the vehicle re-identification speed. In this paper, we propose a viewpoint robust knowledge distillation (VRKD) method for accelerating vehicle re-identification. The VRKD method consists of a complex teacher network and a simple student network. Specifically, the teacher network uses quadruple directional deep networks to learn viewpoint robust features. The student network only contains a shallow backbone sub-network and a global average pooling layer. The student network distills viewpoint robust knowledge from the teacher network via minimizing the Kullback-Leibler divergence between the posterior probability distributions resulted from the student and teacher networks. As a result, the vehicle re-identification speed is significantly accelerated since only the student network of small testing computations is demanded. Experiments on VeRi776 and VehicleID datasets show that the proposed VRKD method outperforms many state-of-the-art vehicle re-identification approaches with better accurate and speed performance.

Generalized multiple sparse information fusion for vehicle re-identification

Vehicle re-identification (reID) aims to search the target vehicle in a non-overlapping multi-camera network, which is important for the intelligent analysis in large scale of surveillance videos. Many existing methods have employed various techniques to achieve discriminative information. However, those methods always focus on the description of one view for the same vehicle images. Hence, a generated multiple sparse information fusion method is proposed for exploiting latent features from multi-views, which employs three different deep networks to extract multiple features from coarse to fine. And these features are regarded as multi-view features. Besides, to fuse these features reasonably, the paper transfers various features into a common space for better seeking distinctive features. Especially, besides ResNet, two feature learning networks are proposed to learn different features, respectively. One is designed to learn robust feature by dropping some features randomly when training the reID model. Another is to combine various salient features from different layers, which forms strong features for the reID task. Moreover, comprehensive experimental results have demonstrated that our proposed method can achieve competitive performances on benchmark datasets VehicleID and VeRi-776.