Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of int...Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.展开更多
In this paper,we provide a new approach for intelligent traffic transportation in the intelligent vehicular networks,which aims at collecting the vehicles’locations,trajectories and other key driving parameters for t...In this paper,we provide a new approach for intelligent traffic transportation in the intelligent vehicular networks,which aims at collecting the vehicles’locations,trajectories and other key driving parameters for the time-critical autonomous driving’s requirement.The key of our method is a multi-vehicle tracking framework in the traffic monitoring scenario..Our proposed framework is composed of three modules:multi-vehicle detection,multi-vehicle association and miss-detected vehicle tracking.For the first module,we integrate self-attention mechanism into detector of using key point estimation for better detection effect.For the second module,we apply the multi-dimensional information for robustness promotion,including vehicle re-identification(Re-ID)features,historical trajectory information,and spatial position information For the third module,we re-track the miss-detected vehicles with occlusions in the first detection module.Besides,we utilize the asymmetric convolution and depth-wise separable convolution to reduce the model’s parameters for speed-up.Extensive experimental results show the effectiveness of our proposed multi-vehicle tracking framework.展开更多
Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of backgrou...Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of background interference caused by continuous scene variations.The recently proposed segment anything model(SAM)has demonstrated exceptional performance in zero-shot segmentation tasks.The combination of SAM and vehicle Re-ID models can achieve efficient separation of vehicle identity and background information.This paper proposes a method that combines SAM-driven mask autoencoder(MAE)pre-training and backgroundaware meta-learning for unsupervised vehicle Re-ID.The method consists of three sub-modules.First,the segmentation capacity of SAM is utilized to separate the vehicle identity region from the background.SAM cannot be robustly employed in exceptional situations,such as those with ambiguity or occlusion.Thus,in vehicle Re-ID downstream tasks,a spatiallyconstrained vehicle background segmentation method is presented to obtain accurate background segmentation results.Second,SAM-driven MAE pre-training utilizes the aforementioned segmentation results to select patches belonging to the vehicle and to mask other patches,allowing MAE to learn identity-sensitive features in a self-supervised manner.Finally,we present a background-aware meta-learning method to fit varying degrees of background interference in different scenarios by combining different background region ratios.Our experiments demonstrate that the proposed method has state-of-the-art performance in reducing background interference variations.展开更多
Magnetic sensors can be applied in vehicle recognition.Most of the existing vehicle recognition algorithms use one sensor node to measure a vehicle’s signature.However,vehicle speed variation and environmental distur...Magnetic sensors can be applied in vehicle recognition.Most of the existing vehicle recognition algorithms use one sensor node to measure a vehicle’s signature.However,vehicle speed variation and environmental disturbances usually cause errors during such a process.In this paper we propose a method using multiple sensor nodes to accomplish vehicle recognition.Based on the matching result of one vehicle’s signature obtained by different nodes,this method determines vehicle status and corrects signature segmentation.The co-relationship between signatures is also obtained,and the time offset is corrected by such a co-relationship.The corrected signatures are fused via maximum likelihood estimation,so as to obtain more accurate vehicle signatures.Examples show that the proposed algorithm can provide input parameters with higher accuracy.It improves the average accuracy of vehicle recognition from 94.0%to 96.1%,and especially the bus recognition accuracy from 77.6%to 92.8%.展开更多
As an emerging visual task,vehicle re-identification refers to the identification of the same vehicle across multiple cameras.Herein,we propose a novel vehicle re-identification method that uses an improved ResNet-50 ...As an emerging visual task,vehicle re-identification refers to the identification of the same vehicle across multiple cameras.Herein,we propose a novel vehicle re-identification method that uses an improved ResNet-50 architecture and utilizes the topology information of a surveillance network to rerank the final results.In the training stage,we apply several data augmentation approaches to expand our training data and increase their diversity in a cost-effective manner.We reform the original RestNet-50 architecture by adding non-local blocks to implement the attention mechanism and replacing part of the batch normalization operations with instance batch normalization.After obtaining preliminary results from the proposed model,we use the reranking algorithm,whose core function is to improve the similarity scores of all images on the most likely path that the vehicle tends to appear to optimize the final results.Compared with most existing state-of-the-art methods,our method is lighter,requires less data annotation,and offers competitive performance.展开更多
Existing methods of vehicle re-identification(ReID)focus on training robust models on the fixed data while ignore the diversity in the training data,which limits generalization ability of the models.In this paper,it p...Existing methods of vehicle re-identification(ReID)focus on training robust models on the fixed data while ignore the diversity in the training data,which limits generalization ability of the models.In this paper,it proposes an occlusion based discriminative feature mining(ODFM)method for vehicle re-identification,which increases the diversity of the training set by synthesizing occlusion samples,to simulate the occlusion problem in the real scene.To better train the ReID model on the data with large occlusions,an attention mechanism was introduced in the mainstream network to learn the discriminative features for vehicle images.Experimental results on two public ReID datasets,VeRi-776 and VehicleID verify the effectiveness of the proposed method comparing to the state-of-the-art methods.展开更多
基金This work was supported,in part,by the National Nature Science Foundation of China under Grant Numbers 61502240,61502096,61304205,61773219in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401+1 种基金in part,by the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant Numbers SJCX21_0363in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘Vehicle re-identification(ReID)aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario.It has gradually become a core technology of intelligent transportation system.Most existing vehicle re-identification models adopt the joint learning of global and local features.However,they directly use the extracted global features,resulting in insufficient feature expression.Moreover,local features are primarily obtained through advanced annotation and complex attention mechanisms,which require additional costs.To solve this issue,a multi-feature learning model with enhanced local attention for vehicle re-identification(MFELA)is proposed in this paper.The model consists of global and local branches.The global branch utilizes both middle and highlevel semantic features of ResNet50 to enhance the global representation capability.In addition,multi-scale pooling operations are used to obtain multiscale information.While the local branch utilizes the proposed Region Batch Dropblock(RBD),which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions.Then features from both branches are combined to provide a more comprehensive and distinctive feature representation.Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.
基金This work was supported in part by the Beijing Natural Science Foundation(L191004)the National Natural Science Foundation of China under No.61720106007 and No.61872047+1 种基金the Beijing Nova Program under No.Z201100006820124the Funds for Cre ative Research Groups of China under No.61921003,and the 111 Project(B18008).
文摘In this paper,we provide a new approach for intelligent traffic transportation in the intelligent vehicular networks,which aims at collecting the vehicles’locations,trajectories and other key driving parameters for the time-critical autonomous driving’s requirement.The key of our method is a multi-vehicle tracking framework in the traffic monitoring scenario..Our proposed framework is composed of three modules:multi-vehicle detection,multi-vehicle association and miss-detected vehicle tracking.For the first module,we integrate self-attention mechanism into detector of using key point estimation for better detection effect.For the second module,we apply the multi-dimensional information for robustness promotion,including vehicle re-identification(Re-ID)features,historical trajectory information,and spatial position information For the third module,we re-track the miss-detected vehicles with occlusions in the first detection module.Besides,we utilize the asymmetric convolution and depth-wise separable convolution to reduce the model’s parameters for speed-up.Extensive experimental results show the effectiveness of our proposed multi-vehicle tracking framework.
基金supported by the National Natural Science Foundation of China under Grant Nos.62076117 and 62166026the Jiangxi Nos.20224BAB212011,20232BAB212008,and 20232BAB202051.
文摘Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of background interference caused by continuous scene variations.The recently proposed segment anything model(SAM)has demonstrated exceptional performance in zero-shot segmentation tasks.The combination of SAM and vehicle Re-ID models can achieve efficient separation of vehicle identity and background information.This paper proposes a method that combines SAM-driven mask autoencoder(MAE)pre-training and backgroundaware meta-learning for unsupervised vehicle Re-ID.The method consists of three sub-modules.First,the segmentation capacity of SAM is utilized to separate the vehicle identity region from the background.SAM cannot be robustly employed in exceptional situations,such as those with ambiguity or occlusion.Thus,in vehicle Re-ID downstream tasks,a spatiallyconstrained vehicle background segmentation method is presented to obtain accurate background segmentation results.Second,SAM-driven MAE pre-training utilizes the aforementioned segmentation results to select patches belonging to the vehicle and to mask other patches,allowing MAE to learn identity-sensitive features in a self-supervised manner.Finally,we present a background-aware meta-learning method to fit varying degrees of background interference in different scenarios by combining different background region ratios.Our experiments demonstrate that the proposed method has state-of-the-art performance in reducing background interference variations.
基金supported by the National Natural Science Foundation of China(No.61104164)the National High-Tech R&D Program(863)of China(No.2012AA112401)
文摘Magnetic sensors can be applied in vehicle recognition.Most of the existing vehicle recognition algorithms use one sensor node to measure a vehicle’s signature.However,vehicle speed variation and environmental disturbances usually cause errors during such a process.In this paper we propose a method using multiple sensor nodes to accomplish vehicle recognition.Based on the matching result of one vehicle’s signature obtained by different nodes,this method determines vehicle status and corrects signature segmentation.The co-relationship between signatures is also obtained,and the time offset is corrected by such a co-relationship.The corrected signatures are fused via maximum likelihood estimation,so as to obtain more accurate vehicle signatures.Examples show that the proposed algorithm can provide input parameters with higher accuracy.It improves the average accuracy of vehicle recognition from 94.0%to 96.1%,and especially the bus recognition accuracy from 77.6%to 92.8%.
文摘As an emerging visual task,vehicle re-identification refers to the identification of the same vehicle across multiple cameras.Herein,we propose a novel vehicle re-identification method that uses an improved ResNet-50 architecture and utilizes the topology information of a surveillance network to rerank the final results.In the training stage,we apply several data augmentation approaches to expand our training data and increase their diversity in a cost-effective manner.We reform the original RestNet-50 architecture by adding non-local blocks to implement the attention mechanism and replacing part of the batch normalization operations with instance batch normalization.After obtaining preliminary results from the proposed model,we use the reranking algorithm,whose core function is to improve the similarity scores of all images on the most likely path that the vehicle tends to appear to optimize the final results.Compared with most existing state-of-the-art methods,our method is lighter,requires less data annotation,and offers competitive performance.
基金in part by the National Natural Science Foundationof China (Nos. 61976002)Hainan Provincial Natural Science Foundation (GrantNo. 117063)+1 种基金the Natural Science Foundation of Anhui Higher Education Institutions of China(KJ2019A0033)the National Laboratory of Pattern Recognition (NLPR) (201900046).
文摘Existing methods of vehicle re-identification(ReID)focus on training robust models on the fixed data while ignore the diversity in the training data,which limits generalization ability of the models.In this paper,it proposes an occlusion based discriminative feature mining(ODFM)method for vehicle re-identification,which increases the diversity of the training set by synthesizing occlusion samples,to simulate the occlusion problem in the real scene.To better train the ReID model on the data with large occlusions,an attention mechanism was introduced in the mainstream network to learn the discriminative features for vehicle images.Experimental results on two public ReID datasets,VeRi-776 and VehicleID verify the effectiveness of the proposed method comparing to the state-of-the-art methods.