A Dual Self-Attention mechanism for vehicle re-Identification

Zhu, Wenqian; Wang, Zhongyuan; Wang, Xiaochen; Hu, Ruimin; Liu, Huikai; Liu, Cheng; Wang, Chao; Li, Dengshi

doi:10.1016/j.patcog.2022.109258

Cited by 19 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our method with some state-of-the-art (SOTA) approaches from the last three years, categorized into three groups: (1) Global feature-based (GF) methods, such as SN [13], VARID [12], VAT [18], and MsKAT [32], mainly concentrate on extracting whole representation for vehicle images. (2) Local feature-based (LF) methods, including DPGM [14], LG-CoT [36], HPGN [37], DFR [38], DSN [39], SFMNet [40], GiT [31], SOFCT [22], MART [41] integrate local features with the global feature to learn reliable vehicle representations. (3) Spatial-temporal (ST) methods, such as DPGM-ST [14] and DFR-ST [38], exploit extra timestamp and camera location information to enhance vehicle re-identification using visual features.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

An,

Zhang,

Shi

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

As a core technology in intelligent transportation systems, vehicle re-identification has attracted growing attention. Most existing methods use CNNs to extract global and local features from vehicle images and roughly integrate them for identifying vehicles, addressing intra-class similarity and inter-class difference. However, a significant challenge arises from redundant information between global and local features and possible misalignment among local features, resulting in suboptimal efficiency when combined. To further improve vehicle re-identification, we propose a stripe-assisted global transformer (SaGT) method, which leverages a dual-branch network based on transformers to learn a discriminative whole representation for each vehicle image. Specifically, one branch exploits a standard transformer layer to extract a global feature, while the other branch employs a stripe feature module (SFM) to construct stripe-based features. To further facilitate the effective incorporation of local information into the learning process of the global feature, we introduce a novel stripe-assisted global loss (SaGL), which combines ID losses to optimize the model. Considering redundancy, we only use the global feature for inference, as we enhance the whole representation with stripe-specific details. Finally, we introduce a spatial-temporal probability (STPro) to provide a complementary metric for robust vehicle re-identification. Extensive and comprehensive evaluations on two public datasets validate the effectiveness and superiority of our proposed method.

show abstract

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

An,

Zhang,

Shi

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…It can be mainly divided into supervised, metric and unsupervised learning methods. Methods based on supervised learning are further divided into methods based on global features [18,19], local features [20,21] and attention mechanism [22]. The goal of metric learning is to learn a mapping from the original features to the embedding space, such that the objects of the same category are close in the embedding space, and the distance between different categories is far away.…”

Section: Vehicle Re-identificationmentioning

confidence: 99%

Multi-Adjacent Camera-Based Dangerous Driving Trajectory Recognition for Ultra-Long Highways

Zhao,

Fu,

Yang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Fast detection of the trajectory is the key point to improve the further emergency proposal. Especially for ultra-long highway, prompt detection is labor-intensive. However, automatic detection relies on the accuracy and speed of vehicle detection, and tracking. In multi-camera surveillance system for ultra-long highways, it is often difficult to capture the same vehicle without intervals, which makes vehicle re-recognition crucial as well. In this paper, we present a framework that includes vehicle detection and tracking using improved DeepSORT, vehicle re-identification, feature extraction based on trajectory rules, and behavior recognition based on trajectory analysis. In particular, we design a network architecture based on DeepSORT with YOLOv5s to address the need for real-time vehicle detection and tracking in real-world traffic management. We further design an attribute recognition module to generate matching individuality attributes for vehicles to improve vehicle re-identification performance under multiple neighboring cameras. Besides, the use of bidirectional LSTM improves the accuracy of trajectory prediction, demonstrating its robustness to noise and fluctuations. The proposed model has a high advantage from the cumulative matching characteristic (CMC) curve shown and even improves above 15.38% compared to other state-of-the-art methods. The model developed on the local highway vehicle dataset is comprehensively evaluated, including abnormal trajectory recognition, lane change detection, and speed anomaly recognition. Experimental results demonstrate the effectiveness of the proposed method in accurately identifying various vehicle behaviors, including lane changes, stops, and even other dangerous driving behavior.

show abstract

“…Ref. [ 37 ] proposed a Dual Self-Attention Module to learn different region dependencies: static self-attention for selectively enhancing semantic features and dynamic self-attention (referred to as cross-region attention) to enhance spatial awareness of local features. Ref.…”

Section: Related Workmentioning

confidence: 99%

GLFNet: Combining Global and Local Information in Vehicle Re-Recognition

Yang,

Liu,

Huang

et al. 2024

Sensors

View full text Add to dashboard Cite

Vehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network extraction structure, either a single global or local measure. However, for vehicle images with high intra-class variance and low inter-class variance, exploring globally invariant features and discriminative local details is necessary. In this paper, we propose a Feature Fusion Network (GLFNet) that combines global and local information. It utilizes global features to enhance the differences between vehicles and employs local features to compactly represent vehicles of the same type. This enables the model to learn features with a large inter-class distance and small intra-class distance, significantly improving the model’s generalization ability. Experiments show that the proposed method is competitive with other advanced algorithms on three mainstream road traffic surveillance vehicle re-identification benchmark datasets.

show abstract

A Dual Self-Attention mechanism for vehicle re-Identification

Cited by 19 publications

References 22 publications

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

Multi-Adjacent Camera-Based Dangerous Driving Trajectory Recognition for Ultra-Long Highways

GLFNet: Combining Global and Local Information in Vehicle Re-Recognition

Contact Info

Product

Resources

About