Vehicle Re-Identification Based on Global Relational Attention and Multi-Granularity Feature Learning

Tian, Xun; Pang, Xiyu; Jiang, Gangwu; Meng, Qinglan; Zheng, Yanli

doi:10.1109/access.2022.3150411

Cited by 9 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By mining distinguishing features, the difficulty of distinguishing vehicles with similar appearance is solved. Tian et al [116] proposed an adaptive attention network. The network captures the global structural information of the vehicle through a global relational attention module to improve the accuracy of re-ID.…”

Section: Vehicle Re-identification Based On Attention Mechanismmentioning

confidence: 99%

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Fei

Han

2023

Sensors

View full text Add to dashboard Cite

Multi-Objective Multi-Camera Tracking (MOMCT) is aimed at locating and identifying multiple objects from video captured by multiple cameras. With the advancement of technology in recent years, it has received a lot of attention from researchers in applications such as intelligent transportation, public safety and self-driving driving technology. As a result, a large number of excellent research results have emerged in the field of MOMCT. To facilitate the rapid development of intelligent transportation, researchers need to keep abreast of the latest research and current challenges in related field. Therefore, this paper provide a comprehensive review of multi-object multi-camera tracking based on deep learning for intelligent transportation. Specifically, we first introduce the main object detectors for MOMCT in detail. Secondly, we give an in-depth analysis of deep learning based MOMCT and evaluate advanced methods through visualisation. Thirdly, we summarize the popular benchmark data sets and metrics to provide quantitative and comprehensive comparisons. Finally, we point out the challenges faced by MOMCT in intelligent transportation and present practical suggestions for the future direction.

show abstract

Section: Vehicle Re-identification Based On Attention Mechanismmentioning

confidence: 99%

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Fei

Han

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The research seems mainly focused in two methods: attention mechanisms and metrics learning. The study by [61] is an example of the first ones. The authors propose a "three-branch adaptive attention network for vehicle Re-ID".…”

Section: Up-to-date Solutionsmentioning

confidence: 99%

“…Metrics mAP r@ank1 r@ank5 GRMF [61] Multi-granularity feature learning 0.882 0.957 0.991 VARID [62] Inter-and intra-view triplet loss 0.793 0.962 0.992 SN++ [63] Support neighbours loss 0.757 0.951 0.981 Meng et al [64] 3D viewpoint alignment 0.832 0.987 0.992…”

Section: Model Characteristicsmentioning

confidence: 99%

“…Right after the first YOLOv5 (the one at the entrance of the entire system) extracts the ROI of the car detected, the image is cropped and becomes the input of the re-identification net. This cropped image goes through the backbone and the aggregation layers [61] and generates a 4096 features vector, and this re-identification is concluded by calculating the Euclidean distance between the 4096-feature vectors from the visual recognition model. Each of the processed images will have its corresponding feature vector, which is compared with the features vector of the objective vehicle, to calculate the distance.…”

Section: Vehicle Re-identificationmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Video Surveillance Systems for Vehicle Identification Based on Multinet Architecture

2022

View full text Add to dashboard Cite

Security cameras have been proven to be particularly useful in preventing and combating crime through identification tasks. Here, two areas can be mainly distinguished: person and vehicle identification. Automatic license plate readers are the most widely used tool for vehicle identification. Although these systems are very effective, they are not reliable enough in certain circumstances. For example, due to traffic jams, vehicle position or weather conditions, the sensors cannot capture an image of the entire license plate. However, there is still a lot of additional information in the image which may also be of interest, and that needs to be analysed quickly and accurately. The correct use of the processing mechanisms can significantly reduce analysis time, increasing the efficiency of video cameras significantly. To solve this problem, we have designed a solution based on two technologies: license plate recognition and vehicle re-identification. For its development and testing, we have also created several datasets recreating a real environment. In addition, during this article, it is also possible to read about some of the main artificial intelligence techniques for these technologies, as they have served as the starting point for this research.

show abstract

“…The main task in vehicle re-identification is to learn a feature representation with a small distance between the same vehicle in different views and a large distance between different vehicles [3]. During the decades, the paradigms of vehicle re-identification can be divided into supervised methods [4][5][6] and unsupervised approaches [7][8][9] according to whether the label of training data is involved or not. The supervised vehicle re-identification relies on the labels of the vehicle images, and approximates the fixed distribution of the training samples [10,11].…”

Section: Introductionmentioning

confidence: 99%

Focus on the Visible Regions: Semantic-Guided Alignment Model for Occluded Person Re-Identification

Yang

Wang

Fang

et al. 2020

Sensors

View full text Add to dashboard Cite

The occlusion problem is very common in pedestrian retrieval scenarios. When persons are occluded by various obstacles, the noise caused by the occluded area greatly affects the retrieval results. However, many previous pedestrian re-identification (Re-ID) methods ignore this problem. To solve it, we propose a semantic-guided alignment model that uses image semantic information to separate useful information from occlusion noise. In the image preprocessing phase, we use a human semantic parsing network to generate probability maps. These maps show which regions of images are occluded, and the model automatically crops images to preserve the visible parts. In the construction phase, we fuse the probability maps with the global features of the image, and semantic information guides the model to focus on visible human regions and extract local features. During the matching process, we propose a measurement strategy that only calculates the distance of public areas (visible human areas on both images) between images, thereby suppressing the spatial misalignment caused by non-public areas. Experimental results on a series of public datasets confirm that our method outperforms previous occluded Re-ID methods, and it achieves top performance in the holistic Re-ID problem.

show abstract

Vehicle Re-Identification Based on Global Relational Attention and Multi-Granularity Feature Learning

Cited by 9 publications

References 44 publications

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Intelligent Video Surveillance Systems for Vehicle Identification Based on Multinet Architecture

Focus on the Visible Regions: Semantic-Guided Alignment Model for Occluded Person Re-Identification

Contact Info

Product

Resources

About