Efficient and Deep Vehicle Re-Identification Using Multi-Level Feature Extraction

Zakria,; Cai, Jingye; Deng, Jianhua; Aftab, Muhammad Umar; Khokhar, Muhammad Saddam; Kumar, Rajesh

doi:10.3390/app9071291

Cited by 27 publications

(13 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many vehicle re-identification methods are based on the Siamese Network. Zakria et al [10] proposed a novel vehicle re-identification approach, first they chose the vehicle from a gallery set according to appearance, and then verified the chosen vehicle's license plates with a query image to identify the targeted vehicle. In the model, the global channel extracted the feature vector from the whole vehicle image, and the local region channel extracted more discriminative and salient features from different regions.…”

Section: ) Vehicle Re-identification Methods Based On Metric Learningmentioning

confidence: 99%

“…tracked across multiple cameras, which saves labor and cost. Besides, vehicle re-identification systems have many possible practical applications, such as intelligent parking, suspicious vehicle tracking, vehicle event detection, vehicle counting, and automatic charging [10]. Furthermore, it has a vital role in applications such as live monitoring or multi-view vehicle tracking for urban surveillance, therefore, vehicle reidentification technology is crucial to the future development of the Internet of things, as well as the construction of intelligent transportation system and smart city.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Vehicle Re-Identification Based on Deep Learning

2019

View full text Add to dashboard Cite

Vehicle re-identification is one of the core technologies of intelligent transportation systems, and it is crucial for the construction of smart cities. With the rapid development of deep learning, vehicle re-identification technologies have made significant progress in recent years. Therefore, making a comprehensive survey about the vehicle re-identification methods based on deep learning is quite indispensable. There are mainly five types of deep learning-based methods designed for vehicle re-identification, i.e. methods based on local features, methods based on representation learning, methods based on metric learning, methods based on unsupervised learning, and methods based on attention mechanism. The major contributions of our survey come from three aspects. First, we give a comprehensive review of the current five types of deep learning-based methods for vehicle re-identification, and we further compare them from characteristics, advantages, and disadvantages. Second, we sort out vehicle public datasets and compare them from multiple dimensions. Third, we further discuss the challenges and possible research directions of vehicle re-identification in the future based on our survey. INDEX TERMS Deep learning, intelligent transportation system, vehicle re-identification, vehicle public datasets.

show abstract

Section: ) Vehicle Re-identification Methods Based On Metric Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Survey of Vehicle Re-Identification Based on Deep Learning

2019

View full text Add to dashboard Cite

show abstract

“…To achieve accurate classification of COVID-19 pneumonia lesion in CT scans, we experiment using the 2D convolutional neural network, taking advantage of its invariant property [31]. With CNN's hierarchical and connectivity pattern of feature extraction [32], each layer of the model is able to accomplish extensive assembling of complex patterns based on their receptive field [33]. Inspired by the VGG CNN framework, we implemented our COVID-19-Net using the VGG16 architecture [34].…”

Section: Covid-19-netmentioning

confidence: 99%

Transfer Learning and Semisupervised Adversarial Detection and Classification of COVID‐19 in CT Images

et al. 2021

View full text Add to dashboard Cite

The ongoing coronavirus 2019 (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in a severe ramification on the global healthcare system, principally because of its easy transmission and the extended period of the virus survival on contaminated surfaces. With the advances in computer-aided diagnosis and artificial intelligence, this paper presents the application of deep learning and adversarial network for the automatic identification of COVID-19 pneumonia in computed tomography (CT) scans of the lungs. The complexity and time limitation of the reverse transcription-polymerase chain reaction (RT-PCR) swab test makes it disadvantageous to depend solely on as COVID-19’s central diagnostic mechanism. Since CT imaging systems are of low cost and widely available, we demonstrate that the drawback of the RT-PCR can be alleviated with a faster, automated, and reduced contact diagnostic process via the use of a neural network model for the classification of infected and noninfected CT scans. In our proposed model, we explore the benefit of transfer learning as a means of resolving the problem of inadequate dataset and the importance of semisupervised generative adversarial network for the extraction of well-mapped features and generation of image data. Our experimental evaluation indicates that the proposed semisupervised model achieves reliable classification, taking advantage of the reflective loss distance between the real data sample space and the generated data.

show abstract

“…The FaceScrub and CASIA-WebFace datasets contain 106863 and 494 414 images respectively [35] [36].In addition, OpenFace's neural network gives an ability of feature extraction method to obtain human face with the different view of angle even with the low dimensional representation. There is a difference between training the deep neural network (DNN) model for feature representation and training a model for classifying [37] people with the DNN model.…”

Section: A Openface Neural Network Modelsmentioning

confidence: 99%

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Khokhar¹,

Ayoub²,

Jamali³

et al. 2021

JISR-C

View full text Add to dashboard Cite

Face plays a vital role in the Recognition or Re-Identification of a person. Therefore, it is significant to identify and extract the facial visual features that automatically lead to face identification-based classification. Facial features comprise different ways of detection, for instance, they could be located at corners or midpoints of the facial features that rely on multiple components such as eyes, lips, nose with different emotions and expressions used in face recognition. This paper introduced a robust and efficient deep learning model with the use of a transfer learning approach for PSO for extraction and selection of the best facial features. Deep learning models “Openface via PSO and introduced customized Inception-V3 model via PSO is used and present detailed comparative accuracy of both models in terms of classification recognition. For this, the paper presents seven different algorithms to evaluate the efficiency of the model with four different face databases. It is evident from the result; neural network classifier shows a gradual hike to calculate accuracy with the proposed PSO-based OpenFace deep learning approach. On the other hand, random forest and AdaBoost algorithm were observed most compatible with the customized PSO-based Inception-V3 model.

show abstract

Efficient and Deep Vehicle Re-Identification Using Multi-Level Feature Extraction

Cited by 27 publications

References 40 publications

A Survey of Vehicle Re-Identification Based on Deep Learning

A Survey of Vehicle Re-Identification Based on Deep Learning

Transfer Learning and Semisupervised Adversarial Detection and Classification of COVID‐19 in CT Images

Efficient Face Re-Identification through PSO Based Adaptive Deep Learning Models

Contact Info

Product

Resources

About