A Vehicle Recognition Algorithm Based on Deep Transfer Learning with a Multiple Feature Subspace Distribution

Wang, Hai; Yu, Yijie; Cai, Yingfeng; Chen, Long; Chen, Xiaobo

doi:10.3390/s18124109

Cited by 24 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features are then concurrently passed to multiple machine learning classifiers including SVM, decision trees, and K-nearest neighbors, from which target verification is performed by majority vote. A recent method for vehicle make and model recognition introduced by Wang et al [33] suggests using the multiple feature subspace hypothesis based on sparse constraints, and transfer learning. Deep Belief Network (BDN) is used in combination with multiple Restricted Boltzmann Machines (RBM) to constitute the multiple subspace feature extractor.…”

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence for Text-Based Vehicle Search, Recognition, and Continuous Localization in Traffic Videos

Panetta

Kezebou

Oludare

et al. 2021

View full text Add to dashboard Cite

The concept of searching and localizing vehicles from live traffic videos based on descriptive textual input has yet to be explored in the scholarly literature. Endowing Intelligent Transportation Systems (ITS) with such a capability could help solve crimes on roadways. One major impediment to the advancement of fine-grain vehicle recognition models is the lack of video testbench datasets with annotated ground truth data. Additionally, to the best of our knowledge, no metrics currently exist for evaluating the robustness and performance efficiency of a vehicle recognition model on live videos and even less so for vehicle search and localization models. In this paper, we address these challenges by proposing V-Localize, a novel artificial intelligence framework for vehicle search and continuous localization captured from live traffic videos based on input textual descriptions. An efficient hashgraph algorithm is introduced to compute valid target information from textual input. This work further introduces two novel datasets to advance AI research in these challenging areas. These datasets include (a) the most diverse and large-scale Vehicle Color Recognition (VCoR) dataset with 15 color classes—twice as many as the number of color classes in the largest existing such dataset—to facilitate finer-grain recognition with color information; and (b) a Vehicle Recognition in Video (VRiV) dataset, a first of its kind video testbench dataset for evaluating the performance of vehicle recognition models in live videos rather than still image data. The VRiV dataset will open new avenues for AI researchers to investigate innovative approaches that were previously intractable due to the lack of annotated traffic vehicle recognition video testbench dataset. Finally, to address the gap in the field, five novel metrics are introduced in this paper for adequately accessing the performance of vehicle recognition models in live videos. Ultimately, the proposed metrics could also prove intuitively effective at quantitative model evaluation in other video recognition applications. T One major advantage of the proposed vehicle search and continuous localization framework is that it could be integrated in ITS software solution to aid law enforcement, especially in critical cases such as of amber alerts or hit-and-run incidents.

show abstract

Section: Related Workmentioning

confidence: 99%

Artificial Intelligence for Text-Based Vehicle Search, Recognition, and Continuous Localization in Traffic Videos

Panetta

Kezebou

Oludare

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, the artificial features depend on human experience to a large extent, and the deep information of image is not easy to be mined, so the effectiveness of artificial features is hard to be ensured. Therefore, the deep learning based vehicle recognition algorithms are paid more attention in recent years, which include some traditional deep learning models such as Convolutional Neural Network model [13][14][15], Deep Belief Network model [16][17], Transfer learning model [18][19][20], Restricted Boltzmann Machine [21][22][23], and some improved models such as Conv5 [24], Teacher-Student Network [25], Parsing-based View-aware Embedding Network [26], Semantics-guided Part Attention Network [27], the model fused by multiple networks [28], and the network based on reconstruction [29], et al For the supervised vehicle classification problem, these deep learning methods have achieved good results, but for vehicle face matching problem under the conditions that the times of each vehicle being captured is very limited and the number of the training samples is too small, the universalities of these models are not very well. Therefore, under a limited number of vehicle face samples, it is very meaningful to propose a vehicle re-identification algorithm with good robustness and universality.…”

Section: Related Workmentioning

confidence: 99%

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

2021

KSII TIIS

View full text Add to dashboard Cite

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

show abstract

“…After the learning feature ends in the deep convolutional network, a small number of tagged data input networks are used to fine-tune the parameters, and the network is continuously optimized. 17,21,26,27,28 The output of the fully connected layer k can be obtained by weighting the inputs and by the effect of the activation function…”

Section: Deep Convolutional Networkmentioning

confidence: 99%

Vehicle license plate recognition method based on deep convolution network in complex road scene

Liu

Cai

Chen

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part D:

Self Cite

View full text Add to dashboard Cite

The license plate robust recognition algorithm in complex road scene has both theoretical and practical values. The existing license plate recognition algorithm can achieve better recognition results under ideal road scenes such as moderate light intensity, good shooting angle, and clear license plate target, but in complex road scenes such as fast speed, blurred aging of license plates, and low illumination such as rainy days, the effectiveness of the license plate recognition algorithm still needs to be improved. Based on the realistic requirements of license plate recognition algorithm and in-depth analysis of the principle of deep convolution network, we designed a deep convolution network for Chinese characters, letters, and numbers in the license plate to automatically learn the essential features of the image to make up for the limitation of the artificial feature recognition of the traditional license plate recognition algorithm. At the same time, according to the convolution kernel, downsampling, and nonlinear operation of the deep convolution network, the nonlinear abstraction ability of the license plate character feature is improved. The experimental results show that the proposed method can quickly and accurately identify the license plate character in complex road scenes. The recognition accuracy is better than the existing license plate recognition algorithm, which improves the accuracy of license plate recognition and achieves an ideal license plate recognition effect.

show abstract

A Vehicle Recognition Algorithm Based on Deep Transfer Learning with a Multiple Feature Subspace Distribution

Cited by 24 publications

References 31 publications

Artificial Intelligence for Text-Based Vehicle Search, Recognition, and Continuous Localization in Traffic Videos

Artificial Intelligence for Text-Based Vehicle Search, Recognition, and Continuous Localization in Traffic Videos

Vehicle Face Re-identification Based on Nonnegative Matrix Factorization with Time Difference Constraint

Vehicle license plate recognition method based on deep convolution network in complex road scene

Contact Info

Product

Resources

About