A Large-Scale Frontal Vehicle Image Dataset for Fine-Grained Vehicle Categorization

Lü, Lei; Wang, Ping; Huang, Hua

doi:10.1109/tits.2020.3027451

Cited by 19 publications

(25 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have analysed the strengths and shortcomings of datasets like CompCars [6], VMMR-db [7] and Frontal-103 [8] and used them in a series of experiments.…”

Section: Discussionmentioning

confidence: 99%

“…Content may change prior to final publication. [6] Mixed Web 52,083 431 models Geographical bias, far from real world, multiplicity problem ignored BoxCars [3], [11] Mixed/3D Surveillance 63,750 126 models Geographical bias, images size and resolution VMMR-db [7] Mixed Real 291,752 9,170 models Geographical bias, multiple labels for the same class Frontal-103 [8] Front model. In [12], Gu et al proposed a method to deal with severe pose variation.…”

Section: B Fine-grained Vehicle Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Are We Ready for Accurate and Unbiased Fine-Grained Vehicle Classification in Realistic Environments?

et al. 2021

View full text Add to dashboard Cite

Fine-grained vehicle classification from images, also known as Vehicle Make and Model Recognition (VMMR), has become an important research topic in the last years, with a growing number of scientific contributions in multiple application areas, such as autonomous vehicles, surveillance systems, traffic monitoring and management, among others. Recent techniques based on deep learning have proven to be very effective in addressing this problem. So effective that, based on the state-of-the-art results (above 95% accuracy), it would seem that the problem is practically solved. However, our main hypothesis is that the existing datasets to date have limited variability, which precludes good and unbiased generalisation of the models trained with them. In particular, it is observed that the test datasets are very similar in nature to those used for training and validation which makes these benchmarks prone to dataset bias and to overfitting. When these systems are tested with more challenging data or data from different datasets performance degrades considerably. In this paper, on the one hand, we evaluate state-of-the-art deep learning models to perform fine-grained vehicle classification and explore multiple training techniques, such as curriculum learning or weighted losses, to mitigate the bias between different makes and models and to assess the limits of current approaches. On the other hand, we analyse the existing datasets, present an additional dataset from a challenging scenario, and merge all the data into a cross-dataset that includes common samples and classes from the existing datasets. In this way, we can evaluate geographical, make and model biases, and performance and generalisation capabilities from a more realistic perspective. The obtained results suggest that we are still far from accurate and unbiased vehicle make and model recognition in realistic traffic and driving scenarios.INDEX TERMS Fine-grained classification, vehicle make and model, dataset bias, curriculum learning, weighted loss, cross-datasets.

show abstract

“…We have analysed the strengths and shortcomings of datasets like CompCars [6], VMMR-db [7] and Frontal-103 [8] and used them in a series of experiments.…”

Section: Discussionmentioning

confidence: 99%

Section: B Fine-grained Vehicle Classificationmentioning

confidence: 99%

Are We Ready for Accurate and Unbiased Fine-Grained Vehicle Classification in Realistic Environments?

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Since, no accurate M&M vehicle labels are provided in Apollo3DCar, to simulate the real-world MMR error, we randomly select 5% and 10% vehicles taking a generic prior, as elaborated in Section 2. These MMR percentages are realistic as given in [6,7,8].…”

Section: Methodsmentioning

confidence: 99%

“…Recently, vehicle make-and-model-recognition (VMMR) on monocular images has achieved impressive performance [6,7,8]. As the 3D shape of a vehicle is fully determined by its fine-grained model and make (M&M) label, in our approach, we suggest to look-up the appropriate 3D vehicle shape from a known database of vehicle CAD models.…”

Section: Introductionmentioning

confidence: 99%

MONO6D: Monocular Vehicle 6D Pose Estimation with 3D Priors

Lyu

Royen

Munteanu

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Predicting the 6DoF pose of vehicles from a single view image without additional constraints remains an ill-posed problem. Current monocular approaches require expensive and time-consuming annotations of vehicle-specific feature points and/or the 2D-3D feature correspondences. In this paper, we propose a novel monocular approach for vehicle pose estimation in SE(3), dubbed Mono6D, that uses vehicle 3D priors provided by vehicle make-and-model recognition methods to estimate the 6D pose. The proposed method mainly consists of: 1) a two-separate-branch module to learn multi-modal representations; 2) a fusion schema to learn pose-specific representative embeddings. The experimental results show that the proposed method is superior to the state-of-the-art approaches in both objective and subjective terms.

show abstract

“…Lu et al [11] presented an image dataset, Frontal-103, for fine-grained vehicle classification that contains frontal vehicle images. The dataset comprises 65,433 images taken from the Internet containing 1759 vehicle models that are further categorized in 103 vehicle makes.…”

Section: Related Workmentioning

confidence: 99%

A Particle Swarm Optimization Based Deep Learning Model for Vehicle Classification

Alhudhaif¹,

Saeed²,

Imran³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Image classification is a core field in the research area of image processing and computer vision in which vehicle classification is a critical domain. The purpose of vehicle categorization is to formulate a compact system to assist in real-world problems and applications such as security, traffic analysis, and selfdriving and autonomous vehicles. The recent revolution in the field of machine learning and artificial intelligence has provided an immense amount of support for image processing related problems and has overtaken the conventional, and handcrafted means of solving image analysis problems. In this paper, a combination of pre-trained CNN GoogleNet and a nature-inspired problem optimization scheme, particle swarm optimization (PSO), was employed for autonomous vehicle classification. The model was trained on a vehicle image dataset obtained from Kaggle that has been suitably augmented. The trained model was classified using several classifiers; however, the Cubic SVM (CSVM) classifier was found to outperform the others in both time consumption and accuracy (94.8%). The results obtained from empirical evaluations and statistical tests reveal that the model itself has shown to outperform the other related models not only in terms of accuracy (94.8%) but also in terms of training time (82.7 s) and speed prediction (380 obs/sec).

show abstract

A Large-Scale Frontal Vehicle Image Dataset for Fine-Grained Vehicle Categorization

Cited by 19 publications

References 48 publications

Are We Ready for Accurate and Unbiased Fine-Grained Vehicle Classification in Realistic Environments?

Are We Ready for Accurate and Unbiased Fine-Grained Vehicle Classification in Realistic Environments?

MONO6D: Monocular Vehicle 6D Pose Estimation with 3D Priors

A Particle Swarm Optimization Based Deep Learning Model for Vehicle Classification

Contact Info

Product

Resources

About