Vehicle Classification Based on Soft Computing Algorithms

Dalka, Piotr; Czyżewski, Andrzej

doi:10.1007/978-3-642-13529-3_9

Cited by 17 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…statistical moments, speeded-up robust features from luminance images and image descriptors based on Gabor filters), and several classifiers (e.g. neural networks, decision trees, nearest neighbours) for vehicle classification [28].…”

Section: Literature Reviewmentioning

confidence: 99%

Evolving sensor environments with visual attention: An experimental exploration

Creţu

2012

2012 IEEE International Symposium on Robotic and Sensors Environments Proceedings

View full text Add to dashboard Cite

The research community is experiencing nowadays a significant growth in the amount of sensor data made available to several practical applications, particularly those dealing with visual information. The availability of large datasets poses critical challenges for the selection of only relevant features to allow their timely use and interpretation. The recent years marked an increasing interest in algorithms inspired from biological human vision as an alternative source of ideas for the development of computational resources to deal with large datasets. In particular, computational models of visual attention have been shown to significantly improve the speed of scene understanding and object recognition by attending only the regions of interest and distributing the resources where they are required. This paper explores the use and gauges the performance of visual attention mechanisms for identifying an optimal feature set that ensures the identification and classification of objects in images, in two different scenarios. The first scenario addresses the issue of the identification of different categories of vehicles from multiple viewpoints in a controlled environment, with a relatively known background. The other scenario explores the capabilities of an improved visual attention model for the identification of buildings in satellite imaging, characterized by large variations in content and characteristics and by a cluttered background.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Evolving sensor environments with visual attention: An experimental exploration

Creţu

2012

2012 IEEE International Symposium on Robotic and Sensors Environments Proceedings

View full text Add to dashboard Cite

show abstract

“…The advantage of such model based approaches is a reduction in view-point dependence; however, they remain limited to the basic classes (bus/lorry, van, car/taxi, motorbike/bicycle) and producing simple 3D models accurate enough to distinguish between the many makes and models or subtypes of private cars seems unlikely to have high success. Turning to exploiting lower level image features, [7] apply a two-step kNN classifier with geometric and texture based features for 7 types classes of vehicle exploiting both frontal and rear views, [5] applied various classifiers to three vehicle type classes based on SURF and Gabor features, and [12] developed an SVM classifier based on a structural edge signature extracted from rear vehicle views. However, [12] is limited to 3 classes with a total of 1664 images.…”

Section: Related Workmentioning

confidence: 99%

Vehicle subtype, make and model classification from side profile video

Boyle

Ferryman

2015

2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

This paper addresses the challenging domain of vehicle classification from pole-mounted roadway cameras, specifically from side-profile views. A new public vehicle dataset is made available consisting of over 10000 side profile images (86 make/model and 9 sub-type classes). 5 state-of-the-art classifiers are applied to the dataset, with the best achieving high classification rates of 98.7% for sub-type and 99.7-99.9% for make and model recognition, confirming the assertion made that single vehicle side profile images can be used for robust classification.

show abstract

“…Some widespread descriptors include Gabor filters, principal component analysis (PCA) [8], and histograms of oriented gradients (HOG) [9]. Gabor filters have been broadly used for image-based vehicle verification [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

Vehicle recognition based on Gabor and Log-Gabor transforms

Priyadharshini¹,

Arivazhagan²,

Sangeetha³

2014

2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies

View full text Add to dashboard Cite

Image-based vehicle recognition is usually addressed as a supervised classification problem. Here, vehicle recognition is performed using two different transforms such as Gabor and Log-Gabor. First the images are convolved with Gabor and LogGabor filter with different scales and orientations. Then mean and standard deviation are computed for all the filtered images. These features are fed to SVM classifier for further training and classification. The experimentation is carried out in GTI database. From the experiments it is revealed that the LogGabor transform significantly outperforms the standard Gabor transform for image-based vehicle recognition.

show abstract

Vehicle Classification Based on Soft Computing Algorithms

Cited by 17 publications

References 19 publications

Evolving sensor environments with visual attention: An experimental exploration

Evolving sensor environments with visual attention: An experimental exploration

Vehicle subtype, make and model classification from side profile video

Vehicle recognition based on Gabor and Log-Gabor transforms

Contact Info

Product

Resources

About