Vehicle Type Recognition Combining Global and Local Features via Two-Stage Classification
| Autor: | Wei Sun, Jun He, Xiaorui Zhang, Shi Shunshun, Jin Yan |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Stage classification
Engineering Article Subject General Mathematics ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology computer.software_genre k-nearest neighbors algorithm Discriminative model 0502 economics and business 0202 electrical engineering electronic engineering information engineering Canny edge detector 050210 logistics & transportation business.industry lcsh:Mathematics 05 social sciences Gabor wavelet General Engineering Pattern recognition Sparse approximation lcsh:QA1-939 ComputingMethodologies_PATTERNRECOGNITION lcsh:TA1-2040 020201 artificial intelligence & image processing Artificial intelligence Data mining lcsh:Engineering (General). Civil engineering (General) business Vehicle type computer Classifier (UML) |
| Zdroj: | Mathematical Problems in Engineering, Vol 2017 (2017) |
| ISSN: | 1563-5147 1024-123X |
| DOI: | 10.1155/2017/5019592 |
| Popis: | This study proposes a new vehicle type recognition method that combines global and local features via a two-stage classification. To extract the continuous and complete global feature, an improved Canny edge detection algorithm with smooth filtering and non-maxima suppression abilities is proposed. To extract the local feature from four partitioned key patches, a set of Gabor wavelet kernels with five scales and eight orientations is introduced. Different from the single-stage classification, where all features are incorporated into one classifier simultaneously, the proposed two-stage classification strategy leverages two types of features and classifiers. In the first stage, the preliminary recognition of large vehicle or small vehicle is conducted based on the global feature via a k-nearest neighbor probability classifier. Based on the preliminary result, the specific recognition of bus, truck, van, or sedan is achieved based on the local feature via a discriminative sparse representation based classifier. We experiment with the proposed method on the public and established datasets involving various challenging cases, such as partial occlusion, poor illumination, and scale variation. Experimental results show that the proposed method outperforms existing state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text