Vehicle Attribute Recognition by Appearance: Computer Vision Methods for Vehicle Type, Make and Model Classification

Ni, Xingyang; Huttunen, Heikki

doi:10.1007/s11265-020-01567-6

Cited by 19 publications

(7 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ni and Huttunen [70] also provide a brief literature review but make a distinction between make recognition systems (4) and model recognition systems (19). Consequently, the accuracy of car make recognition ranged from 81.3% to 99.6% (for image databases ranging from 1,482 to 30,955 images), whereas car model recognition accuracy ranged from 64.3% to 98.5% (for image databases containing between 300 and 90,940).…”

Section: Resultsmentioning

confidence: 99%

System for automatic detection and classification of cars in traffic

Bralić

Musić

2022

St open

View full text Add to dashboard Cite

Objective: To develop a system for automatic detection and classification of cars in traffic in the form of a device for autonomic, real-time car detection, license plate recognition, and car color, model, and make identification from video.Methods: Cars were detected using the You Only Look Once (YOLO) v4 detector. The YOLO output was then used for classification in the next step. Colors were classified using the k-Nearest Neighbors (kNN) algorithm, whereas car models and makes were identified with a single-shot detector (SSD). Finally, license plates were detected using the OpenCV library and Tesseract-based optical character recognition. For the sake of simplicity and speed, the subsystems were run on an embedded Raspberry Pi computer.Results: A camera was mounted on the inside of the windshield to monitor cars in front of the camera. The system processed the camera’s video feed and provided information on the color, license plate, make, and model of the observed car. Knowing the license plate number provides access to details about the car owner, roadworthiness, car or license place reports missing, as well as whether the license plate matches the car. Car details were saved to file and displayed on the screen. The system was tested on real-time images and videos. The accuracies of car detection and car model classification (using 8 classes) in images were 88.5% and 78.5%, respectively. The accuracies of color detection and full license plate recognition were 71.5% and 51.5%, respectively. The system operated at 1 frame per second (1 fps).Conclusion: These results show that running standard machine learning algorithms on low-cost hardware may enable the automatic detection and classification of cars in traffic. However, there is significant room for improvement, primarily in license plate recognition. Accordingly, potential improvements in the future development of the system are proposed.

show abstract

Section: Resultsmentioning

confidence: 99%

System for automatic detection and classification of cars in traffic

Bralić

Musić

2022

St open

View full text Add to dashboard Cite

show abstract

“…In [26], the prominence (saliency) and shape of the rear lamps and registration plate have been used for identification to counteract the light limitation at night. In this method, SVM, KNN 9 , and decision trees have been used for classification. Sarfaraz et al [27] present a probabilistic method based on patches that automatically learns a set of patches for the vehicles' classes in the training phase.…”

Section: B the Methods Based On Feature Extraction And Applying To Th...mentioning

confidence: 99%

“…The studies on vehicle type identification are classified into two classes, DNN-based methods and the methods based on traditional feature extraction and classification [9,10]. These studies are reviewed in the following.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Approach for Vehicle Identification based on Image Registration and Deep Learning

Asgarian Dehkordi,

Khosravi,

Asgarian Dehkordi

et al. 2022

Scientia Iranica

View full text Add to dashboard Cite

Fine-grained vehicle type recognition using on-road cameras is among interesting topics in machine vision. It has several challenges like inter-class similarity, different viewing angles, and different lighting and weather conditions. This paper presents a novel approach for vehicle classification based on a novel augmentation method and deep learning. In the proposed smart augmentation, the vehicle images of each class are registered on the reference vehicles of all other classes and then added to the training set of that class. In this way, we will have a lot of new images which are very similar to both reference and target classes. This helps the CNN model to handle inter-class similarities very well. In the test phase, the input image is registered on every reference image in parallel and applied to the model. Finally, the winner is determined by summing up the provided scores of all models. The targeted data augmentation along with the proposed classification strategy has high recognition power and is capable of providing high accuracy using small CNNs or any other classification method without the need for large datasets. The proposed method achieved a recognition rate of 99.8% with only 150K parameters.

show abstract

“…The output of each fully connected layer is a value describing that particular attribute. For more details about recent work in vehicle attribute prediction, Ni and Huttunen [48] have a good survey of recent work, and some existing vehicle datasets for vehicle attributes recognition (e.g. color, type, make, license plate, and model) can be found in [70,38].…”

Section: Related Workmentioning

confidence: 99%