Vehicle color classification using manifold learning methods from urban surveillance videos

Wang, Yu-Chen; Han, Chin‐Chuan; Hsieh, Chen-Ta; Fan, Kuo-Chin

doi:10.1186/1687-5281-2014-48

Cited by 9 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The obtained accuracy results ranged from 71% to 89% for set 1 and 68% to 73% for set 2, respectively. Finally, Wang et al [68] used stationary surveillance cameras to collect traffic images with more than 42,000 isolated individual vehicles. Images were processed using a desktop computer (i7@2.67GHz) and classified according to the 7 most commonly used colors.…”

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

“…Yu-Chen Wang et al, [5] study vehicle color classification utilizing complex learning routines and come up with a new plan for the color reorganization of vehicles utilizing the locating algorithm of regions of interest (ROIs) and color histogram characteristics from still images. Vehicle information distinguishment is a paramount part of intelligent transportation systems.…”

Section: Introductionmentioning

confidence: 99%

Classify vehicles: Classification or clusterization?

Thota

Badawy

Changalasetty

et al. 2015

2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015]

View full text Add to dashboard Cite

Vehicle classification has crop up as an important field of study due of its importance in variety of applications like surveillance, security framework, traffic congestion prevention and accidents avoidance. The image sequences for traffic scenes are recorded by a stationary NI smart camera. The video clip is processed in LabVIEW to detect vehicle and measure characteristics like width, length, area, perimeter using image process feature extraction techniques. Data mining is the use of automated data analysis techniques to uncover previously undetected relationships among data items. Two of the major data mining techniques are classification and clustering. To classify a vehicle as big or small needs to classify vehicles into classes. Among many, two techniques in WEKA are feed-forward neural network (NN) classification technique and k-means clustering techniques. To choose between the two techniques is a challenging task. We carry experiments using the extracted features of vehicles from traffic video with both techniques and found that classification model out-performed cluster model by a small degree.

show abstract

“…To handle this challenge, feature selection [4][5][6][7][8] and subspace learning [9,10] have been developed to obtain suitable feature representations. Feature selection is commonly used as a preprocessing step for classification, so most feature selection algorithms are only designed for better predictability, such as high prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

SIP-FS: a novel feature selection for data representation

Guo

et al. 2018

J Image Video Proc.

View full text Add to dashboard Cite

Multiple features are widely used to characterize real-world datasets. It is desirable to select leading features with stability and interpretability from a set of distinct features for a comprehensive data description. However, most of existing feature selection methods focus on the predictability (e.g., prediction accuracy) of selected results yet neglect stability. To obtain compact data representation, a novel feature selection method is proposed to improve stability, and interpretability without sacrificing predictability (SIP-FS). Instead of mutual information, generalized correlation is adopted in minimal redundancy maximal relevance to measure the relation between different feature types. Several feature types (each contains a certain number of features) can then be selected and evaluated quantitatively to determine what types contribute to a specific class, thereby enhancing the so-called interpretability of features. Moreover, stability is introduced in the criterion of SIP-FS to obtain consistent results of ranking. We conduct experiments on three publicly available datasets using one-versus-all strategy to select class-specific features. The experiments illustrate that SIP-FS achieves significant performance improvements in terms of stability and interpretability with desirable prediction accuracy and indicates advantages over several state-of-the-art approaches.

show abstract

Vehicle color classification using manifold learning methods from urban surveillance videos

Cited by 9 publications

References 28 publications

System for automatic detection and classification of cars in traffic

System for automatic detection and classification of cars in traffic

Classify vehicles: Classification or clusterization?

SIP-FS: a novel feature selection for data representation

Contact Info

Product

Resources

About