Recognition of Low-Resolution Logos in Vehicle Images Based on Statistical Random Sparse Distribution

Peng, Haoyu; Wang, Xun; Wang, Huiyan; Yang, Wenwu

doi:10.1109/tits.2014.2336675

Cited by 15 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these datasets are not widely used. The datasets provided in [19,24] are extremely small. Evidently, testing on a set with limited number of images is inadequate to prove the robustness of the VLR methods.…”

Section: Methodsmentioning

confidence: 99%

“…Vehicle license plates and headlights are obvious objects in cars that help to define the size of the rectangular candidate region. The success of license plate location (LPL) technology [17,18] has prompted some research [19,20] to first detect the license plate and eventually use the topological relationship between the license plate and vehicle logo position to extract a candidate region that contains the logo. Thereafter, morphological methods [21,22,23] such as edge detection and color segmentation, are applied in the candidate region to accurately locate the logo.…”

Section: Related Workmentioning

confidence: 99%

“…Cyganek et al [29] presented a vehicle logo recognition system based on the novel combination of tensor-based feature extraction and an ensemble of tensor subspace classifiers. Peng et al [19] proposed an approach based on statistical random sparse distribution (SRSD) feature and multiscale scanning to deal with poor-quality images captured from urban crossings. In general, traditional machine learning methods are laborious and require well-designed handcrafted features to accomplish the classification task.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Vehicle Logo Recognition Based on Enhanced Matching for Small Objects, Constrained Region and SSFPD Network

Liu

Han

Min

et al. 2019

Sensors

View full text Add to dashboard Cite

Vehicle Logo Recognition (VLR) is an important part of vehicle behavior analysis and can provide supplementary information for vehicle identification, which is an essential research topic in robotic systems. However, the inaccurate extraction of vehicle logo candidate regions will affect the accuracy of logo recognition. Additionally, the existing methods have low recognition rate for most small vehicle logos and poor performance under complicated environments. A VLR method based on enhanced matching, constrained region extraction and SSFPD network is proposed in this paper to solve the aforementioned problems. A constrained region extraction method based on segmentation of the car head and car tail is proposed to accurately extract the candidate region of logo. An enhanced matching method is proposed to improve the detection performance of small objects, which augment each of training images by copy-pasting small objects many times in the unconstrained region. A single deep neural network based on a reduced ResNeXt model and Feature Pyramid Networks is proposed in this paper, which is named as Single Shot Feature Pyramid Detector (SSFPD). The SSFPD uses the reduced ResNeXt to improve classification performance of the network and retain more detailed information for small-sized vehicle logo detection. Additionally, it uses the Feature Pyramid Networks module to bring in more semantic context information to build several high-level semantic feature maps, which effectively improves recognition performance. Extensive evaluations have been made on self-collected and public vehicle logo datasets. The proposed method achieved 93.79% accuracy on the Common Vehicle Logos Dataset and 99.52% accuracy on another public dataset, respectively, outperforming the existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle Logo Recognition Based on Enhanced Matching for Small Objects, Constrained Region and SSFPD Network

Liu

Han

Min

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Low dimensional features of vehicle tail light are classified using a Bayesian network to four different vehicle types. Author in [19] used statistical random pixel distribution features acquired from low dimensional images to recognize the logo of the vehicle. Multiscale scanning algorithm is used to jointly detect and classify logos.…”

Section: Literature Surveymentioning

confidence: 99%

Traffic Adaptive Deep Learning based Fine Grained Vehicle Categorization in Cluttered Traffic Videos

S¹,

Deepu²

2021

IJACSA

View full text Add to dashboard Cite

Smart traffic management is being proposed for better management of traffic infrastructure and regulate traffic in smart cities. With surge of traffic density in many cities, smart traffic management becomes utmost necessity. Vehicle categorization, traffic density estimation and vehicle tracking are some of the important functionalities in smart traffic management. Vehicles must be categorized based on multiple levels like type, speed, direction of travel and vehicle attributes like color etc. for efficient tracking and traffic density estimation. Vehicle categorization becomes very challenging due to occlusions, cluttered backgrounds and traffic density variations. In this work, a traffic adaptive multi-level vehicle categorization using deep learning is proposed. The solution is designed to solve the problems in vehicle categorization in terms of occlusions, cluttered backgrounds.

show abstract

“…Vehicle attribute analysis, including model, make (vehicle manufacturer), type, colour analysis, is an essential component in intelligent transportation systems, which has a wide range of applications, such as traffic surveillance [1], criminal detection, security enforcement, robot navigation, active safety systems [2] and law enforcement. Due to the logo of a vehicle directly revealing the manufacturer, vehicle logo recognition plays a crucial role in vehicle attribute analysis with much attention [3–5].…”

Section: Introductionmentioning

confidence: 99%

Extensive exploration of comprehensive vehicle attributes using D‐CNN with weighted multi‐attribute strategy

Zhuo

Feng

Cheng

et al. 2017

IET Intelligent Transport Systems

View full text Add to dashboard Cite

Recognition of Low-Resolution Logos in Vehicle Images Based on Statistical Random Sparse Distribution

Cited by 15 publications

References 21 publications

Vehicle Logo Recognition Based on Enhanced Matching for Small Objects, Constrained Region and SSFPD Network

Vehicle Logo Recognition Based on Enhanced Matching for Small Objects, Constrained Region and SSFPD Network

Traffic Adaptive Deep Learning based Fine Grained Vehicle Categorization in Cluttered Traffic Videos

Extensive exploration of comprehensive vehicle attributes using D‐CNN with weighted multi‐attribute strategy

Contact Info

Product

Resources

About