Vehicle type classification via adaptive feature clustering for traffic surveillance video

Wang, Shu; Liu, Feng; Gan, Zongliang; Cui, Ziguan

doi:10.1109/wcsp.2016.7752672

Cited by 8 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this approach they are able to distinguish pedestrians from small and large vehicles. The method proposed by Shu Wang et al in [WLGC16] categorizes three types of vehicles, compact, mid-sized and heavy-duty. It is described in some detail in figure 2.11 It works in four steps which will now be described.…”

Section: Bounding Box Ratio Methodsmentioning

confidence: 99%

Computer-vision-based surveillance of intelligent transportation systems

Braun

Santos

Rossetti

2018

2018 13th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

Now that this period of my life is upon its dawn, it is time to thank everyone who accompanied me through this journey which has seen me grow both as an individual and as a professional. Without your support this adventure would not have been the same.To the ρ7 Boyz, João Pereira, José Pinto, Henrique Ferrolho, Luís Reis and João Dias, as well as Sara Paiva and Beatriz Baldaia, the residents of Lab I120, thank you for all the good moments.To my parents and my brother for always being there for me, offering sage advice and true friendship. Thank you to my girlfriend Cátia Matos, who on a daily basis helped me face the toughest problems and overcome the greatest challenges.To all my friends who showed a great degree of interest with this project, always ready to help,

show abstract

Section: Bounding Box Ratio Methodsmentioning

confidence: 99%

Computer-vision-based surveillance of intelligent transportation systems

Braun

Santos

Rossetti

2018

2018 13th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

show abstract

“…camera calibration), allowing to establish ROIs, reducing the analyzed region which increases the performance of the proposed algorithms. Meanwhile DL for vehicle detection, exploits parallel architectures and, in successful implementations, it performs both region proposals and object detection [64], [66], [108], [109], [110], with near real-time operation.…”

Section: A Challengesmentioning

confidence: 99%

Detection of Motorcycles in Urban Traffic Using Video Analysis: A Review

Espinosa

Velastín

Branch

2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Motorcycles are Vulnerable Road Users (VRU) and as such, in addition to bicycles and pedestrians, they are the traffic actors most affected by accidents in urban areas. Automatic video processing for urban surveillance cameras has the potential to effectively detect and track these road users. The present review focuses on algorithms used for detection and tracking of motorcycles, using the surveillance infrastructure provided by CCTV cameras. Given the importance of results achieved by Deep Learning theory in the field of computer vision, the use of such techniques for detection and tracking of motorcycles is also reviewed. The paper ends by describing the performance measures generally used, publicly available datasets (introducing the Urban Motorbike Dataset (UMD) with quantitative evaluation results for different detectors), discussing the challenges ahead and presenting a set of conclusions with proposed future work in this evolving area.

show abstract

“…Another implementation of vehicle type classification based on grayscale images from a surveillance camera is done by Wang et al that combined CNN with the extreme learning technique (ELM) [15]. The vehicle features from grayscale images were extracted using CNN, and additional samples of a vehicle are trained in ELM to extract other vehicle features.…”

Section: Related Workmentioning

confidence: 99%

Vehicle Type Classification Using an Enhanced Sparse-Filtered Convolutional Neural Network With Layer-Skipping Strategy

2020

View full text Add to dashboard Cite

In this paper, a vehicle type classification approach is proposed by using an enhanced feature extraction technique based on Sparse-Filtered Convolutional Neural Network with Layer-Skipping strategy (SF-CNNLS). To extract rich and discriminant vehicle features, we introduce Three-Channels of SF-CNNLS (TC-SF-CNNLS) as the feature extraction technique. Local and global features of vehicles are extracted from three channels of an image which are, luminance and chromatic components. This technique is inspired by how human eyes differentiating objects that share almost similar features. TC-SF-CNNLS is tested with a benchmark dataset that provides frontal-view images to classify vehicle types of the bus, passenger car, taxi, minivan, SUV, and truck with Softmax Regression as a classifier. This test aims to observe the ability of this technique in differentiating vehicles with almost similar features but different classes. A test is also conducted with the self-obtained dataset (SPINT) to observe the effectiveness of this technique. The results are observed based on accuracy, precision, recall, and f-score, whereby, TCSF-NNLS has successfully recognized all the classes with an average accuracy of 0.905, precision is between 0.8629 to 0.9548, recall is between 0.83 to 0.96 and f-score is between 0.8564 to 0.9523. In addition, this technique is able to outperform other existing techniques with an average accuracy of 93.% compared to only 89.2% when 5 classes of vehicles are tested. INDEX TERMS Vehicle type recognition, convolutions neural network, deep learning, computational intelligence.

show abstract

Vehicle type classification via adaptive feature clustering for traffic surveillance video

Cited by 8 publications

References 17 publications

Computer-vision-based surveillance of intelligent transportation systems

Computer-vision-based surveillance of intelligent transportation systems

Detection of Motorcycles in Urban Traffic Using Video Analysis: A Review

Vehicle Type Classification Using an Enhanced Sparse-Filtered Convolutional Neural Network With Layer-Skipping Strategy

Contact Info

Product

Resources

About