The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Vehicle Type Classification Using a Semisupervised Convolutional Neural Network
Abstract
In this paper, we propose a vehicle type classification method using a semisupervised convolutional neural network from vehicle frontal-view images. In order to capture rich and discriminative information of vehicles, we introduce sparse Laplacian filter learning to obtain the filters of the network with large amounts of unlabeled data. Serving as the output layer of the network, the softmax classifier is trained by multitask learning with small amounts of labeled data. For a given vehicle image, the network can provide the probability of each type to which the vehicle belongs. Unlike traditional methods by using handcrafted visual features, our method is able to automatically learn good features for the classification task. The learned features are discriminative enough to work well in complex scenes. We build the challenging BIT-Vehicle dataset, including 9850 high-resolution vehicle frontal-view images. Experimental results on our own dataset and a public dataset demonstrate the effectiveness of the proposed method.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In comparison to these two approaches, recent DL-based solutions such as [2], [3], [23], [24] have been widely adopted due to their robustness and improved vehicle detection performance in images and videos.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [23]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
Hubel, D. H., & Wiesel, T. N. (1962) · The Journal of Physiology · doi:10.1113/jphysiol.1962.sp006837 · Cited by 13,680
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354
Greedy layer-wise training of deep networks
Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841
What is the best multi-stage architecture for object recognition?
Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153
Research works printed but not linked: 35
- 10.2307/2006193 · DOI
- 10.1080/net.12.3.255.270 · DOI
- 10.1016/0031-3203(82)90024-3 · DOI
- kumar, 2012, Learning task grouping and overlap in multi-task learning, Proc Int Conf Mach Learn, 1383
- belkin, 2006, Manifold regularization: A geometric framework for learning from labeled and unlabeled examples, J Mach Learn Res, 7, 2399
- 10.1162/neco.1994.6.4.559 · DOI
- ngiam, 0, Sparse filtering, Proc Adv Neural Inf Process Syst, 1125
- 10.1371/journal.pcbi.0040027 · DOI
- lyu, 0, Nonlinear image representation using divisive normalization, Proc IEEE Comput Soc Conf Comput Vis Pattern Recog, 1
- sobel, 1970, Camera Models and Machine Perception
- 10.1137/080716542 · DOI · Paper page
- 10.5244/C.18.61 · DOI
- 10.1109/ICPR.2006.264 · DOI
- 10.1016/j.csi.2010.06.005 · DOI
- 10.1109/TITS.2012.2213814 · DOI
- 10.1007/978-1-4614-3501-3_27 · DOI
- 10.1109/ICPR.2002.1048232 · DOI
- osadchy, 2007, Synergistic face detection and pose estimation with energy-based models, J Mach Learn Res, 8, 1197
- 10.1109/TIP.2011.2160954 · DOI
- 10.1109/TITS.2006.874722 · DOI
- zhang, 0, A PCA-based vehicle classification framework, Proc 22nd IEEE Intl Conf Data Engineering, 17
- kavukcuoglu, 0, Learning convolutional feature hierarchies for visual recognition, Proc Adv Neural Inf Process Syst, 1090
- ma, 0, Edge-based rich representation for vehicle classification, Proc IEEE Int Conf Comput Vis, 2, 1185
- 10.1109/TPAMI.2007.70728 · DOI
- 10.1109/ICAL.2007.4338720 · DOI
- 10.1109/6979.994794 · DOI
- 10.1007/978-3-319-01766-2_68 · DOI
- 10.1109/ITSC.2001.948656 · DOI
- 10.1109/CVPR.2013.446 · DOI
- 10.1109/CVPR.2014.212 · DOI · Paper page
- 10.1109/CVPR.2013.465 · DOI
- zhen, 0, Vehicle type classification using distributions of structural and appearance-based features, Proc Int Conf Image Process, 4321
- 10.1109/CVPR.2014.224 · DOI
- 10.1109/ICMEW.2012.73 · DOI
- 10.1126/science.1127647 · DOI · Paper page
Cited by
Sorted by citations
Items 101–200 of 328
Multi-Scale Vehicle Detection for Foreground-Background Class Imbalance with Improved YOLOv2
Wu, Z., Sang, J., Zhang, Q., Xiang, H., Cai, B., & Xia, X. (2019) · Sensors · doi:10.3390/s19153336 · Cited by 26
“The reason may be that the different models will focus on different In our experiments, the BIT-Vehicle dataset was divided into training set and test set with the ration”
MethodInfluentialDetection and Classification of Moving Vehicle From Video Using Multiple Spatio-Temporal Features
Wang, Y., Ban, X.-J., Wang, H., Wu, D., Wang, H., Yang, S.-W., Liu, S.-N., & Lai, J. (2019) · IEEE Access · doi:10.1109/access.2019.2923199 · Cited by 22
A concise review on vehicle detection and classification
Kul, S., Eken, S., & Sayar, A. (2017) · International Conference on Emerging Technologies · doi:10.1109/icengtechnol.2017.8308199 · Cited by 22
“[15] proposed a vehicle type classification method that uses a halfsupervised convolutional neural network from front view images of the vehicles.”
MethodTensor-Empowered Federated Learning for Cyber-Physical-Social Computing and Communication Systems
Yang, L. T., Zhao, R., Liu, D., Lu, W., & Deng, X. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3282264 · Cited by 36
“The effectiveness of the proposed tensor-empowered FL has been verified in the real-world dataset BIT-Vehicle [131]”
BackgroundKul, S., Tashiev, I., Sentas, A., & Sayar, A. (2021) · IEEE Access · doi:10.1109/access.2021.3085736 · Cited by 22
“cle type (BIT-Vehicle) [47], color [48], and speed [49].”
BackgroundA Dynamic Transformer Network for Vehicle Detection
Tian, C., Liu, K., Zhang, B., Huang, Z., Lin, C., & Zhang, D. D. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3565318 · Cited by 24
“More detailed information of MAB can be obtained from [33].”
Guo, Y., Liang, R., Cui, Y., Zhao, X., & Meng, Q. (2022) · IET Intelligent Transport Systems · doi:10.1049/itr2.12190 · Cited by 21
Tong, H., Sharifzadeh, H., & Mcloughlin, I. (2020) · Interspeech · doi:10.21437/interspeech.2020-1997 · Cited by 21
“The network was based on CNN [89][90][91] and Histogram Oriented Gradient (HOG), proposed by Dalal et al in [92], and scale-invariant feature transform (SIFT),proposed by Lowe in [93], algorithms.”
MethodHasan, M. M., Wang, Z., Hussain, M. A. I., & Fatima, K. (2021) · Sensors · doi:10.3390/s21227545 · Cited by 26
ResNet-Based Model for Autonomous Vehicles Trajectory Prediction
Zhang, Z. (2021) · 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece51280.2021.9342418 · Cited by 20
Vehicle Detection and Classification: A Review
Kiran, V. K., Parida, P., & Dash, S. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-49339-4_6 · Cited by 26
SS-HCNN: Semi-Supervised Hierarchical Convolutional Neural Network for Image Classification
Chen, T., Lu, S., & Fan, J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2886758 · Cited by 28
“Due to the challenges in collecting large-scale datasets and manual data annotation, semi-supervised CNN learning that uses partially labelled data samples has attracted increasing interest in recent years [4], [9]–[13].”
BackgroundMethodApplication Research of Neural Network in Vehicle Target Recognition and Classification
Lin, M., & Zhao, X. (2019) · International Conference on Intelligent Transportation, Big Data and Smart City · doi:10.1109/icitbs.2019.00010 · Cited by 20
Vehicle logo recognition based on overlapping enhanced patterns of oriented edge magnitudes
Yu, Y., Wang, J., Lu, J., Xie, Y., & Nie, Z. (2018) · Computers & electrical engineering · doi:10.1016/j.compeleceng.2018.07.045 · Cited by 20
Traffic Analytics With Low-Frame-Rate Videos
Luo, Z., Jodoin, P., Su, S., Li, S., & Larochelle, H. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2632439 · Cited by 29
“[29] proposed a semisupervised method for training a CNN model used to classify”
MethodIntelligent Vehicle Monitoring: Distributed-Acoustic-Sensor-Enabled Smart Road Infrastructure
Zhong, R., Chiang, C.-Y., & Jaber, M. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3529925 · Cited by 16
“Dong et al. [16] proposed a classification method using a semi-supervised convolutional neural network (CNN) to recognize vehicle type by processing the vehicle’s front view images.”
CNN-Based Classification for Highly Similar Vehicle Model Using Multi-Task Learning
Avianto, D., Harjoko, A., & Afiahayati, F. (2022) · Journal of Imaging · doi:10.3390/jimaging8110293 · Cited by 22
“The Softmax function is a combination of several sigmoid functions in the form of nodes [66], which can generate class probabilities for each task as output [67].”
BackgroundArtificial intelligent systems for vehicle classification: A survey
Tan, S. H., Chuah, J. H., Chow, C., Kanesan, J., & Leong, H. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107497 · Cited by 22
Dense-TNT: Efficient Vehicle Type Classification Neural Network Using Satellite Imagery
Luo, R.-K., Song, Y., Zhao, H., Zhang, Y., Zhang, Y., Zhao, N.-B., Huang, L.-P., & Su, R. (2022) · Italian National Conference on Sensors · doi:10.3390/s24237662 · Cited by 18
“To increase the interpretability of CNN, some research applies semi-supervised manner by feeding unlabeled data in pretraining process and learning output parameters in a supervised way [26].”
Indoor scene segmentation algorithm based on full convolutional neural network
Zhu, Z.-J., Li, D.-M., Hu, Y., Li, J., Liu, D., & Li, J.-J. (2020) · Neural computing & applications (Print) · doi:10.1007/s00521-020-04961-0 · Cited by 17
Rahman, M. M., Rahim, M., Ayman, U., Sohel, A., Hossain, M. A., Moni, M. A., & Moustafa, A. (2025) · Emerging Science Journal · doi:10.28991/esj-2025-09-02-023 · Cited by 16
“Dong et al. [28] introduced an unsupervised convolutional neural network pre-trained with sparse filtering and a layer-skipping strategy for effective vehicle type classification from frontal view images, using soft max regression for final classification.”
Ni, F., Zhang, J., & Taciroğlu, E. (2023) · Mechanical systems and signal processing · doi:10.1016/j.ymssp.2023.110667 · Cited by 16
The Dual-Fuzzy Convolutional Neural Network to Deal With Handwritten Image Recognition
Zhou, W., Liu, M., & Xu, Z. (2022) · IEEE transactions on fuzzy systems · doi:10.1109/tfuzz.2022.3170657 · Cited by 16
“The developed methods include the time-frequency CNN [9], the semi-supervised CNN [10], the discriminative CNN [11], the cascaded three-dimensional CNN [12], the complex-valued CNN [13], the distance metric optimization driven CNN [14], the two-flow CNN [15], the sparse”
MethodClassify vehicles in traffic scene images with deformable part-based models
Bai, S., Liu, Z.-Y., & Yao, C. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0890-y · Cited by 16
“Figure 8 shows that using a larger number of training images per class will improve the performance of the pro- Table 1 Computed areas under the ROC curves of the classifiers Bus Microbus Minivan SUV Sedan Truck Areas under ROC curves 0.941 0.840 0.885 0.891 0.923 0.938 Table 2 Specificity, recall, and precision of th…”
MethodInfluentialVehicle Type Recognition Combining Global and Local Features via Two-Stage Classification
Sun, W., Zhang, X.-R., Shi, S., He, J., & Jin, Y. (2017) · doi:10.1155/2017/5019592 · Cited by 16
“Additionally, we also test our method on the BIT-Vehicle dataset provided in [1]; our method achieves 90.”
BackgroundMethodInfluentialDerrouz, H., Elbouziady, A., Abdelali, H. A., Thami, R. O. H., Fkihi, S. E., & Bourzeix, F. (2019) · IEEE Access · doi:10.1109/access.2019.2920740 · Cited by 15
“Dong and his team used a convolutional neural network (CNN) to classify vehicles into six classes [5].”
BackgroundMethodInfluentialMan-Made Object Recognition from Underwater Optical Images Using Deep Learning and Transfer Learning
Yu, X., Xing, X.-R., Zheng, H., Fu, X.-Y., Huang, Y., & Ding, X.-H. (2018) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.2018.8461549 · Cited by 15
“The proposed network is pre-trained on ImageNet [21, 24], and then fine-tuned with our own data.”
MethodLong Multi-digit Number Recognition from Images Empowered by Deep Convolutional Neural Networks
Asif, M., Ahmad, M. B., Mushtaq, S., Masood, K., Mahmood, T., & Nagra, A. A. (2021) · The Computer Journal · doi:10.1093/comjnl/bxab117 · Cited by 21
Simultaneous Burr and Cut Interruption Detection during Laser Cutting with Neural Networks
Adelmann, B., & Hellmann, R. (2021) · Italian National Conference on Sensors · doi:10.3390/s21175831 · Cited by 14
“In contrast, in the images captured in our experiments, the object to analyze always has the same size, orientation and illumination conditions which should simplify the classification when compared to classifying common, moving items like vehicles or animals [34,35].”
BackgroundRobust Vehicle Classification Based on Deep Features Learning
Niroomand, N., Bach, C., & Elser, M. (2021) · IEEE Access · doi:10.1109/access.2021.3094366 · Cited by 14
“[67] proposed a vehicle type classificationmethod using a semi-supervised convolutional neural network from high-resolution vehicle frontal view images.”
BackgroundMethodIRUVD: a new still-image based dataset for automatic vehicle detection
Ali, A., Sarkar, R., & Das, D. K. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15365-2 · Cited by 19
“BIT dataset [8] is another vehicle classification dataset that consists of 6 classes - bus, SUV, minivan, truck, microbus, and Sedan.”
Gun Detection with Model and Type Recognition using Haar Cascade Classifier
Jain, A., Aishwarya, & Garg, G. (2020) · 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit48917.2020.9214211 · Cited by 13
“In [10,11], vehicle and type discovery are performed by utilizing all panoramic vehicle pictures and the framework accomplishes great paces of exactness.”
MethodPano-RSOD: A Dataset and Benchmark for Panoramic Road Scene Object Detection
Li, Y., Tong, G., Gao, H., Wang, Y., Zhang, L., & Chen, H. (2019) · Electronics · doi:10.3390/electronics8030329 · Cited by 14
“BIT-Vehicle Dataset [31] covers 9850 images of bus, microbus, minivan, sedan, SUV, and truck, which can be used to evaluate the performance of multi-class vehicle detection algorithms.”
BackgroundA convolutional neural network for visual object recognition in marine sector
Kumar, A. S., & Sherly, E. (2017) · 2017 2nd International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct.2017.8226141 · Cited by 13
“Examples of such cases are recognizing different car models [1] or different kinds of dog breeds [2].”
BackgroundA large scale dataset for classification of vehicles in urban traffic scenes
Bharadwaj, H. S., Biswas, S., & Ramakrishnan, K. R. (2016) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3009977.3010040 · Cited by 14
“They extend their work in [8] to include multi-task learning to train the output softmax classifier with the aim of enhancing the discriminative power of the network.”
BackgroundPattern recognition of Vehicle Logo using Tchebichef and Legendre moment
Soon, F. C., Khaw, H. Y., & Chuah, J. H. (2015) · Student Conference on Research and Development · doi:10.1109/scored.2015.7449438 · Cited by 13
“In addition, current vehicle speed limit control, traffic flow control and traffic surveillance rely mainly on the correct recognition of the LPR to pinpoint the targeted or monitored vehicle [2].”
BackgroundGSD-YOLOX: Lightweight and more accurate object detection models
Gao, X.-H., Yu, A.-N., Tan, J., Gao, X.-Z., Zeng, X.-P., & Wu, C.-C. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.104009 · Cited by 12
Sathyanarayana, N., & Narasimhamurthy, A. (2022) · Journal of The Institution of Engineers (India) Series B · doi:10.1007/s40031-022-00838-z · Cited by 12
“[18] introduced a sparse Laplacian filter learning model for extracting discriminative and rich information of the vehicles for better classification.”
MethodSentas, A., Tashiev, I., Küçükayvaz, F., Kul, S., Eken, S., Sayar, A., & Becerikli, Y. (2018) · International Conference on Emerging Intelligent Data and Web Technologies · doi:10.1007/978-3-319-75928-9_86 · Cited by 12
Liu, D., Yang, L. T., Zhao, R., Deng, X., Zhu, C., & Ruan, Y. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3364250 · Cited by 16
“The BIT-Vehicle dataset [27] contains six vehicle types.”
BackgroundFast vehicle detection algorithm based on lightweight YOLO7-tiny
Shi, Q.-X., Zhong, F., Li, B., Xu, Z.-W., Hong, J.-J., & Li, R.-X. (2023) · International Conference on Computer Vision and Data Mining · doi:10.1117/12.3048399 · Cited by 11
Yang, L., Luo, J., Song, X., Li, M., Wen, P., & Xiong, Z.-X. (2021) · Entropy · doi:10.3390/e23070910 · Cited by 11
“We randomly select 6103 images with a resolution of 1600 × 1200 from the Open ITS dataset [55], 1921 images with a resolution of 1920 × 1080 from the BIT Vehicle dataset [56], and 280 images with a resolution of 720 × 1160 from the CCPD dataset [57].”
MethodVehicle Speed Monitoring using Convolutional Neural Networks
Barth, V. B. D. O., de Oliveira, R., Oliveira, M. D., & do Nascimento, V. (2019) · IEEE Latin America Transactions · doi:10.1109/tla.2019.8896823 · Cited by 17
“Al [32] foram capazes de classificar veículos em tempo real através de CNNs.”
BackgroundSelbes, B., & Sert, M. (2017) · Advanced Video and Signal Based Surveillance · doi:10.1109/avss.2017.8078514 · Cited by 11
“Although the CNN models are used in vehicle classification task standalone [7, 10], to the best of our knowledge, we integrate CNN features and audio features for vehicle type classification problem in this context for the first time.”
BackgroundMethodResultInfluentialSports Sequence Images Based on Convolutional Neural Network
Chen, Y.-H. (2021) · doi:10.1155/2021/3326847 · Cited by 11
SCD-YOLO: a lightweight vehicle target detection method based on improved YOLOv5n
Li, H., Zhuang, X.-F., Bao, S., Chen, J.-N., & Yang, C. (2024) · J. Electronic Imaging · doi:10.1117/1.jei.33.2.023041 · Cited by 10
Maiga, B., Dalveren, Y., Kara, A., & Derawi, M. (2023) · Sustainability · doi:10.3390/su152316292 · Cited by 10
“The methods presented in [13–24] are proposed for real-time ITS applications that use high-quality monitoring cameras.”
BackgroundMethodInfluentialBasak, S., & Suresh, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16337-2 · Cited by 8
“The work by Roecker et al. [38] presents a model to outperform the model proposed in [15, 16] for vehicle type classification on the BIT-Vehicle dataset.”
InfluentialDetection of Traffic Congestion from Surveillance Videos using Machine Learning Techniques
Rao, S., RamBabu, R., Kumar, B. A., Srinivas, V., & Rao, P. (2022) · 2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac55078.2022.9987342 · Cited by 10
“neural network was proposed in [8], the dataset collected from Manchester, UK.”
BackgroundAnalisis dan Penerapan Algoritma Convolutional Neural Network untuk Klasifikasi Kendaraan Prioritas
Abdulhakim, R., Carudin, & Dermawan, B. A. (2021) · Jurnal Sains dan Informatika · doi:10.34128/jsi.v7i2.335 · Cited by 10
Luo, J., Lu, J., & Yue, G. (2021) · Journal of Electronic Imaging (JEI) · doi:10.1117/1.jei.30.3.033036 · Cited by 10
“The images used in this paper are from Beijing Institute of Technology ’ s (BIT)-Vehicle dataset, 33 which contains images with dimensions of 1600 × 1200 and 1920 × 1080 taken by two cameras at different times and locations.”
MethodEl-Sayed, R. S., & Elsayed, M. N. (2020) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v9.i4.pp700-712 · Cited by 9
“, [6] presented a method for vehicle type classification.”
MethodInfluentialA Vehicle Recognition Algorithm Based on Deep Convolution Neural Network
Yang, Y. (2020) · Traitement du signal · doi:10.18280/ts.370414 · Cited by 10
“Dong et al. [18] developed a CNN-based feature extraction algorithm, and combined the algorithm with support vector machine (SVM) classifier into a recognition system for vehicle types on expressways.”
IRVD: A Large-Scale Dataset for Classification of Iranian Vehicles in Urban Streets
Gholamalinejad, H., & Khosravi, H. (2020) · doi:10.22044/jadm.2020.8438.1982 · Cited by 10
“The ‘BIT-Vehicle dataset’ has been used by [21] and [25] to report encouraging results for vehicle classification.”
MethodSafety evaluation method of hoisting machinery based on neural network
Chen, F. (2020) · Neural computing & applications (Print) · doi:10.1007/s00521-020-04963-y · Cited by 10
Semi-supervised vehicle classification via fusing affinity matrices
Sun, M., Hao, S.-J., & Liu, G.-C. (2018) · Signal Processing · doi:10.1016/j.sigpro.2018.03.006 · Cited by 10
Weakly-supervised vehicle detection and classification by convolutional neural network
Jiang, C., & Zhang, B. (2016) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2016.7852775 · Cited by 11
“Excellent performances have been demonstrated for face detection [10], pedestrian detection [11], image classification [8-9], and vehicle classification [12].”
BackgroundMoving Object Detection and Classification Using Neuro-Fuzzy Approach
Rashidan, M., Mustafah, Y., Shafie, A., Zainuddin, N., Aziz, N., & Azman, A. W. (2016) · International Conference on Multimedia and Ubiquitous Engineering · doi:10.14257/ijmue.2016.11.4.26 · Cited by 10
“In [16], the classification of vehicle frontal-view images use a combination of low level local features and high level global features through two stages of convolutional neural network (CNN).”
BackgroundFarid, D. M., Das, P. K., Islam, M., & Sina, E. (2025) · IEEE Access · doi:10.1109/access.2025.3539713 · Cited by 14
“In 2015, Dong et al. [50] introduced the BIT-Vehicle dataset, which originated from the Beijing Institute of Technology, China.”
Enhanced Road Vehicle Object Detection Based on Improved Deformable DETR
Yin, H., & Chen, L. (2024) · 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit61980.2024.10581739 · Cited by 9
“We conducted experiments using the BIT-Vehicle [10] public dataset as the vehicle detection dataset.”
MethodVehicle detection algorithm based on lightweight YOLOX
Xiong, C., Yu, A.-N., Yuan, S., & Gao, X.-H. (2022) · Signal, Image and Video Processing · doi:10.1007/s11760-022-02390-1 · Cited by 9
“We use a public dataset made by the Beijing Institute of Technology: BIT-Vehicle [30], which includes 9850 images, andmost images have only one or two vehicles.”
MethodHashemi, S., Emami, H., & Sangar, A. B. (2021) · International Journal of Communication Systems · doi:10.1002/dac.4928 · Cited by 9
“High precision (all types of cars: 96%), multiscope, multiscale Dong et al.(46) Good accuracy (frontal-view of cars: 88.”
BackgroundMethodInfluentialLimsoonthrakul, S., Dailey, M. N., Marikhu, R., Timtong, V., Chairat, A., Suphavilai, A., Seetamanotch, W., & Ekpanyapong, M. (2021) · Sustainability · doi:10.3390/su13031210 · Cited by 8
Theagarajan, R., Thakoor, N. S., & Bhanu, B. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2902312 · Cited by 12
“To the best of our knowledge the only other datasets that have night time images are the BITVehicle [12] and MIO-TCD [33] datasets.”
BackgroundVehicle Type Recognition From Surveillance Data Based on Deep Active Learning
Ding, X.-H., Wang, J., Dong, C.-W., & Huang, Y. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2967077 · Cited by 9
“transform (SIFT), oriented contour points, pyramid histogram of oriented gradients (PHOG) [10]–[16].”
BackgroundToward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition
Lima, G. E., Nascimento, V., Santos, E., Nascimento, E., Jr., Laroca, R., & Menotti, D. (2026) · Journal of the Brazilian Computer Society · doi:10.5753/jbcs.2026.5899 · Cited by 8
“Early studies used handcrafted feature extraction methods applied to small and limited datasets [ Fer-ryman et al ., 1995; Jolly et al ., 1996; Lai et al ., 2001; Wu et al ., 2001; Ma and Grimson, 2005].”
Hurr, C., Li, C., & Li, H. (2022) · Mobile Information Systems · doi:10.1155/2022/8982881 · Cited by 8
Automated Truck Taxonomy Classification Using Deep Convolutional Neural Networks
Almutairi, A., He, P., Rangarajan, A., & Ranka, S. (2022) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-022-00306-4 · Cited by 8
“However, CNNs were by far the most-used technique for this problem[13][20][6][3]; some used transfer learning with a CNN[38].”
MethodNezhad, S. A., Khatibi, T., & Sohrabi, M. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/8151177 · Cited by 11
“,e network determines the probability of each class by using a Soft-max activation function in the output layer [44].”
Method3D CHANGE DETECTION IN URBAN AREAS BASED ON DCNN USING A SINGLE IMAGE
Amirkolaee, H. A., & Arefi, H. (2019) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xlii-4-w18-89-2019 · Cited by 8
“…Neural Networks (CNN) in extracting deep and invariant features make them suitable for various topics in remote sensing such as object detection (Dong et al., 2015), height estimation (Amirkolaee and Arefi, 2019b; Ghamisi and Yokoya, 2018), as well as scene classification (Chen et al., 2016).”
BackgroundLiu, D. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3420151 · Cited by 11
“…images are video frames selected from surveillance videos by the dataset authors), i.e., Beijing Institute of Technology (BIT)-Vehicle [13], Vehicle Type Image Data 2 (VTID2) [14], and Vehicle Images Dataset for Make & Model Recognition (VIDMMR) [15], as additional datasets, on which…”
BackgroundMethodResultInfluentialSmart City Traffic Monitoring:YOLOv7 Transfer Learning Approach for Real-Time Vehicle Detection
Baiat, Z. E., & Baydere, Ş. (2023) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets58706.2023.10216009 · Cited by 6
“The model was evaluated on BIT-Vehicle [8] and CompCars [9] datasets and achieved an mAP of 94.”
MethodInfluentialA Comparative Study on Object Detection Using Retinanet
Reddy, B. S., Reddy, A. M., Sradda, M. H. D. S., Mounika, T., Mounika, S., & K, M. (2022) · 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon) · doi:10.1109/mysurucon55714.2022.9972742 · Cited by 7
LiVeR: Lightweight Vehicle Detection and Classification in Real-Time
Shekhar, C., Debadarshini, J., & Saha, S. (2022) · ACM Trans. Internet Things · doi:10.1145/3674150 · Cited by 7
“Latency(ms) [0-5] [5-10][10-15] 0 25 50 75 100”
BackgroundInfluentialSTL-Detector: Detecting City-Wide Ride-Sharing Cars via Self-Taught Learning
Zheng, L., Zheng, L., Dong, X., Sun, D., & Liu, W. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3094530 · Cited by 5
“[17] proposed a novel framework of vehicle type classification from vehicle frontal view images using a convolutional neural network.”
MethodEnd-to-end quantum-inspired method for vehicle classification based on video stream
Derrouz, H., Cabri, A., Abdelali, H. A., Thami, R. O. H., Bourzeix, F., Rovetta, S., & Masulli, F. (2022) · Neural computing & applications (Print) · doi:10.1007/s00521-021-06718-9 · Cited by 7
“To evaluate the proposed method, two types of datasets are used: the well known BITdataset [8] and a Moroccan dataset [5] that contains data collected from Moroccan roads.”
MethodInfluentialMulti-component vehicle type recognition using adapted CNN by optimal transport
Liao, B. Y., He, H., Du, Y. R., & Guan, S. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-02042-w · Cited by 7
“A series of comparative experiments are carried out on BIT-vehicle [25] dataset to verify the effectiveness of OTK.”
MethodŞener, A. Ş., İnce, İ. F., Baydargil, H. B., Garip, İ., & Ozturk, O. (2021) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070211025338 · Cited by 7
“22 In another paper, The VMR method for recognizing most vehicle manufacturers is based on vehicle logo recognition, but the robustness of logo recognition is not sufficient for many reasons, including a study in which the sensitivity can be increased by 99.7% with an algorithm with a pretraining…”
BackgroundMethodInfluentialFast and Accurate Deep Learning Architecture on Vehicle Type Recognition
Surinta, O., & Boonsirisumpun, N. (2021) · Current Applied Science and Technology · doi:10.55003/001 · Cited by 7
“[4], Huttunen et al .”
Vehicle Type Recognition Algorithm Based on Improved Network in Network
Zhu, E., Xu, M., & Pi, D. (2021) · Complexity · doi:10.1155/2021/6061939 · Cited by 8
“[10] adopted the sparse Laplace filter and a semisupervised convolution neural network to extract vehicle features and classify vehicles.”
MethodXu, K., Gong, H., & Liu, F. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.1005 · Cited by 7
“Dong et al. [18] designed a semisupervised CNN for vehicle type classification from frontal view images.”
MethodVehicle Type Recognition Based on Radon-CDT Hybrid Transfer Learning
Guan, S., Liao, B. Y., Du, Y. R., & Yin, X. (2019) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess47205.2019.9040687 · Cited by 8
“E x p e r ime n t a l R es u l t s a n d A n a l y s is In this paper, the popular data set BIT-Vehicle [11] is used for training and testing.”
MethodVehicle Type Classification using Hierarchical Classifiers
Lian, J., Zhang, J., Gan, T., & Jiang, S.-B. (2018) · Journal of Physics: Conference Series · doi:10.1088/1742-6596/1069/1/012099 · Cited by 7
Sliwa, B., Piatkowski, N., Haferkamp, M., Dorn, D., & Wietfeld, C. (2018) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2018.8569391 · Cited by 8
“7% / 6 [7] (multiple datasets) medium no yes no DLW Inertial Sensors 99% / 3 [8], Accelerometer / Magnetometer (few samples) low / high possible yes yes T 93.”
BackgroundNiroomand, N., & Bach, C. (2024) · IEEE Access · doi:10.1109/access.2024.3359990 · Cited by 7
“Semi-supervised clustering endeavors to optimize cluster accuracy by identifying superior clusters in comparison to those obtained through unsupervised learning algorithms [18], [45], [46], [47].”
MethodAfdhal, A., Saddami, K., Arief, M., Sugiarto, S., Fuadi, Z., & Nasaruddin, N. (2024) · IEEE Access · doi:10.1109/access.2024.3507713 · Cited by 12
“Evaluated on two public datasets, BIT-Vehicle [35] and UA-DETRAC [36], the YOLOv4_AF model outperformed all three state-of-the-art models, including EfficientDet [37], Faster R-CNN and the original YOLOv4.”
Spatially Recalibrated Convolutional Neural Network for Vehicle Type Recognition
Tan, S.-H., Chuah, J. H., Chow, C., & Kanesan, J. (2023) · IEEE Access · doi:10.1109/access.2023.3342109 · Cited by 7
“They reported 95.2% on Beijing Institute of Technology (BIT)-Vehicle dataset [20].”
BackgroundMethodInfluentialZhang, H., Li, X., Yuan, H., Liang, H., Wang, Y., & Song, S. (2023) · Sensors · doi:10.3390/s23239569 · Cited by 7
Car Emotion Labeling Based on Color-SSL Semi-Supervised Learning Algorithm by Color Augmentation
Guo, Z., Lin, L., Liu, B., Zhang, L., Chang, K., Li, L., Jiang, Z., & Wu, J. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/4331838 · Cited by 6
Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation
Hu, Z.-J., Lam, W. H. K., Wong, S., Chow, A., & Ma, W. (2021) · arXiv.org · doi:10.48550/arxiv.2111.00941 · Cited by 6
“Existing public datasets are designed for a range of purposes, such as vehicle re-identification (reID), autonomous driving, vehicle detection, etc. (Lin et al. 2014; Deng et al. 2009; Yu et al. 2020; Zhang et al. 2017b; Lyu et al. 2018; Dong et al. 2015; Luo et al. 2018).”
BackgroundOptimization of Vehicle Classification Model using Genetic Algorithm
Cero, C., Sybingco, E., Brillantes, A. K. M., Amon, M. C. E., Puno, J. C., Billones, R. K., Dadios, E., & Bandala, A. A. (2019) · International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management · doi:10.1109/hnicem48295.2019.9072880 · Cited by 6
“Vehicle type classification finds application in different scenarios like vehicle management, analysis of traffic statistics, toll collection and so on [1] [2].”
BackgroundMethodCoarse-to-Fine Context Aggregation Network for Vehicle Make and Model Recognition
Tan, S. H., Chuah, J. H., Chow, C., & Kanesan, J. (2023) · IEEE Access · doi:10.1109/access.2023.3330114 · Cited by 6
“However, the handcrafted features are susceptible to external disturbances and this deteriorates the classification performance in real-life scenarios [34], [35], [36], [37], [38].”
BackgroundCar-1000: A New Large Scale Fine-Grained Visual Categorization Dataset
Hu, Y.-T., Li, S., Yan, J., Shao, W., & Luo, X. (2025) · arXiv.org · doi:10.48550/arxiv.2503.12385 · Cited by 5
“As for other datasets toward fine-grained car classification [7, 26, 28], considering their limited scales, categories and attribute information, none can serve as a comprehensive benchmark.”
Exploring Classification of Vehicles Using Horn Sound Analysis: A Deep Learning-Based Approach
Rafi, M. A. I., Sohan, M. R., Hasan, M. S., Rafa, T. S., & Jawad, A. (2024) · 2024 23rd International Symposium INFOTEH-JAHORINA (INFOTEH) · doi:10.1109/infoteh60418.2024.10496018 · Cited by 5
“Recent studies have shown that machine learning techniques, especially convolutional neural networks (CNNs) [7], can help with identifying environmental sounds, including those produced by different types of vehicles [8, 9].”
BackgroundGeometry-Based Parking Assistance Using Sensor Fusion for Robots With Hardware Schemes
Chinnaiah, M. C., Vani, G. D., Karumuri, S., Srikanthan, T., Lam, S.-K., Narambhatla, J., Krishna, D., & Dubey, S. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3345037 · Cited by 5
Ma, S., Yang, J. J., Chorzepa, M. G., Morris, C., Kim, S.-H. S., & Durham, S. A. (2024) · SN Computer Science · doi:10.1007/s42979-023-02569-4 · Cited by 5
Deep learning based video surveillance for predicting vehicle density in real time scenario
Priyanka, G., Kumar, J., & Veena, S. T. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-023-04549-1 · Cited by 5
Analysis and Research on YOLOv5s Vehicle Detection with CA and BiFPN Fusion
Lin, M.-Y., Wang, Z., & Huang, L. (2022) · 2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE) · doi:10.1109/ecice55674.2022.10042933 · Cited by 5
“The BIT-Vehicle Dataset is used for the experiment [13] as it is a public data set for vehicle detection provided by the Beijing Institute of Technology.”
MethodClassification of vehicle types using fused deep convolutional neural networks
Qian, Z., Zhao, C., Zhang, B.-L., Lin, S., Hua, L., Li, H., Ma, X., Ma, T., & Wang, X.-L. (2022) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-211505 · Cited by 5
Inversion Attacks against CNN Models Based on Timing Attack
Chen, Z., Tang, M., & Li, J. (2022) · Security and Communication Networks · doi:10.1155/2022/6285909 · Cited by 3
Metadata
- Authors
- Dong, Z., Wu, Y., Pei, M., & Jia, Y.
- Affiliations
- Beijing Institute of Technology (CN)
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2015-08
- Volume
- 16
- Issue
- 4
- Pages
- 2247-2256
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2045721916
- Cited by
- 387
- References
- 0
- Citations by year
- 2026: 16 · 2025: 27 · 2024: 41 · 2023: 41 · 2022: 59 · 2021: 52 · 2020: 45 · 2019: 33 · 2018: 34 · 2017: 26 · 2016: 12 · 2015: 1
- FWCI
- 21.13
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- Funders
- National Natural Science Foundation of China (61203291)
- Specialized Research Fund for the Doctoral Program of Higher Education of China (20121101120029)
- Specialized Fund for Joint Building Program of Beijing Municipal Education Commission
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- vehicle classification, semi-supervised learning, convolutional neural networks, unlabeled data, multi-task learning, representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
