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.
Integrity signals
Registry
Cites
Statistics
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?
Recent DL-based solutions have been widely adopted due to their robustness and improved vehicle detection performance in images and videos.
“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]
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 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
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 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning
Sun, Y., Cao, B., Zhu, P., & Hu, Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3168279 · Cited by 732 · see citing works
“Vehicle detection aims to find the location of the vehicle and determine its category [39].”
Convolutional Neural Networks: A Survey
Krichen, M. (2023) · Computers · doi:10.3390/computers12080151 · Cited by 623 · see citing works
Joint Deep Learning for land cover and land use classification
Zhang, C., Sargent, I., Pan, X., Li, H., Gardiner, A., Hare, J. S., & Atkinson, P. (2019) · Remote Sensing of Environment · doi:10.1016/j.rse.2018.11.014 · Cited by 468 · see citing works
“…117 feature representation, the CNN has demonstrated great potential in many remotely sensed 118 tasks such as vehicle detection (Chen et al., 2014; Dong et al., 2015), road network extraction 119 (Cheng et al., 2017), remotely sensed scene classification (Othman et al., 2016), and semantic 120…”
BackgroundReal-Time Vehicle Detection Based on Improved YOLO v5
Zhang, Y., Guo, Z.-Y., Wu, J., Tian, Y., Tang, H., & Guo, X. (2022) · Sustainability · doi:10.3390/su141912274 · Cited by 459 · see citing works
“A total of 1493 pictures with vehicle information were extracted, and the original vehicle detection image library was set with the selection of 1060 pictures of multiple types of vehicles from the BIT Vehicle_Dataset [33].”
MethodAn object-based convolutional neural network (OCNN) for urban land use classification
Zhang, C., Sargent, I., Pan, X., Li, H., Gardiner, A., Hare, J. S., & Atkinson, P. (2018) · Remote Sensing of Environment · doi:10.1016/j.rse.2018.06.034 · Cited by 436 · see citing works
“…and scene understanding, the CNN has demonstrated great potential in 99 many remote sensing tasks such as vehicle detection (Chen et al., 2014; Dong et al., 2015), 100 road network extraction (Cheng et al., 2017), remotely sensed scene classification (Othman et 101 al., 2016; Sargent et al.,…”
BackgroundA hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification
Zhang, C., Pan, X., Li, H., Gardiner, A., Sargent, I., Hare, J. S., & Atkinson, P. (2017) · Isprs Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.07.014 · Cited by 396 · see citing works
“81 In the remote sensing domain, CNNs have been studied actively and shown to produce 82 state-of-the-art results over the past few years, focusing primarily on object detection 83 (Dong et al., 2015) or scene classification (Hu et al., 2015a; Zhang et al., 2016).”
MethodVision-based vehicle detection and counting system using deep learning in highway scenes
Song, H., Liang, H., Li, H., Dai, Z., & Yun, X. (2019) · European Transport Research Review · doi:10.1186/s12544-019-0390-4 · Cited by 392 · see citing works
“The datasets are taken by surveillance cameras; an example is the BIT-Vehicle Dataset [35], which contains 9,850 images.”
MethodA hybrid deep learning CNN–ELM for age and gender classification
Duan, M., Li, K., Yang, C., & Li, K. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.08.062 · Cited by 259 · see citing works
The traffic signal control problem for intersections: a review
Eom, M., & Kim, B.-I. (2020) · European Transport Research Review · doi:10.1186/s12544-020-00440-8 · Cited by 233 · see citing works
An Improved YOLOv2 for Vehicle Detection
Sang, J., Wu, Z., Guo, P., Hu, H., Xiang, H., Zhang, Q., & Cai, B. (2018) · Sensors · doi:10.3390/s18124272 · Cited by 223 · see citing works
“, t i l t ll f r it i , j ec olo ( I )- ehicle [28] and ars [ ], .”
MethodObject Detection through Modified YOLO Neural Network
Ahmad, T., Ma, Y., Yahya, M., Ahmad, B., Nazir, S., & Haq, A. U. (2020) · Scientific Programming · doi:10.1155/2020/8403262 · Cited by 229 · see citing works
Intelligent Traffic Monitoring Systems for Vehicle Classification: A Survey
Won, M. (2019) · IEEE Access · doi:10.1109/access.2020.2987634 · Cited by 167 · see citing works
“applies the semisupervised convolutional neural network (CNN) for feature extraction [72].”
MethodDetecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
Yin, Q., Hu, Q., Liu, H., Zhang, F., Wang, Y., Lin, Z., An, W., & Guo, Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3130436 · Cited by 155 · see citing works
“CLIF [70] 1 24,564 4,016 WPAFB [19] 1 1,025 4,260 NWPU VHR-10 [30] 10 800 ~1,000 VEDAI [33] 3 1,268 512/1,024 3K Vehicle Detection [31] 2 20 5,616 BIT-Vehicle [71] 6 9,850 ~1,600/1,920 VISO (Ours) 4 17,730 12,000”
Applications of Deep Learning in Intelligent Transportation Systems
Haghighat, A., Ravichandra-Mouli, V., Chakraborty, P., Esfandiari, Y., Arabi, S., & Sharma, A. (2020) · Journal of Big Data Analytics in Transportation · doi:10.1007/s42421-020-00020-1 · Cited by 125 · see citing works
“[193] have used a combination of region-of-interest (ROI) performance, CNN feature extraction and an SVM as a classifier to detect arrow signs on the roadway and classify their direction.”
InfluentialA Systematic Review of Drone Based Road Traffic Monitoring System
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2022) · IEEE Access · doi:10.1109/access.2022.3207282 · Cited by 121 · see citing works
“as [2], [3], [23], [24] have been widely adopted due to their 140 robustness and improved vehicle detection performance in 141 images and videos.”
BackgroundATRW: A Benchmark for Amur Tiger Re-identification in the Wild
Li, S., Li, J., Tang, H., Qian, R., & Lin, W. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413569 · Cited by 121 · see citing works
“Vehicles are also an important object for re-ID due to its wide applications in video surveillance [7].”
BackgroundImage Segmentation Using Computational Intelligence Techniques: Review
Chouhan, S. S., Kaul, A., & Singh, U. P. (2018) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-018-9257-4 · Cited by 142 · see citing works
Intelligent Traffic-Monitoring System Based on YOLO and Convolutional Fuzzy Neural Networks
Lin, C.-J., & Jhang, J.-Y. (2022) · IEEE Access · doi:10.1109/access.2022.3147866 · Cited by 116 · see citing works
“Moreover, the two proposed models were compared with other common models, namely AlexNet, GoogLeNet, VGG16, VGG-19, ResNet50, Sparse Laplacian CNN [49], and PCN-Net [50].”
MethodInfluentialRekavandi, A. M., Xu, L., Boussaïd, F., Seghouane, A., Hoefs, S., & Bennamoun, M. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3530678 · Cited by 111 · see citing works
“BIT-Vehicle [230] dataset contains images displaying changes in illumination conditions, vehicle scale, vehicle color, and viewpoints.”
Wearable Vision Assistance System Based on Binocular Sensors for Visually Impaired Users
Jiang, B., Yang, J.-C., Lv, Z., & Song, H. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2842229 · Cited by 107 · see citing works
“This advantage is more obvious when the input of the network is multidimensional image [46], [47].”
Background3D head pose estimation with convolutional neural network trained on synthetic images
Liu, X.-B., Liang, W., Wang, Y., Li, S., & Pei, M.-T. (2016) · International Conference on Information Photonics · doi:10.1109/icip.2016.7532566 · Cited by 106 · see citing works
“Recent years, CNN method shows good performance in many computer vision tasks, such as classification [13, 14], object detection [15], face retrieval [16] and so on.”
MethodSelf-citationSoft computing approaches for image segmentation: a survey
Chouhan, S. S., Kaul, A., & Singh, U. P. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6005-6 · Cited by 114 · see citing works
“in [66] proposed a semi-supervised CNN for the vehicle category identification.”
Object Detection in Traffic Videos: A Survey
Ghahremannezhad, H., Shi, H., & Liu, C. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3258683 · Cited by 121 · see citing works
“The mean average precision (mAP) of object detection on UA-DE-TRAC [60], Peng Cheng [61], UAVDT [62], Haze-Car [63], BIT-Vehicle [64], UTSD [65], and MIO-TCD [66] datasets.”
MethodJagannathan, P., Rajkumar, S., Frnda, J., Divakarachari, P. B., & Prabu, S. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/5590894 · Cited by 106 · see citing works
“[19] implemented a new semisupervised CNN architecture for vehicle type classification.”
MethodInfluentialReal-time vehicle type classification with deep convolutional neural networks
Wang, X.-C., Zhang, W., Wu, X.-C., Xiao, L., Qian, Y.-B., & Fang, Z. (2019) · Journal of Real-Time Image Processing · doi:10.1007/s11554-017-0712-5 · Cited by 101 · see citing works
An Ensemble CNN2ELM for Age Estimation
Duan, M., Li, K.-L., & Li, K.-Q. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2766583 · Cited by 99 · see citing works
“maps [63], [64].”
Learning Transportation Modes From Smartphone Sensors Based on Deep Neural Network
Fang, S.-H., Fei, Y.-X., Xu, Z.-Z., & Tsao, Y. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2737825 · Cited by 97 · see citing works
“Modeling big data using a deep learning model has been performed extensively and is recognized in several applications such as traffic flow prediction [31], speech enhancement [32], [33], and vehicle type classification [34].”
MethodAutomated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
Zhou, W., Berrío, J. S., Worrall, S., & Nebot, E. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2909066 · Cited by 99 · see citing works
“As mentioned in [33], [34] and also shown by our previous work [8], [35], a relatively small dataset with 200 images is”
ResultZhou, Y., Pei, Y., Li, Z., Fang, L., Zhao, Y., & Yi, W. (2020) · Measurement · doi:10.1016/j.measurement.2020.107801 · Cited by 84 · see citing works
Hyper‐parameters optimisation of deep CNN architecture for vehicle logo recognition
Soon, F. C., Khaw, H. Y., Chuah, J. H., & Kanesan, J. (2018) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2018.5127 · Cited by 80
“In the recent decade, CNN has been extensively applied in various areas, i.e. image noise-type recognition [9], vehicle LPR [10], vehicle-type classification [11] etc.”
MethodLi, J., Xu, Z., Fu, L., Zhou, X., & Yu, H. (2021) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102946 · Cited by 80 · see citing works
Deep Learning Techniques for Vehicle Detection and Classification from Images/Videos: A Survey
Berwo, M. A., Khan, A., Fang, Y., Fahim, H., Javaid, S., Mahmood, J., Abideen, Z. U., & Syam, M. S. (2023) · Sensors · doi:10.3390/s23104832 · Cited by 90 · see citing works
Shang, Y., Tang, X., Zhao, G., Jiang, P., & Lin, T. R. (2022) · Measurement · doi:10.1016/j.measurement.2022.111893 · Cited by 103 · see citing works
A lightweight Tiny-YOLOv3 vehicle detection approach
Tajar, A. T., Ramazani, A., & Mansoorizadeh, M. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-021-01131-w · Cited by 76 · see citing works
MPCE: A Maximum Probability Based Cross Entropy Loss Function for Neural Network Classification
Zhou, Y., Wang, X., Zhang, M.-C., Zhu, J.-L., Zheng, R., & Wu, Q.-T. (2019) · IEEE Access · doi:10.1109/access.2019.2946264 · Cited by 76 · see citing works
“At present, softmax function has been wildly used for output layers in multi-classifier learning because of its ability to convert output values into probabilities [25], [26].”
MethodNIRFaceNet: A Convolutional Neural Network for Near-Infrared Face Identification
Peng, M., Wang, C., Chen, T., & Liu, G. (2016) · Inf. · doi:10.3390/info7040061 · Cited by 75 · see citing works
Violence detection and face recognition based on deep learning
Wang, P., Wang, P., & Fan, E. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.11.018 · Cited by 65
Zhang, C., Sargent, I., Pan, X., Gardiner, A., Hare, J. S., & Atkinson, P. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2822783 · Cited by 65 · see citing works
“CNNs have been introduced and actively investigated in the field of remote sensing over the past few years, focusing primarily on object detection [19] and scene classification [20].”
BackgroundZhang, B., & Zhang, J. (2021) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2020.3001154 · Cited by 64 · see citing works
“The current video-based approaches mainly focus on the identification of vehicle type [2], [3], construction of the 3D bounding box [4], [5], measurement of speed [6], [7], vehicle counting [8]–[11] and so on.”
Dabiri, S., Marković, N., Heaslip, K., & Reddy, C. K. (2020) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102644 · Cited by 64
“Afterward, vehicles are classified to several groups using visual features (e.g., width, length, area, and perimeter) computed by traditional vision-based techniques (Kafai and Bhanu, 2012) or abstract automatic features learned by deep-learning algorithms (Dong et al., 2015).”
MethodWang, J., Zheng, H., Huang, Y., & Ding, X.-H. (2018) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2017.2765676 · Cited by 64 · see citing works
“Many pretraining strategies for CNNs, including both supervised [20] and unsupervised strategies [15], have been reported.”
BackgroundMethodButt, M. A., Khattak, A. M., Shafique, S., Hayat, B., Abid, S., Kim, K., Ayub, M. W., Sajid, A., & Adnan, A. (2021) · Complexity · doi:10.1155/2021/6644861 · Cited by 67 · see citing works
“[20] have presented CNN based semisupervised classification method for real-time vehicle classification.”
MethodCao, W., Yuan, J.-H., He, Z., Zhang, Z., & He, Z.-Q. (2018) · IEEE Access · doi:10.1109/access.2018.2795798 · Cited by 57 · see citing works
Swin transformer based vehicle detection in undisciplined traffic environment
Deshmukh, P., Satyanarayana, G., Majhi, S., Sahoo, U. K., & Das, S. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2022.118992 · Cited by 55 · see citing works
A vehicle classification system based on hierarchical multi-SVMs in crowded traffic scenes
Fu, H.-Y., Ma, H., Liu, Y., & Lu, D. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.12.134 · Cited by 53 · see citing works
A Large and Diverse Dataset for Improved Vehicle Make and Model Recognition
Tafazzoli, F., Frigui, H., & Nishiyama, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.121 · Cited by 51 · see citing works
“As of existing vehicle datasets, they either cover a subset of makes and models [24,32], or only categorize vehicles at a high level (i.e., SUV, Truck, Sedan) [6,20], and those usable mainly for vehicle related tasks such as detection and pose estimation [8, 17, 22].”
BackgroundVehicle detection in intelligent transport system under a hazy environment: a survey
Husain, A., Maity, T., & Yadav, R. K. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2018.5351 · Cited by 48 · see citing works
Pamuła, T. (2018) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2018.2842040 · Cited by 48 · see citing works
“In [13] a method for classifying front view vehicles is proposed which uses a semi-supervised method for training a CNN model.”
MethodKim, P.-K., & Lim, K.-T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.126 · Cited by 48 · see citing works
“[4] classify vehicle types using a Convolutional Neural Network on 9,850 high-resolution vehicle frontal-view images.”
MethodSmart real-time evaluation of tunnel fire risk and evacuation safety via computer vision
Zhang, X., Chen, X., Ding, Y., Zhang, Y., Wang, Z., Shi, J., Johansson, N., & Huang, X. (2024) · Safety Science · doi:10.1016/j.ssci.2024.106563 · Cited by 53 · see citing works
Sentas, A., Tashiev, I., Küçükayvaz, F., Kul, S., Eken, S., Sayar, A., & Becerikli, Y. (2018) · Evolutionary Intelligence · doi:10.1007/s12065-018-0167-z · Cited by 47 · see citing works
PCANet-Based Convolutional Neural Network Architecture for a Vehicle Model Recognition System
Soon, F. C., Khaw, H. Y., Chuah, J. H., & Kanesan, J. (2019) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2018.2833620 · Cited by 46
“[16] adopted a semisupervised Convolutional Neural Network (CNN) for vehicle type classification.”
MethodChen, C.-S., Chen, G.-Y., Zhou, D., Jiang, D., & Chen, D. (2024) · arXiv.org · doi:10.48550/arxiv.2402.15761 · Cited by 45
“…seeking to identify various subcategories within a broader category, such as the various species of birds [2], [3], medical images [4], cars [5], [6], aircraft [7], dogs [8], pets [9], flowers [10], natural images [11], [12], etc. Food image recognition is also an important branch of…”
BackgroundCoupled Longitudinal and Lateral Control of a Vehicle using Deep Learning
Devineau, G., Polack, P., Altché, F., & Moutarde, F. (2018) · International Conference on Intelligent Transportation Systems · doi:10.1109/itsc.2018.8570020 · Cited by 45 · see citing works
“For instance, numerous authors make use of CNNs for classification [17], or semantic segmentation [18] purposes.”
BackgroundMonocular Visual Traffic Surveillance: A Review
Zhang, X., Feng, Y., Angeloudis, P., & Demiris, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3147770 · Cited by 54 · see citing works
“They have been widely adopted in vehicle type recognition [7], [8], traffic flow estimation [9], headway [10] and speed [1], [11] measurement, accident detection [12], [13] and prediction [2], and training data generation for behavior learning [14], [15].”
BackgroundFu, Y., Ye, Z., Deng, J., Zheng, X., Huang, Y., Yang, W., Wang, Y., & Wang, K. (2019) · Remote Sensing · doi:10.3390/rs11141678 · Cited by 47 · see citing works
“In the remote sensing domain, deep CNNs have also been actively studied and shown obvious improvements on object detection [21] and scene classification [22].”
Real-Time Vehicle Make and Model Recognition System
Manzoor, M. A., Morgan, Y., & Bais, A. (2019) · Machine Learning and Knowledge Extraction · doi:10.3390/make1020036 · Cited by 44 · see citing works
“propose a two-level semi-supervised Convolution Neural Network (CNN) to learn local and global features and utilize softmax regression to categorize the vehicles in six classes [12].”
MethodFine-grained vehicle type detection and recognition based on dense attention network
Ke, X., & Zhang, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.101 · Cited by 48 · see citing works
Huang, Y., Liu, Z., Jiang, M., Yu, X., & Ding, X.-H. (2020) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2018.2888698 · Cited by 42 · see citing works
“The work in [10] followed an unsupervised pre-training manner on frontal view surveillance images with image reconstruction.”
The Channel as a Traffic Sensor: Vehicle Detection and Classification Based on Radio Fingerprinting
Sliwa, B., Piatkowski, N., & Wietfeld, C. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2983207 · Cited by 41 · see citing works
“Existing systems rely on different communication tech-5 nologies, which mostly operate in the 2.4 GHz band, e.g., Bluetooth [52], [44] or CSI-based WiFi [20].”
BackgroundInfluentialAdaboost-based security level classification of mobile intelligent terminals
Wang, F., Jiang, D.-D., Wen, H., & Song, H. (2019) · Journal of Supercomputing · doi:10.1007/s11227-019-02954-y · Cited by 41 · see citing works
“[17] used the semi-supervised convolutional neural network to classify vehicle types so that it could automatically learn better characteristic parameters for classification in complex scenarios.”
MethodImpact of Driving Behavior on Traffic Delay at a Congested Signalized Intersection
Qi, L., Zhou, M., & Luan, W. (2017) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2016.2613598 · Cited by 40
“In urban environments, more than 80% vehicles are cars [48], [49] with a limit”
BackgroundHazDesNet: An End-to-End Network for Haze Density Prediction
Zhang, J., Min, X.-K., Zhu, Y.-C., Zhai, G.-T., Zhou, J., Yang, X.-K., & Zhang, W.-J. (2022) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2020.3030673 · Cited by 39 · see citing works
“Although some methods overcome the data shortage problem by augmentation [25], [26] and few-shot learning [27], and some other methods are proposed using a small number of training samples [28], [29], these tasks are different from the haze density prediction task.”
MethodSun, W., Zhang, G., Zhang, X., Zhang, X., & Ge, N. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09171-3 · Cited by 116 · see citing works
Towards Understanding Sparse Filtering: A Theoretical Perspective
Zennaro, F. M., & Chen, K. (2016) · Neural Networks · doi:10.1016/j.neunet.2017.11.010 · Cited by 39 · see citing works
“The weight matrix W can be interpreted as a dictionary (Denil and de Freitas, 2012) or as a filter bank (Dong et al., 2015), where each row is a codeword or a filter applied to every sample in the columns of X .”
BackgroundA Super-Learner Ensemble of Deep Networks for Vehicle-Type Classification
Hedeya, M. A., Eid, A., & Abdel-Kader, R. F. (2020) · IEEE Access · doi:10.1109/access.2020.2997286 · Cited by 39 · see citing works
“[6] used a pre-trained Convolutional Neural Network together with multi-task learning to classify the vehicles into Bus, Microbus, Minivan, Sedan, SUV, and Truck from vehicle”
BackgroundMethodInfluentialAmur Tiger Re-identification in the Wild
Li, S., Li, J., Lin, W.-Y., & Tang, H.-L. (2019) · arXiv.org · doi:10.48550/arxiv.1906.05586 · Cited by 37
“Vehicles are also an important object for re-ID due to its wide applications in video surveillance [7].”
BackgroundVehicle Speed Measurement Based on Binocular Stereovision System
Yang, L., Li, M., Song, X., Xiong, Z.-X., Hou, C., & Qu, B. (2019) · IEEE Access · doi:10.1109/access.2019.2932120 · Cited by 36 · see citing works
“Beijing [42], and all 1402 images from an open license plate dataset (resolution 1600×1200) provided by the OpenITS”
MethodDistributed and collaborative real-time vehicle detection and classification over the video streams
Kul, S., Eken, S., & Sayar, A. (2017) · doi:10.1177/1729881417720782 · Cited by 36
Fingerprint Recognition using Convolution Neural Network with Inversion and Augmented Techniques
Garg, R., Singh, G., Singh, A., & Singh, M. (2024) · Systems and Soft Computing · doi:10.1016/j.sasc.2024.200106 · Cited by 35 · see citing works
Location-aware fine-grained vehicle type recognition using multi-task deep networks
Hu, B., Lai, J., & Guo, C. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.02.085 · Cited by 35 · see citing works
Shin, H., Na, K., Chang, J., & Uhm, T. (2022) · ETRI Journal · doi:10.4218/etrij.2021-0395 · Cited by 34 · see citing works
“There are BIT Vehicle [16] and GTI Vehicle [17] datasets related to vehicles, and research on vehicle tracking, including rough classification (such as bus, SUV, sedan, and truck) and vehicle detection, is in progress.”
BackgroundObject Detection Based on Improved YOLOv3-tiny
Gong, H., Li, H., Xu, K., & Zhang, Y. (2019) · ACM Cloud and Autonomic Computing Conference · doi:10.1109/cac48633.2019.8996750 · Cited by 34 · see citing works
“Our datasets consist of a partial COCO dataset and BITVehicle dataset [21].”
MethodMultiple vehicle tracking and classification system with a convolutional neural network
Kim, H. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01429-5 · Cited by 34 · see citing works
Sharma, P., Singh, A., Singh, K., & Dhull, A. (2021) · Multimedia tools and applications · doi:10.1007/s11042-020-10366-x · Cited by 33 · see citing works
“Initially some semi-supervised/ unsupervised two stage CNNs were used for the classification [5, 6].”
MethodAutomated Vehicle Detection and Classification
Boukerche, A., Siddiqui, A. J., & Mammeri, A. (2017) · ACM Computing Surveys · doi:10.1145/3107614 · Cited by 81 · see citing works
“(Dong et al. 2015) Bus (558), MicroBus (883), Minivan (476), SUV (1392), Sedan (5922), Truck (822) Slight variations Day, Evening, Night”
BackgroundMethodInfluentialFuzzy based Pooling in Convolutional Neural Network for Image Classification
Sharma, T., Singh, V., Sudhakaran, S., & Verma, N. (2019) · IEEE International Conference on Fuzzy Systems · doi:10.1109/fuzz-ieee.2019.8859010 · Cited by 31 · see citing works
“• Output Layer: The SoftMax classifier [10] is commonly used as the output layer for classification problems.”
MethodA Hierarchical Scheme for Vehicle Make and Model Recognition From Frontal Images of Vehicles
Lu, L., & Huang, H. (2019) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2018.2835471 · Cited by 31 · see citing works
“Previous work [15], [18]–[25] has made many attempts on”
Deep Learning-Based Vehicle Classification for Low Quality Images
Tas, S., Sari, O., Dalveren, Y., Pazar, S., Kara, A., & Derawi, M. (2022) · Italian National Conference on Sensors · doi:10.3390/s22134740 · Cited by 29
“Another classification method using semisupervised convolutional neural network (CNN) is presented in [14].”
MethodDetection of Gaussian noise and its level using deep convolutional neural network
Chuah, J. H., Khaw, H. Y., Soon, F. C., & Chow, C. (2017) · IEEE Region 10 Conference · doi:10.1109/tencon.2017.8228272 · Cited by 29 · see citing works
“Among them, convolutional neural network (CNN) has been widely applied in fields like image deconvolution [18], image denoising [19, 20], vehicle type classification [21], face recognition [22] and many more.”
BackgroundVehicle type classification and attribute prediction using multi-task RCNN
Huo, Z., Xia, Y., & Zhang, B.-L. (2016) · 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2016.7852774 · Cited by 29 · see citing works
Vehicle logo recognition using whitening transformation and deep learning
Soon, F. C., Khaw, H. Y., Chuah, J. H., & Kanesan, J. (2018) · Signal, Image and Video Processing · doi:10.1007/s11760-018-1335-4 · Cited by 28 · see citing works
BSV-PAGS: Blockchain-based special vehicles priority access guarantee scheme
Wang, Y., Yu, J.-G., Yan, B., Wang, G.-J., & Shan, Z. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.07.012 · Cited by 27 · see citing works
Semisupervised PCA Convolutional Network for Vehicle Type Classification
Soon, F. C., Khaw, H. Y., Chuah, J. H., & Kanesan, J. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3000306 · Cited by 27 · see citing works
“To validate the classification performance of the proposed PCN with the work of [1], we”
BackgroundMethodInfluentialMulti-View Vehicle Type Recognition With Feedback-Enhancement Multi-Branch CNNs
Chen, Z.-B., Ying, C., Lin, C., Liu, S., & Li, W. (2019) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2017.2737460 · Cited by 27 · see citing works
“nizing vehicles of several types in images that contain more than one vehicles [8], [9].”
BackgroundR-CNN Based Vehicle Object Detection via Segmentation Capabilities in Road Scenes
Chughtai, B. R., Alhasson, H. F., Alnusayri, M., Alatiyyah, M., Aljuaid, H., Jalal, A., & Park, J. (2025) · IEEE Access · doi:10.1109/access.2024.3524453 · Cited by 27 · see citing works
“In [75] the paper presents a vehicle type classification approach using a semi supervised convolutional neural network (CNN) trained on frontal-view vehicle images.”
Ni, X., & Huttunen, H. J. (2020) · Journal of Signal Processing Systems · doi:10.1007/s11265-020-01567-6 · Cited by 27 · see citing works
Gholamalinejad, H., & Khosravi, H. (2021) · Expert systems with applications · doi:10.1016/j.eswa.2021.115420 · Cited by 25 · see citing works
Joint 3D Reconstruction and Object Tracking for Traffic Video Analysis Under IoV Environment
Cao, M.-W., Zheng, L.-P., Jia, W., & Liu, X.-P. (2021) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2020.2995768 · Cited by 25 · see citing works
“[19] proposed a semi-supervised convolutional”
Yu, Y., Guan, H., Li, D.-L., & Yu, C. (2019) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2019.2956082 · Cited by 25 · see citing works
“In addition, semisupervised CNN with sparse Laplacian filter learning was also developed for vehicle type recognition [10].”
MethodWang, K., Hao, W., Sun, Z., Wang, S., Tan, E., Li, L., & Jin, Y.-L. (2018) · IEEE Access · doi:10.1109/access.2018.2879809 · Cited by 25 · see citing works
“As a specific type of deep neural network (DNN), CNN was successfully applied in image classification tasks [18], a method was introduced to classifying front view vehicles, which used a semi-supervised approach for training a CNN model [19].”
MethodAutomatic Vehicle type Classification with Convolutional Neural Networks
Roecker, M. N., Costa, Y., Almeida, J. L. R., & Matsushita, G. H. G. (2018) · International Conference on Systems, Signals, and Image Processing · doi:10.1109/iwssip.2018.8439406 · Cited by 25 · see citing works
“As a result, using supervised training with high-intensity data augmentation, we achieved state-ofart accuracy on the BIT-Vehicle Dataset [2].”
BackgroundMethodInfluentialA Lightweight Vehicle Detection Method Fusing GSConv and Coordinate Attention Mechanism
Huang, D., Tu, Y., Zhang, Z., & Ye, Z. (2024) · Italian National Conference on Sensors · doi:10.3390/s24082394 · Cited by 24 · see citing works
“( ) ( ) 2 2 2 2 2 2 = − + − prd gt prd gt d x x y y (6) In this paper, the BIT-Vehicle vehicle dataset released by the Beijing Institute of Technology is used [35], which has six model categories, namely SUV, Sedan, Microbus, Truck, Bus and Minivan.”
MethodHussain, K., Afifi, M., & Moussa, G. S. (2019) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2018.2838117 · Cited by 24 · see citing works
“[4] presented a semi-supervised Convolutional Neural Network (CNN) achieving 88.”
BackgroundMethodInfluentialObject identification for inventory management using convolutional neural network
Verma, N., Sharma, T., Rajurkar, S. D., & Salour, A. (2016) · International Conference on Artificial Intelligence and Pattern Recognition · doi:10.1109/aipr.2016.8010578 · Cited by 24 · see citing works
“In Neural Network, Softmax Classifier [39] is used to classify the input image among various classes.”
MethodVehicle Detection and Type Classification Based on CNN-SVM
Karungaru, S., Dongyang, L., & Terada, K. (2021) · International Journal of Machine Learning and Computing · doi:10.18178/ijmlc.2021.11.4.1052 · Cited by 23 · see citing works
“The dataset used in this work is based on BIT-Vehicle [12], which is a dataset produced by the Beijing Institute of Technology.”
MethodA Vehicle Detection Method Based on Improved YOLOv3
Shi, J., Qu, X., Feng, Y., & Wang, C. (2021) · IEEE Advanced Information Technology, Electronic and Automation Control Conference · doi:10.1109/iaeac50856.2021.9391043 · Cited by 23 · see citing works
“This article uses BIT-Vehicle Dataset as the dataset to train the model[15].”
MethodAwang, S., Azmi, N., & Rahman, M. A. (2020) · IEEE Access · doi:10.1109/access.2019.2963486 · Cited by 23
“[9], [10] extracted vehicle features from grayscale images by introducing unsupervised and semi-supervised CNN, respectively.”
BackgroundMethodResultInfluentialShi, Y., Lv, F., Wang, X., Xia, C., Li, S., Yang, S., Xi, T., & Zhang, G. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00673 · Cited by 15 · see citing works
“As well as for vehicle data, we use an open-source dataset, BIT-Vehicle [7] to construct the test set.”
MethodDevi, N., Kavida, A. C., & Murugan, R. (2022) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-022-01506-x · Cited by 22 · see citing works
“CNN has been studied actively in the remote sensing domain and produced state-of-the-art results over the past few years, focusing primarily on object detection (Dong et al., 2015) or scene classification (Hu et al., 2015).”
Background
- 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
