An Improved YOLOv2 for Vehicle Detection
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Vehicle detection is one of the important applications of object detection in intelligent transportation systems. It aims to extract specific vehicle-type information from pictures or videos containing vehicles. To solve the problems of existing vehicle detection, such as the lack of vehicle-type recognition, low detection accuracy, and slow speed, a new vehicle detection model YOLOv2_Vehicle based on YOLOv2 is proposed in this paper. The k-means++ clustering algorithm was used to cluster the vehicle bounding boxes on the training dataset, and six anchor boxes with different sizes were selected. Considering that the different scales of the vehicles may influence the vehicle detection model, normalization was applied to improve the loss calculation method for length and width of bounding boxes. To improve the feature extraction ability of the network, the multi-layer feature fusion strategy was adopted, and the repeated convolution layers in high layers were removed. The experimental results on the Beijing Institute of Technology (BIT)-Vehicle validation dataset demonstrated that the mean Average Precision (mAP) could reach 94.78%. The proposed model also showed excellent generalization ability on the CompCars test dataset, where the “vehicle face” is quite different from the training dataset. With the comparison experiments, it was proven that the proposed method is effective for vehicle detection. In addition, with network visualization, the proposed model showed excellent feature extraction ability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures













Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“As compared to the state-of-the-art-algorithms that were employed in previous studies [29][30][31][32], the proposed algorithm attained the highest performance, followed by [29], as it achieved a mAP of 94.78% while using the YOLOv2 object detector as shown in Figure 10.”
From A Real-Time Computer Vision Based Approach to Detection and Classification of Traffic Incidents (2023) · cites this paper as [29]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“A new network structure Darknet-19 was designed by removing the full connection layers of the network, and batch normalization [27] was applied to each layer Referring to the anchor mechanism of Faster R-CNN, k-means clustering was used to obtain the anchor boxes.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“However, as a general object detection model, YOLOv2 is applicable to cases where there are a variety of classes to be detected, and the differences among the classes are large, such as persons, horses, and bicycles.”
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 3×
“In this paper, two vehicle datasets collected from road monitoring, the Beijing Institute of Technology (BIT)-Vehicle [28] and CompCars [29], were used.”
MethodDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“CompCars only includes two vehicle types: sedan and SUV, with more than 40,000 images.”
BackgroundYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 3×
“This method can observe of vehicle edge information, which indicates that the convolution kernel in the first layer successfully shows”
MethodInfluential
Research works printed but not linked: 2
- Sang, 2017, Vehicle detection based on faster-RCNN, J. Chongqing Univ. (Nat. Sci. Ed.), 40, 32
- Arthur, D., and Vassilvitskii, S. (2007, January 7–9). k-means++: The advantages of careful seeding. Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, New Orleans, LA, USA.
Cited by
Recent Advancements in End-to-End Autonomous Driving Using Deep Learning: A Survey
Chib, P. S., & Singh, P. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3318070 · Cited by 301
“BIT [125] 2015 ✓ ✓ ✓ 9850 frames Beijing Academics”
Traffic flow estimation with data from a video surveillance camera
Fedorov, A., Nikolskaia, K., Ivanov, S., Shepelev, V., & Minbaleev, A. (2019) · Journal Of Big Data · doi:10.1186/s40537-019-0234-z · Cited by 149
Humayun, M., Ashfaq, F., Jhanjhi, N. Z., & Alsadun, M. K. (2022) · Electronics · doi:10.3390/electronics11172748 · Cited by 138
Vision-Based Autonomous Vehicle Systems Based on Deep Learning: A Systematic Literature Review
Pavel, M. I., Tan, S. Y., & Abdullah, A. (2022) · Applied Sciences · doi:10.3390/app12146831 · Cited by 160
A Real-Time Computer Vision Based Approach to Detection and Classification of Traffic Incidents
Basheer Ahmed, M. I., Zaghdoud, R., Ahmed, M. S., Sendi, R., Alsharif, S., Alabdulkarim, J., Albin Saad, B. A., Alsabt, R., Rahman, A., & Krishnasamy, G. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7010022 · Cited by 122
YOLOv7-RAR for Urban Vehicle Detection
Zhang, Y., Sun, Y., Wang, Z., & Jiang, Y. (2023) · Sensors · doi:10.3390/s23041801 · Cited by 119
“Jun Sang et al. [30] studied and created the improved YOLOv2.”
BackgroundGeetha, A. S., Alif, M. A. R., Hussain, M., & Allen, P. (2024) · Vehicles · doi:10.3390/vehicles6030065 · Cited by 130
“YOLOv2, leveraging GPU features and the anchor box technique, improved upon its predecessor in the detection, classification, and tracking of vehicles [34].”
MethodTagliavini, L., Colucci, G. P., Botta, A., Cavallone, P., Baglieri, L., & Quaglia, G. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01745-7 · Cited by 105
“1 3 recognition [51, 52], semantic place [53, 54], activity [55] and terrain classification [56], 3D environment representation [57], gesture and voice recognition [58, 59], road [60], vehicle [61, 62], pedestrian detection [63], object tracking [64], human [65] and environment change detection [66].”
BackgroundDeep 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 108
Neupane, B., Horanont, T., & Aryal, J. (2022) · Sensors · doi:10.3390/s22103813 · Cited by 85
“[23] came up with an improved detection model based on YOLOv2, which used the k-means++ algorithm to train a dataset to cluster vehicle bounding boxes.”
MethodDeep learning serves traffic safety analysis: A forward‐looking review
Razi, A., Chen, X., Li, H., Wang, H., Russo, B. J., Chen, Y., & Yu, H. (2022) · IET Intelligent Transport Systems · doi:10.1049/itr2.12257 · Cited by 98
Luo, J., Fang, H., Shao, F., Zhong, Y., & Hua, X. (2020) · Defence Technology · doi:10.1016/j.dt.2020.10.006 · Cited by 88
Sekkat, H., Tigani, S., Saadane, R., & Chehri, A. (2021) · Applied Sciences · doi:10.3390/app11177917 · Cited by 84
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 89
Front Vehicle Detection Algorithm for Smart Car Based on Improved SSD Model
Cao, J., Song, C., Song, S., Peng, S., Wang, D., Shao, Y., & Xiao, F. (2020) · Sensors · doi:10.3390/s20164646 · Cited by 69
Enhanced Self-Checkout System for Retail Based on Improved YOLOv10
Tan, L., Liu, S., Gao, J., Liu, X., Chu, L., & Jiang, H. (2024) · Journal of Imaging · doi:10.3390/jimaging10100248 · Cited by 69
“The corresponding equation is as follows: where IoU measures the overlap between the predicted bounding box and the true bounding box; “d” is the Euclidean distance between the centers of the predicted and true bounding boxes, and “c” is the diagonal length of the smallest enclosing box that…”
BackgroundImpedovo, D., Balducci, F., Dentamaro, V., & Pirlo, G. (2019) · Sensors · doi:10.3390/s19235213 · Cited by 61
“YOLO has been successfully used for Vehicle Detection in [29] where the focal loss is exploited and validated on the BIT-Vehicle dataset and in [30] where, on the same dataset, a mean Average Precision (mAP) of 94.78% is reported.”
MethodInfluentialOsmani, K., & Schulz, D. (2024) · Sensors · doi:10.3390/s24103064 · Cited by 72
“In this context, regression-based approaches aim to compute the object’s correlative and class probability, including YOLO [164], YOLOv2 [165], YOLOv3 [166], YOLOv4 [167], and YOLOv5 [168].”
MethodAutomated pavement detection and artificial intelligence pavement image data processing technology
Shang, J., Zhang, A. A., Dong, Z., Zhang, H., & He, A. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105797 · Cited by 59
Densely-Populated Traffic Detection Using YOLOv5 and Non-maximum Suppression Ensembling
Rahman, R., Azad, Z. B., & Hasan, M. B. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-6636-0_43 · Cited by 62
“Recently, YOLO is being used for vehicle detection [13, 14, 15].”
MethodKhalifa, O. O., Wajdi, M., Saeed, R. A., Hashim, A. H. A., Ahmed, M. Z., & Ali, E. S. (2022) · Journal of Advanced Transportation · doi:10.1155/2022/9189600 · Cited by 60
“To cluster the vehicle bounding boxes in training datasets, the k-means algorithm was proposed and coupled with six differently sized anchor boxes [3]. method also applied normalization to improve the detection of the bounding boxes with different aspect ratios.”
BackgroundMethodRetractedA Robust Framework for Object Detection in a Traffic Surveillance System
Akhtar, M. J., Mahum, R., Butt, F. S., Amin, R., El‐Sherbeeny, A. M., Lee, S. M., & Shaikh, S. (2022) · Electronics · doi:10.3390/electronics11213425 · Cited by 56
Comparison of YOLO Versions for Object Detection from Aerial Images
Atik, M. E., Duran, Z., & ÖZGÜNLÜK, R. (2021) · International Journal of Environment and Geoinformatics · doi:10.30897/ijegeo.1010741 · Cited by 61
Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network
Mostofa, M., Ferdous, S. N., Riggan, B. S., & Nasrabadi, N. M. (2020) · IEEE Access · doi:10.1109/access.2020.2990870 · Cited by 53
“Carlet and Abayowa [26] proposed a modified YOLOv2 [27] for locating vehicles in aerial imagery.”
BackgroundMa, R., Zhang, Z., Dong, Y.-Q., & Pan, Y. (2020) · Italian National Conference on Sensors · doi:10.3390/s20185051 · Cited by 36
“Videos are obtained from the perspective of front or side view [17,18].”
BackgroundOrientation- and Scale-Invariant Multi-Vehicle Detection and Tracking from Unmanned Aerial Videos
Wang, J., Simeonova, S., & Shahbazi, M. (2019) · Remote Sensing · doi:10.3390/rs11182155 · Cited by 50
“…11 fps) with F1-score of 39% [40], varying resolutions up to 608 × 608 pixels with processing time of 0.038 sec per frame (~26 fps) with mAP of 68% [42], resolution of 960 × 540 pixels at 9 fps with mAP of 85% [43], resolution of 512 × 512 pixels at 75 fps with mAP of 80%–89% [44], resolution of…”
BackgroundMethodInfluentialObject Detection Algorithm Based on Multi-Scaled Convolutional Neural Networks
Nandhini, T. J., & Thinakaran, K. (2023) · International Conference on Artificial Intelligence and Signal Processing (AISP) · doi:10.1109/aisp57993.2023.10134980 · Cited by 49
“Within the confines of the laboratory, our model was conceived and eventually perfected [15].”
MethodDetection of vehicle with Infrared images in Road Traffic using YOLO computational mechanism
Mahmood, M. T., Ahmed, S. R., & Ahmed, M. R. (2020) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/928/2/022027 · Cited by 47
“The various scales of the vehicle may influence the vehicle detection model[2].”
BackgroundAlshehri, M. S., Wu, T., Almujally, N. A., Alqahtani, Y., Hanzla, M., Jalal, A., & Liu, H. (2025) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2025.1681341 · Cited by 50
“Improvements such as k-means clustering for anchor box generation and multi-scale feature fusion have further enhanced earlier YOLO versions; for instance, Sang et al. (2018) proposed BIT-Vehicle dataset using an optimized YOLOv2 model.”
SE-Lightweight YOLO: Higher Accuracy in YOLO Detection for Vehicle Inspection
Niu, C., Song, Y., & Zhao, X. (2023) · Applied Sciences · doi:10.3390/app132413052 · Cited by 38
MEB-YOLO: An Efficient Vehicle Detection Method in Complex Traffic Road Scenes
Song, Y., Hong, S., Hu, C., He, P., Tao, L., Tie, Z., & Ding, C. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.038910 · Cited by 46
Kul, S., Tashiev, İ., Şentaş, A., & Sayar, A. (2021) · IEEE Access · doi:10.1109/access.2021.3085736 · Cited by 38
“Table 5 shows our test result for YOLOv4, YOLOv4-Tiny and compared them with the model results proposed by Sang et al. [61] and Sang et al. [62].”
ResultSeong, S., Song, J., Yoon, D., Kim, J., & Choi, J. (2019) · Sensors · doi:10.3390/s19194263 · Cited by 32
“YOLOv2, which is a representative end-to-end object-detection algorithm based on CNN, was applied to vehicle detection in a single image [27].”
BackgroundMethodMTSDet: multi-scale traffic sign detection with attention and path aggregation
Wei, H., Zhang, Q., Qian, Y., Xu, Z., & Han, J. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03459-7 · Cited by 32
“As can be seen from Table 2, MTSDet has improved mAP compared to the advanced methods of YOLOv2, YOLOv3, SSD, RetinaNet, Cascade RCNN, Faster RCNN, HRNet, Detr, Libra RCNN, and Doublehead RCNN by 11.2%, 5.3%, 4.5%, 6.9%, 1.1%, 7.4%, 4.3%, 10.4%, 9.8%, 3.4%.”
MethodInfluentialSelf-citationEnd-to-end trainable network for degraded license plate detection via vehicle-plate relation mining
Chen, S.-L., Tian, S., Ma, J.-W., Liu, Q., Yang, C. H., Chen, F., & Yin, X.-C. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.040 · Cited by 31
Last Decade in Vehicle Detection and Classification: A Comprehensive Survey
Maity, S., Bhattacharyya, A., Singh, P. K., Kumar, M., & Sarkar, R. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-022-09764-1 · Cited by 33
“Sang et al. [93] adopted a multilayer fusion strategy.”
BackgroundVehicle detection in thermal images with an improved yolov3-tiny
Gong, J., Zhao, J., Li, F., & Zhang, H. (2020) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics50287.2020.9201995 · Cited by 30
“The current vehicle detection methods can be mainly divided into two types [2]: the traditional machine-learning-based methods and the deep-learning-based methods.”
MethodMulti-object Recognition Method Based on Improved YOLOv2 Model
Shi, B., Li, X., Nie, T., Zhang, K., & Wang, W. (2021) · Information Technology And Control · doi:10.5755/j01.itc.50.1.25094 · Cited by 31
“In summary, the YOLOv2 object detection algorithm is used to solve the low recognition rate problem, which caused by vehicle shape, structure color and real scene complex features [23].”
MethodA System for a Real-Time Electronic Component Detection and Classification on a Conveyor Belt
Varna, D., & Abromavičius, V. (2022) · Applied Sciences · doi:10.3390/app12115608 · Cited by 31
Real-Time Vehicle Object Detection Method Based on Multi-Scale Feature Fusion
Guo, K., Li, X., Zhang, M., Bao, Q., & Yang, M. (2021) · IEEE Access · doi:10.1109/access.2021.3104849 · Cited by 30
“R-CNN (Region-based Convolutional Network) [29] candidate frame is obtained by a selective search algorithm, then the candidate region is extracted by a deep convolutional neural network.”
MethodMulti-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 proposed method was compared with YOLOv2_Vehicle [27] and the other methods for vehicle detection. detection.”
MethodInfluentialSelf-citationVision-based Autonomous Vehicle Recognition: A New Challenge for Deep Learning-based Systems
Boukerche, A., & Ma, X. (2021) · ACM Computing Surveys · doi:10.1145/3447866 · Cited by 36
“Therefore, the authors extended [93] and proposed Rk-means++ to enhance the model adaptability to vehicles of various sizes to achieve multi-scale detection.”
BackgroundMethodObject Detection Using Stacked YOLOv3
Padmanabula, S. S., Puvvada, R. C., Sistla, V., & Kolli, V. K. K. (2020) · Ingénierie des systèmes d information · doi:10.18280/isi.250517 · Cited by 28
“It will detect objects quickly with high exactitude and has been successfully appealed in many detection problems [13-15].”
BackgroundMethodVehicle Detection and Ranging Using Two Different Focal Length Cameras
Liu, J., & Zhang, R. (2020) · Journal of Sensors · doi:10.1155/2020/4372847 · Cited by 27
“Sang et al. proposed an improved YOLOv2 to improve detection accuracy and speed [27].”
BackgroundPan, X., Li, S., Li, R., & Sun, N. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3213018 · Cited by 23
“Machine learning algorithms, such as vehicle detection methods based on histogram of oriented gradients (HOG) and support vector machine (SVM), relatively low efficiency, and is prone to mishandling, as well as some of the deep learning methods that are proposed in recent years [12], [13].”
BackgroundHasibuan, N. N., Zarlis, M., & Efendi, S. (2021) · SinkrOn · doi:10.33395/sinkron.v6i1.11231 · Cited by 29
“Determining vehicle density on the road and video surveillance analysis help a lot in traffic management systems (Sang et al. 2018).”
HFC-YOLO11: A Lightweight Model for the Accurate Recognition of Tiny Remote Sensing Targets
Bai, J., Zhu, W., Nie, Z., Yang, X., Qing-lin, X., & Li, D. (2025) · Computers · doi:10.3390/computers14050195 · Cited by 21
Real-Time Fire Detection Method for Electric Vehicle Charging Stations Based on Machine Vision
Zhang, S., Yang, Q., Gao, Y., & Gao, D. (2022) · World Electric Vehicle Journal · doi:10.3390/wevj13020023 · Cited by 20
“In [6–8], the YOLOv2 lgorithm was widely used in target detection.”
MethodGuo, F., Wang, Y., & Qian, Y. X. (2022) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2022.100427 · Cited by 25
An Active Multi-Object Ultrafast Tracking System with CNN-Based Hybrid Object Detection
Li, Q., Hu, S., Shimasaki, K., & Ishii, I. (2023) · Sensors · doi:10.3390/s23084150 · Cited by 23
“In follow-up studies, algorithms such as YOLOv2 [53], YOLOv3 [54], YOLOv4 [55], YOLOv5 [56], and YOLOv6 [57] have been proposed.”
A Low Cost Edge Computing and LoRaWAN Real Time Video Analytics for Road Traffic Monitoring
Yassin, S. S., Zennaro, M., Libsie, M., Pietrosémoli, E., & Manzoni, P. (2020) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn50589.2020.00130 · Cited by 20
“Since speed is the main requirement for real-time vehicle detection and counting, and given that YOLO v3 is faster than SSD and Faster RCNN [11], we chose YOLO v3 as our object detection machine learning model (transfer learning) for vehicle detection and counting.”
MethodSaeedizadeh, N., Jalali, S. M. J., Khan, B., & Mohamed, S. M. K. (2025) · Expert Systems · doi:10.1111/exsy.70020 · Cited by 21
Real-Time Fuel Truck Detection Algorithm Based on Deep Convolutional Neural Network
Alsanad, H. R., Osman Nuri, U. C. A. N., Ilyas, M., Khan, A. U. R., & Bayat, O. (2020) · IEEE Access · doi:10.1109/access.2020.3005391 · Cited by 19
“References [30]–[35] explored vehicle detection using CNNs.”
Optimized YOLOv2 based vehicle classification and tracking for intelligent transportation system
Kavitha, N., & Chandrappa, D. N. (2021) · Results in Control and Optimization · doi:10.1016/j.rico.2021.100008 · Cited by 19
Survey on Image-Based Vehicle Detection Methods
Adam, M. A. A., & Tapamo, J. (2025) · World Electric Vehicle Journal · doi:10.3390/wevj16060303 · Cited by 18
ID-Net: an improved mask R-CNN model for intrusion detection under power grid surveillance
Gao, F., Ji, S., Guo, J., Li, Q., Ji, Y., Liu, Y., Feng, S., Wei, H., Wang, N., & Yang, B. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05688-2 · Cited by 19
Deep learning-based vehicle detection from orthophoto and spatial accuracy analysis
Bıyık, M. Y., Atik, M. E., & Duran, Z. (2022) · International Journal of Engineering and Geosciences · doi:10.26833/ijeg.1080624 · Cited by 18
Chen, Y., & Wu-sheng, H. (2021) · IEEE Access · doi:10.1109/access.2021.3051659 · Cited by 17
“Moreover, the accuracy of the results may not necessarily improve with the increasing of training sets, and suitability may be more important, such as SSD + ResNet [49] and SSD + VGG16 [50], YOLOv2 + DarkNet19 [51] and YOLOv3 + DarkNet53 [52].”
BackgroundFlexible neural network for fast and accurate road scene perception
Mehtab, S., & Yan, W. Q. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-11933-0 · Cited by 28
“Sang et al. [31] modified YOLOv2 by combining k -means++ clustering algorithm for generating best-fit anchor box.”
MethodNeuLens: spatial-based dynamic acceleration of convolutional neural networks on edge
Hou, X., Guan, Y., & Han, T. (2022) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3495243.3560528 · Cited by 23
“…of ARAC supernet in other vision applications, including action recognition [16], traffic accident detection [2], abnormal activity detection [10], traffic sign recognition [66], flower classification [82], vehicle detection [64], fall detection [6], vehicle make and model recognition [70].”
BackgroundLim, J., Lee, J., An, C., & Park, E. (2024) · IET Intelligent Transport Systems · doi:10.1049/itr2.12576 · Cited by 16
A Novel Smart Lightweight Visual Attention Model for Fine-Grained Vehicle Recognition
Boukerche, A., & Ma, X. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3131530 · Cited by 19
Application of YOLO Algorithm for Intelligent Transportation Systems: A Survey and New Perspectives
Lv, X., Chen, T., Song, C., Yang, C., & Ping, T. (2025) · International Journal of Distributed Sensor Networks · doi:10.1155/dsn/2859040 · Cited by 15
“Bochkovskiy et al. [13] Sang et al. [114] License plate recognition and counting (cid:129) Rapidly locate license plates in images or video streams.”
Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net
Ge, Y., Jiang, D., & Sun, L. (2023) · Sensors · doi:10.3390/s23104837 · Cited by 15
“These methods are widely used in many areas, such as vehicle detection [8], ship detection [9], face recognition [10], agricultural pest monitoring [11], etc., as well as defect detection [5,6].”
MethodTesting and Evaluation of Low-Cost Sensors for Developing Open Smart Campus Systems Based on IoT
Neis, P., Warch, D., & Hoppe, M. (2023) · Sensors · doi:10.3390/s23208652 · Cited by 20
“Depending on the application, there are special versions for real-time detection of different road users [62,64–66].”
BackgroundUnderwater target detection and embedded deployment based on lightweight YOLO_GN
Chen, X., Fan, C., Shi, J., Wang, H., & Yao, H. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06020-0 · Cited by 19
Engineering Vehicle Detection Based on Improved YOLOv6
Ling, H., Zhao, T., Zhang, Y., & Lei, M. (2024) · Applied Sciences · doi:10.3390/app14178054 · Cited by 17
Recent Technology Advancements in Smart City Management: A Review
Tavares, J. M. R. S., Chiranjeevi, K., Machado, J. J. M., Jain, D. K., Dannana, S., Gottapu, S. K., & Gandomi, A. H. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.058461 · Cited by 21
Machine Learning for Real-Time Vehicle Detection in All-Electronic Tolling System
Chattopadhyay, D., Rasheed, S., Yan, L., Lopez, A. A., Farmer, J., & Brown, D. E. (2020) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds49339.2020.9106682 · Cited by 15
“In [11], k-means++ is employed to cluster vehicle bounding boxes and its weight and height are normalized to reduce the influence of larger-sized vehicles in loss function.”
MethodShokri, D., Larouche, C., & Homayouni, S. (2024) · Electronics · doi:10.3390/electronics13142883 · Cited by 14
SARNet: Spatial Attention Residual Network for pedestrian and vehicle detection in large scenes
Wei, H., Zhang, Q., Han, J., Fan, Y., & Qian, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03217-9 · Cited by 15
“…target detection, one-stage detection method and two-stage detection method, among which common one-stage detection methods include YOLO, YOLOv2 [14], YOLOv3 [15], SSD [16], RetinaNet [17], etc.common two-stage detection methods, including Faster RCNN [18], R-FCN [19], Mask RCNN [20], Cascade…”
MethodSelf-citationTwo-Wheeled Vehicle Detection Using Two-Step and Single-Step Deep Learning Models
Kausar, A., Jamil, A., Nida, N., & Yousaf, M. H. (2020) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-020-04837-4 · Cited by 14
Rock Joint Detection from Borehole Imaging Logs Using a Convolutional Neural Networks Model
Ge, Y., Liu, G., Wang, H., Tang, H., & Zhao, B. (2025) · Journal of Earth Science · doi:10.1007/s12583-024-1989-5 · Cited by 12
“Furthermore, the YOLO model extracted the features from these anchor boxes via the feature extraction layers to forecast the bounding box (the yellow outline) which contained the rock joint (Wu et al., 2020; Sang et al., 2018; Shinde et al., 2018).”
EWNet: An early warning classification framework for smart grid based on local-to-global perception
Gao, F., Li, Q., Ji, Y., Ji, S., Guo, J., Sun, H., Liu, Y., Feng, S., Wei, H., Wang, N., et al. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.007 · Cited by 12
Pillai, U. K. K., & Valles, D. (2020) · IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS) · doi:10.1109/iemtronics51293.2020.9216368 · Cited by 12
“Researchers in [12] proposed a modified YOLOv2 network structure to classify vehicle types with eight classes by a multi-layer feature fusion strategy.”
BackgroundWeber, Y., & Kanarachos, S. A. (2019) · Sensors · doi:10.3390/s19224870 · Cited by 11
“One-step detectors such as You Only Look Once (YOLO) gained popularity due to less complex processing pipelines, high frame rates and accuracy [9,10].”
BackgroundDeep Learning-based Trajectory Estimation of Vehicles in Crowded and Crossroad Scenarios
Siddique, A., & Afanasyev, I. M. (2021) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct50888.2021.9347580 · Cited by 11
Kosuru, V. S. R., & Venkitaraman, A. K. (2022) · International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE) · doi:10.1109/icstcee56972.2022.10100170 · Cited by 11
“Centered weights are then classified to pixel that occupies each subset of bounding box for frames to fill in [8].”
BackgroundSODRet: Instance retrieval using salient object detection for self-service shopping
Hassan, M. U., Zhao, X., Sarwar, R., Aljohani, N. R., & Hameed, I. A. (2023) · Machine Learning with Applications · doi:10.1016/j.mlwa.2023.100523 · Cited by 15
Yin, T., Chen, W., Liu, B., Li, C., & Du, L. (2023) · Mathematics · doi:10.3390/math12010124 · Cited by 10
Multiscale self-attention for unmanned ariel vehicle-based infrared thermal images detection
Ali, M. S., Latif, A., Anwar, M. W., & Ashraf, M. H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110488 · Cited by 12
Image-Based Learning to Measure the Stopped Delay in an Approach of a Signalized Intersection
Shin, J., Roh, S., & Sohn, K. (2019) · IEEE Access · doi:10.1109/access.2019.2955307 · Cited by 10
“More recently, the performance of YOLO has been highlighted in vehicle detection studies [27], [28].”
BackgroundVehicle Detection in Remote Sensing Image Based on Machine Vision
Zhou, L., Chang, Z., Yan, H., Zuo, X., Qiao, B., Zhou, B., Fan, M., & Liu, Y. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/8683226 · Cited by 10
“For example, Jun et al. [29] proposed a vehicle detection model YOLOv2_- vehicle based on the YOLOv2 algorithm and obtained an average accuracy of 94.78% on the Beijing Institute of Technology (BIT) Vehicle validation dataset.”
MethodInfluentialBhattacharyya, A., Bhattacharya, A., Maity, S., Singh, P. K., & Sarkar, R. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14661-1 · Cited by 12
Pick-and-place application using a dual arm collaborative robot and an RGB-D camera with YOLOv5
Kijdech, D., & Vongbunyong, S. (2023) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v12i2.pp197-210 · Cited by 10
Artificial Intelligence in Autonomous Vehicles—A Survey of Trends and Challenges
Rajasekaran, U., Malini, A., & Murugan, M. (2024) · Wiley eBooks · doi:10.1002/9781119847656.ch1 · Cited by 15
Chen, X., Zhang, H., Shankar, A., Bhushan, B., & Joshi, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-89929-7 · Cited by 9
Application of Object Recognition for Plastic Waste Detection and Classification Using YOLOv3
Ardana, I. W. R., Purnama, I. B. I., & Yasa, I. M. S. (2020) · International Conference on Applied Science and Technology (iCAST) · doi:10.1109/icast51016.2020.9557735 · Cited by 9
FlexiNet: Fast and Accurate Vehicle Detection for Autonomous Vehicles
Mehtab, S., Sarwar, F., & Yan, W. (2021) · International Conference on Control and Computer Vision (ICCCV) · doi:10.1145/3484274.3484282 · Cited by 12
“YOLOv2 was taken in combination with k -means++ clustering for selecting various anchor boxes [19], however, the results were not compared by using any benchmark datasets, high-cost hardware was utilized to conduct the experiments.”
MethodDetection of the autonomous car robot using Yolo
Sahib, F. I. A.-A., Taher, H., & Ghani, R. F. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1879/3/032129 · Cited by 9
Hashemi, S., Emami, H., & Sangar, A. B. (2021) · International Journal of Communication Systems · doi:10.1002/dac.4928 · Cited by 9
“These datasets are not comprehensive enough for evaluating the VDC systems, and developing more comprehensive and up-to-date datasets containing various data types such as 3D images are needed.(10,19,20,141,149) A VDC system consists of several components.”
BackgroundInfluentialWei, Y., Zeng, Z., He, T., Yu, S., Du, Y., & Zhao, C. (2024) · Sensors · doi:10.3390/s24185912 · Cited by 8
“YOLOv2 [39] and YOLOv3 [40] improved detection performance by introducing multi-scale prediction and deeper network structures.”
BackgroundChang, Y., Zhou, D., Tang, Y., Ou, S., & Wang, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-63398-w · Cited by 8
Fajrianti, E. D., Panduman, Y. Y. F., Funabiki, N., Haz, A. L., Brata, K. C., & Sukaridhoto, S. (2024) · Network · doi:10.3390/network4030014 · Cited by 8
“In [22], Sang et al. developed a fine-tuned model of YOLOv2 to extract vehicle-type information from images or videos.”
BackgroundEdge detective weights initialization on Darknet-19 model for YOLOv2-based facemask detection
Ningthoujam, R., Pritamdas, K., & Singh, L. S. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10427-4 · Cited by 8
“An improved model for vehicle detection [13] adopted a multi-layer feature fusion technique to enhance the feature extraction ability.”
Comparison of YOLO architectures for face mask detection in images
Jovanović, L., Bačanin, N., Zivkovic, M. Z., Mani, J. P., Strumberger, I., & Antonijević, M. (2023) · International Conference on Advanced Technologies, Systems and Services in Telecommunications (TELSIKS) · doi:10.1109/telsiks57806.2023.10316138 · Cited by 8
“YOLO variants, such as YOLOv2 [21] and YOLOv3 [4], have further improved accuracy and speed.”
BackgroundA Review on Advanced Detection Methods in Vehicle Traffic Scenes
Chan, M. N., & Tint, T. (2021) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict50816.2021.9358791 · Cited by 8
“In [14], authors are presented a brand new model, YOLOv2_Vehicle based on version 2 YOLO series for vehicle detection.”
BackgroundMethodLow-resolution Human Identification in thermal imagery
Talluri, P., & Dua, M. (2020) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces48766.2020.9138039 · Cited by 8
“By utilizing Batch-normalization [7] it provides an improved balance between accuracy & running time.”
MethodImproved YOLOv4 approach: A real time occluded vehicle detection
Kumar, S., Jailia, M., & Varshney, S. (2022) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/120139 · Cited by 7
“As object detection technology matures, it is widely used across a variety of fields, such as image recognition, and has attained its top in the detection of traditional images [1].”
Deteksi Bola dan Gawang dengan Metode YOLO Menggunakan Kamera Omnidirectional pada Robot KRSBI-B
Sanubari, F. F., & Puriyanto, R. D. (2022) · Buletin Ilmiah Sarjana Teknik Elektro · doi:10.12928/biste.v4i2.6712 · Cited by 7
“Lalu untuk meningkatkan kemampuan deteksinya, maka dibuatlah YOLOv2 yang merupakan hasil peningkatan dari YOLOv1 dengan meningkatkan batch normalization, menaikkan resolusi klasifikasi, serta menggunakan 19 convolution layer dengan 5 max pooling layer [17][18][19].”
Background
Metadata
- Authors
- Sang, J., Wu, Z., Guo, P., Hu, H., Xiang, H., Zhang, Q., & Cai, B.
- Affiliations
- Chongqing University (CN)
- Corresponding author
- Sang, Jun
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2018-12-04
- Volume
- 18
- Issue
- 12
- Pages
- 4272
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC6308705
- OpenAlex
- W2902306794
- Cited by
- 223
- References
- 28
- Citations by year
- 2026: 9 · 2025: 28 · 2024: 36 · 2023: 43 · 2022: 35 · 2021: 31 · 2020: 29 · 2019: 11 · 2018: 1
- FWCI
- 9.00
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Chongqing Research Program of Basic Science and Frontier Technology (cstc2017jcyjB0305)
- National Key R&D Program of China (2017YFB0802400)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- vehicle detection, YOLOv2, K-means clustering, multi-scale feature fusion, vehicle type recognition, intelligent transportation systems, object detection, network visualization
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.