Simultaneously Detecting and Counting Dense Vehicles From Drone Images
The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
Unmanned aerial vehicles are an essential component in the realization of Industry 4.0. With drones helping to improve industrial safety and efficiency in utilities, construction, and communication, there is an urgent need for drone-based intelligent applications. In this paper, we develop a unified framework to simultaneously detect and count vehicles from drone images. We first explore why the state-of-the-art detectors fail in highly dense drone scenes, which provides more appropriate insights. Then, we propose an effective loss to push the anchors toward matching the ground-truth boxes as much as possible, specifically designed for scale-adaptive anchor generation. Inspired by attention mechanisms in the human visual system, we maximize the mutual information between object classes and features by combining bottom-up cues with top-down attention mechanisms specifically designed for feature extraction. Finally, we build a counting layer with a regularized constraint related to the number of vehicles. Extensive experiments demonstrate the effectiveness of our approach. For both tasks, our proposed method achieves state-of-the-art results on all four challenging datasets. In particular, our results reduce error by a larger factor than previous methods.
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 [2]
In the citing paper
“Furthermore, to address the issue of small and dense objects in aerial scenes, [2] proposed the Scale Adaptive-Circular Flow (SA-CF) framework.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [2]
In the citing paper
“In this framework, a SA strategy was developed to match the different sizes of objects in aerial scenes with the GT BBoxes by formulating a loss function.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [2]
In the citing paper
“The Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) metrics have been employed in the DLbased counting frameworks [2], [38].”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [2]
In the citing paper
“A CF is embedded in the feature extractor to maximize the feature extraction information where bottom-up features are combined with the top-down attention features.”
From A Systematic Review of Drone Based Road Traffic Monitoring System (2022) · cites this paper as [2]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
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
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
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
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
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Cited by
Zhang, J., Li, C., Rahaman, M. M., Yao, Y., Ma, P., Zhang, J., Zhao, X., Jiang, T., & Grzegorzek, M. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10082-4 · Cited by 204
Vehicle Detection From UAV Imagery With Deep Learning: A Review
Bouguettaya, A., Zarzour, H., Kechida, A., & Taberkit, A. M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3080276 · Cited by 185
“In many works, such as [78], [165], and [167], the authors showed that vehicle detection from lower altitudes achieves better accuracy than from higher altitudes.”
BackgroundMethodA steel surface defect inspection approach towards smart industrial monitoring
Hao, R., Lu, B., Cheng, Y., Li, X., & Huang, B. (2021) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-020-01670-2 · Cited by 175
“Object detection techniques have been applied in numerous industries (Hu et al. 2019; Li et al. 2019), but they have not been fully used in steel surface defect inspection.”
BackgroundA 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 139
“A different approach was used in [2], where 895 authors conducted simultaneous detection and counting in 896 UAV imagery by introducing a counting layer after the feature 897 extractor in the CNN framework.”
MethodResultInfluentialApplications and Challenges in Video Surveillance via Drone: A Brief Survey
Dilshad, N., Hwang, J., Song, J., & Sung, N. (2020) · 2020 International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc49870.2020.9289536 · Cited by 139
“The most common approach is to use the GPS information and place different sensors at each entrance and exit point to detect a vehicle whenever it passes by as it is a challenging task because the cars are too dense, small, and continuously in motion [14].”
MethodA Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
Wang, Y., Hou, J., Hou, X., & Chau, L.-P. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3055632 · Cited by 144
“To deal with the failure of state-of-the-art detectors in drone scenes, Li et al. [34] made a set of modifications for detection.”
BackgroundMethodApplications, databases and open computer vision research from drone videos and images: a survey
Akbari, Y., Almaadeed, N., Al-Maadeed, S. A., & Elharrouss, O. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-020-09943-1 · Cited by 133
Pareto Refocusing for Drone-View Object Detection
Leng, J., Mo, M., Zhou, Y., Gao, C., Li, W., & Gao, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3210207 · Cited by 100
“Li et al. [17] introduce multi-task learning, which performs semantic segmentation tasks of foreground and background while performing object detection, achieving better detection results with the assistance of the semantic context of the scene.”
BackgroundMethodSelf-citationKumar, A., Krishnamurthi, R., Nayyar, A., Luhach, A. K., Khan, M. S., & Singh, A. (2020) · Vehicular Communications · doi:10.1016/j.vehcom.2020.100313 · Cited by 104
NWPU-MOC: A Benchmark for Fine-Grained Multicategory Object Counting in Aerial Images
Gao, J., Zhao, L., & Li, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3356492 · Cited by 104
“[47] propose using a unified framework to simultaneously detect and count vehicles.”
MethodMachine Learning for UAV-Aided ITS: A Review With Comparative Study
Telikani, A., Sarkar, A., Du, B., & Shen, J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3422039 · Cited by 73
“Li et al. [89] trained a CNN framework to simultaneously detect and count vehicles in drone-based images.”
BackgroundGao, G., Liu, Q., Hu, Z., Li, L., Wen, Q., & Wang, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3153946 · Cited by 72
A systematic review on computer vision-based parking lot management applied on public datasets
de Almeida, P. R. L., Alves, J. H., Parpinelli, R. S., & Barddal, J. P. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116731 · Cited by 69
“Common datasets used to evaluate methods that deal with this task include the PUCPR+ (an extension of the PUCPR subset from the PKLot) (Hsieh et al., 2017; Li et al., 2019; Gabzdyl, 2020), the original PUCPR subset of the PKLot (Laradji et al.”
BackgroundMethodInfluentialVision-Based Learning for Drones: A Survey
Xiao, J., Zhang, R., Zhang, Y., & Feroskhan, M. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3564184 · Cited by 85
“Single drone applications in vision-based learning primarily involve tasks like obstacle avoidance [34], [36], surveillance [157], [158], [159], [160], search and rescue operations [161], [162], [163], environmental monitoring [164], [165], [166], [167], industrial inspection [28], [168], [169],…”
Bisio, I., Haleem, H., Garibotto, C., Lavagetto, F., & Sciarrone, A. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3128065 · Cited by 50
Deep Learning in Construction: Review of Applications and Potential Avenues
Jacobsen, E. L., & Teizer, J. (2021) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0001010 · Cited by 49
Dilated-Scale-Aware Category-Attention ConvNet for Multi-Class Object Counting
Xu, W., Liang, D., Zheng, Y., Xie, J., & Ma, Z. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3096119 · Cited by 50
Offset Bin Classification Network for Accurate Object Detection
Qiu, H., Li, H., Wu, Q., & Shi, H. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01320 · Cited by 50
“Compared with two-stage detectors, single-stage detectors [18,19,21,23,32–34] reach high inference speed, such as YOLO [32–34], SSD [23], RetinaNet [21].”
BackgroundSelf-citationVehicle Detection in Aerial Images Based on 3D Depth Maps and Deep Neural Networks
Javadi, S., Dahl, M., & Pettersson, M. I. (2021) · IEEE Access · doi:10.1109/access.2021.3049741 · Cited by 43
“In addition, [35] suggested using scale-adaptive anchor boxes to match the size distribution of the training data.”
MethodSpatial Cognition-Driven Deep Learning for Car Detection in Unmanned Aerial Vehicle Imagery
Yu, J., Gao, H., Sun, J., Zhou, D., & Ju, Z. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3124764 · Cited by 41
“We consider the following state-of-the-art methods: 1) Faster R-CNN [5]; 2) SA + CF + CRT [47]; 3) SSD [48]; 4) One-Look Regression [49]; 5) IEP [50]; 6) YOLO9000 [51]; 7) LPN [52]; 8) RetinaNet [53]; 9) YOLOv3 [21]; 10) IoUNet [54]; 11) ShuffleDet [55]; 12) VGG-GAP-HR [56]; 13) GMN [57]; 14) YOLOv4…”
Telikani, A., Sarkar, A., Du, B., Santoso, F., Shen, J., Yan, J. H., Yong, J., & Yap, E. W. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3530913 · Cited by 53
An accurate car counting in aerial images based on convolutional neural networks
Kılıç, E., & Öztürk, S. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03377-5 · Cited by 42
“…et al. 2019) 15.17 IoUNet (Goldman et al. 2019) 7.16 12.00 VGG-GAP-HR (Aich and Stavness 2018b) 5.24 6.67 YOLOv3 (Redmon and Farhadi 2018) 5.24 7.14 SA+CF+CRT (Li et al. 2019) 3.92 5.06 GANet (VGG-16) (Cai et al. 2019) 3.68 5.47 dos Santos de Arruda et al. (2021) 3.16 4.39 HLCNN (VGG-16) 2.52 3.40”
BackgroundInfluentialSzóstak, M., Nowobilski, T., Mahamadu, A., & Pérez, D. C. (2022) · International Journal of Intelligent Unmanned Systems · doi:10.1108/ijius-05-2022-0063 · Cited by 36
Multi-Scale Vehicle Detection in High-Resolution Aerial Images With Context Information
Li, X., Li, X., & Pan, H. (2020) · IEEE Access · doi:10.1109/access.2020.3036075 · Cited by 29
Artificial Intelligence in Industrial Systems
Palhares, R. M., Yuan, Y., & Wang, Q. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2916709 · Cited by 27
DR.VIC: Decomposition and Reasoning for Video Individual Counting
Han, T., Bai, L., Gao, J., Wang, Q., & Ouyang, W. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00309 · Cited by 42
“crowd counting [62], vehicle counting [26]), we use Mean Absolute Error Dataset Videos Frames Head labels Pedestrians Time (s) CroHD 9 11,463 2,276,838 5,230 498 SenseCrowd 634 62,938 2,344,276 43,178 12,588”
MethodGuided Attention Network for Object Detection and Counting on DronesPreprint
Cai, Y., Du, D., Zhang, L., Wen, L., Wang, W., Wu, Y., & Lyu, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11307 · Cited by 24
“org/ YOLO9000 [23], LPN [10], RetinaNet [17], YOLOv3 [24], IoUNet [8], and SA+CF+CRT [15].”
Recent advances in drone-view object detection
Leng, J., Mo, M., Zhou, Y., Ye, Y., Gao, C., & Gao, X. (2023) · Journal of Image and Graphics · doi:10.11834/jig.220836 · Cited by 31
Robust Object Detection in Aerial Imagery Based on Multi-Scale Detector and Soft Densely Connected
Zhang, M., Zhang, B., Liu, M., & Xin, M. (2020) · IEEE Access · doi:10.1109/access.2020.2994379 · Cited by 23
“Therefore, object detection is more challenging for aerial images than natural images [8]–[11].”
BackgroundSmart-Building Applications: Deep Learning-Based, Real-Time Load Monitoring
Çimen, H., García, E. J., Kolaek, M., Çetinkaya, N., Vásquez, J. C., & Guerrero, J. M. (2020) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2020.3023075 · Cited by 25
“Particularly, it has been gaining popularity in many different areas, such as image classification, speech recognition, and health management, due to its superior performance over other traditional methods [4], [5].”
BackgroundDense Traffic Detection at Highway-Railroad Grade Crossings
Guo, F., Jiang, Z., Wang, Y., Chen, C., & Qian, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3140948 · Cited by 26
Mudawi, N. A., Hanzla, M., Alazeb, A., Alshehri, M., Alhasson, H. F., AlHammadi, D. A., & Jalal, A. (2025) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2025.065490 · Cited by 23
“Li et al. [14] proposed a unified framework for vehicle detection and counting, using a scale-adaptive anchor generator and feature pyramid to improve multi-scale detection.”
An Improved FBPN-Based Detection Network for Vehicles in Aerial Images
Wang, B., & Gu, Y. (2020) · Sensors · doi:10.3390/s20174709 · Cited by 20
“focuses on the large variance of scales, and designs a scale-insensitive convolution neural network which accomplishes by a context-aware RoI pooling and a multi-branch decision network [24].”
BackgroundReal-Time Detection of Unauthorized Unmanned Aerial Vehicles Using SEB-YOLOv8s
Fang, A., Feng, S., Liang, B., & Jiang, J. H. (2024) · Sensors · doi:10.3390/s24123915 · Cited by 29
“…equipment, unmanned aerial vehicle (UAV) technology has rapidly developed and been widely applied in areas such as agriculture, transportation, and the military [1,2], but this has also triggered an increase in misuse and violations, posing potential threats to social and national security [3].”
BackgroundCai, R., Li, J., Tan, Y., Tang, J., & Chen, X. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113374 · Cited by 24
Self-citationSmart Count System Based on Object Detection Using Deep Learning
Moon, J.-W., Lim, S., Lee, H., Yu, S., & Lee, K.-B. (2022) · Remote Sensing · doi:10.3390/rs14153761 · Cited by 22
Hierarchical Kernel Interaction Network for Remote Sensing Object Counting
Wang, H., Zeng, X., Zhang, T., Wei, J., Hou, X., Wu, H., & Zhang, K. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3348870 · Cited by 24
“Detection-based remote sensing counting meth-ods [21], [44], [45] relied on the accuracy of detection, which would deteriorate the performance of tiny objects.”
BackgroundCODAN: Counting-driven Attention Network for Vehicle Detection in Congested Scenes
Li, W., Wang, Z., Wu, X. Y., Zhang, J., Peng, Q., & Li, H. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413945 · Cited by 24
“However, due to the lack of multi-scale modeling, the location bias of SDC is large.”
BackgroundMethodInfluentialSelf-citationKrump, M., Ruß, M., & Stütz, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-43890-6_5 · Cited by 18
Wang, J., Shao, F., He, X., & Lu, G. (2022) · Drones · doi:10.3390/drones6100292 · Cited by 16
“[32] combined top-down and bottom-up attention mechanisms and applied a circular flow to guide feature extraction, which makes the network better positioned on the object features and achieves highprecision small object detection.”
Yu, R., Li, H., Jiang, Y., Zhang, B., & Wang, Y. (2022) · Sensors · doi:10.3390/s22062354 · Cited by 16
“There are also certain methods to improve the detection performance of small objects such as designing appropriate anchor size [39,40], introducing visual attention mechanism [41,42], and data augmentation [43,44].”
MethodSelf-citationRemote Sensing Object Counting Through Regression Ensembles and Learning to Rank
Huang, Y., Jin, Y., Zhang, L., & Liu, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3266884 · Cited by 19
“For example, a spatially regularized regional proposal network [15] and a bifunctional framework [16] were used to learn to count vehicles in drone images; the multires-olution crowd network [17] and space-time neighbor-aware network [18] contributed to crowd counting; intensive studies of…”
MethodLi, X., Zhuang, Y., You, B., Wang, Z., Zhao, J., Gao, Y., & Xiao, D. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102143 · Cited by 17
Deeply scale aggregation network for object counting
Li, H., Kong, W., & Zhang, S. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106485 · Cited by 15
Self-citationMathematical programming-based heuristic for highway patrol drone scheduling problem
Choi, S., Lee, M., Park, H., & Han, J. (2024) · Socio-Economic Planning Sciences · doi:10.1016/j.seps.2024.101907 · Cited by 13
Dense center-direction regression for object counting and localization with point supervision
Tabernik, D., Muhovič, J., & Skočaj, D. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110540 · Cited by 16
“In this paper, we use an encoder-decoder model with ResNet-101 as encoder and Feature Pyramid Network [28, 29] as decoder.”
Method3DF-FCOS: Small object detection with 3D features based on FCOS
Yang, X., He, Y., Wu, J., Sun, W., Liu, T., & Ma, S. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103787 · Cited by 12
Drone-Based Car Counting via Density Map Learning
Huang, J., Ding, G., Guo, Y., Yang, D., Wang, S., Wang, T., & Zhang, Y. (2020) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip49819.2020.9301785 · Cited by 13
“We conduct the experiment to compare the performance of our proposed method with state-of-the-art methods, including GAP [16], GSP [17], NFCNN [18] Bold mumbers depict the best preformance. their source code, the results of our proposed are compared with what they provided in their paper.”
ResultObject Counting for Remote-Sensing Images via Adaptive Density Map-Assisted Learning
Ding, G., Cui, M., Yang, D., Wang, T., Wang, S., & Zhang, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3208326 · Cited by 15
“ADMAL is compared with the state-of-the-art methods including crowd counting methods (MCNN [22] and CSR-Net [11]), car counting methods (GAP [51], GSP [52], and UFCNN [53]) and a remote-sensing object counting method (ASPDNet [9], [10]).”
MethodA feature fusion deep-projection convolution neural network for vehicle detection in aerial images
Wang, B., & Xu, B. (2021) · PLoS ONE · doi:10.1371/journal.pone.0250782 · Cited by 11
“proposed a network to detect and count vehicles simultaneously in aerial images in 2019 [4].”
BackgroundMulti-scale self-attention-based feature enhancement for detection of targets with small image sizes
Deng, Y., Hu, X., Li, B., Zhang, C., & Hu, W. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.12.026 · Cited by 11
A Survey on Surveillance using Drones
Theja, G. U. S., Murari, M. S., Singha, M. F., Patgiri, R., & Choudhury, A. (2022) · International Conference on Contemporary Computing · doi:10.1145/3549206.3549253 · Cited by 10
“technique is to apply the GPS realities and area particular sensors at each front and go out element to stagger on a vehicle each time it elapses with the guide of utilizing as it is for an extreme endeavor because of the reality the engines are exorbitantly thick, tiny, and reliably moving [21].”
MethodKrump, M., & Stütz, P. (2023) · Sensors · doi:10.3390/s23073769 · Cited by 14
“According to study [38], it is among the most challenging and largest drone based datasets.”
BackgroundA Dynamic Unmanned Aerial Vehicle Routing Framework for Urban Traffic Monitoring
Bai, Y., & Feng, Y. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3646969 · Cited by 11
“These characteristics make UAVs vital for future smart cities, broadening their roles in areas such as package delivery [1], road inspection [2], crowd surveillance [3] and tra ffi c monitoring [4], [5], [6], [7], [8], [9], [10].”
InfluentialLanguage bias in Visual Question Answering: A Survey and TaxonomyPreprint
Yuan, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.08531 · Cited by 24
Local Thermal Resistance Extraction in Monolithic Microwave Integrated Circuits
Vellvehi, M., Perpiñà, X., León, J., Aviñó-Salvadó, O., Ferrer, C., & Jordà, X. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3040684 · Cited by 8
“[3], [4], and unmanned aerial vehicles [5], [6], respectively.”
BackgroundLee, C.-Y., Lin, H.-J., Yeh, M.-Y., & Ling, J. (2022) · Applied Sciences · doi:10.3390/app12094657 · Cited by 8
Traffic perception from aerial images using butterfly fields
Adaimi, G., Kreiss, S., & Alahi, A. (2023) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2023.104181 · Cited by 23
M-O SiamRPN with Weight Adaptive Joint MIoU for UAV Visual Localization
Wen, K., Chu, J., Chen, J., Chen, Y., & Cai, J. (2022) · Remote Sensing · doi:10.3390/rs14184467 · Cited by 8
Anomaly Detection in Electromechanical Systems by means of Deep-Autoencoder
Arellano-Espitia, F., Delgado-Prieto, M., Martínez-Viol, V., Sobrino, Á. F., & Osornio-Rios, R. A. (2021) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa45728.2021.9613529 · Cited by 10
“In this regard, Deep Learning (DL) techniques based on the ANN principles have enhanced the possibilities of complex data patterns management, characterization and posterior recognition in multiples disciplines [2-4].”
BackgroundJohansen, K. W., de Figueiredo, R. P., Golovina, O., & Teizer, J. (2021) · International Symposium on Automation and Robotics in Construction (ISARC) · doi:10.22260/isarc2021/0085 · Cited by 7
“[10, 11] develop a UAV platform that can be used in the construction industry and analyze the accuracy and barriers in UAV application in this industry.”
Hu, R., Tang, Z., & Yang, R. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110149 · Cited by 9
Roadside Sensor Based Vehicle Counting Incomplex Traffic Environment
Chen, Z., Liu, Z., Hui, Y., Li, W., Li, C., Luan, T. H., & Mao, G. (2019) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps45667.2019.9024473 · Cited by 7
“Similar to [5], many works have been studied to enhance the vehicle counting performance by using video or image information [6]–[11].”
BackgroundSelf-citationLow-Resource Scenario Classification Through Model Pruning Toward Refined Edge Intelligence
Shan, X., Wang, J., Yan, X., Wang, C., Zhang, X., Gui, G., & Sari, H. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3347665 · Cited by 10
“As digitization and intelligence grow in vehicular and road systems, the resultant data explosion necessitates more efficient storage, transmission, computation, and processing capabilities [10].”
BackgroundZhang, Z., Zhang, L., Zhang, H., Guo, Y., Wang, H., & Lu, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121602 · Cited by 7
Remote Sensing Object Counting With Online Knowledge Learning
Jiang, S., Gao, Y., Li, B., Cheng, F., Hang, R., & Liu, Q. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3550300 · Cited by 6
“Li et al. [19] introduced a unified framework that simultaneously detects and counts vehicles in drone images.”
PRISMA Review: Drones and AI in Inventory Creation of Signage
Satama-Bermeo, G., López-Guede, J. M., Rahebi, J., Teso-Fz-Betoño, D., Boyano, A., & Akizu‐Gardoki, O. (2025) · Drones · doi:10.3390/drones9030221 · Cited by 8
“These traditional methods are slow, costly, and prone to human error [4], resulting in incomplete coverage and lower accuracy in identifying and recording the condition of signs [5].”
InfluentialProcessing at the Edge: A Case Study with an Ultrasound Sensor-Based Embedded Smart Device
Poza-Luján, J.-L., Uribe-Chavert, P., Sáenz-Peñafiel, J.-J., & Posadas-Yagüe, J.-L. (2022) · Electronics · doi:10.3390/electronics11040550 · Cited by 7
Peng, B., Zhang, H., Ni, Y., & Xie, J. (2022) · Sustainability · doi:10.3390/su14137912 · Cited by 6
Low-cost modular devices for on-road vehicle detection and characterisation
Poza-Luján, J.-L., Uribe-Chavert, P., & Posadas-Yagüe, J.-L. (2023) · Design Automation for Embedded Systems · doi:10.1007/s10617-023-09270-y · Cited by 6
“Themost efficientmethods use complex devices, such as cameras [9] or even drones [10].”
BackgroundPedestrian and Vehicles Detection with ResNet in Aerial Images
Cengiz, E., Yılmaz, C., Kahraman, H. T., & Bayram, F. (2019) · 4th International Symposium on Innovative Approaches in Engineering and Natural Sciences Proceedings · doi:10.36287/setsci.4.6.107 · Cited by 5
“are worked with the MATLAB program to estimate the number and location of vehicles in a region at the same time [2].”
MethodA Survey on Audio Synthesis and Audio-Visual Multimodal ProcessingPreprint
Shi, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00443 · Cited by 22
“In [19, 74, 75, 93, 53, 51, 52, 73, 11, 10, 50], several neural network-based models with high performance for objective detection can be found.”
BackgroundA Study on Deep Learning Methods in the Concept of Digital Industry 4.0
Şimşek, M. A., & Orman, Z. (2021) · Advances in e-business research series · doi:10.4018/978-1-7998-5015-1.ch016 · Cited by 5
A Novel Cost-Effective IoT-Based Traffic Flow Detection Scheme for Smart Roads
Liu, Z., Li, C., Wang, H., Wang, Y., Hui, Y., Mao, G., & Zhao, P. (2020) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc49849.2020.9238792 · Cited by 4
Image Processing with Deep Learning: Surface Defect Detection of Metal Gears through Deep Learning
Balcıoğlu, Y. S., Sezen, B., Gök, M. Ş., & Tunca, S. (2022) · Materials Evaluation · doi:10.32548/2022.me-04230 · Cited by 8
Vehicle Counting Network with Attention-based Mask Refinement and Spatial-awareness Block Loss
Zhang, J., Qiao, J.-J., Wu, X. Y., & Li, W. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475246 · Cited by 3
Self-citationUtilization of Li-Fi Technology for Black Box in Ground Vehicles
Maheswari, S. L. U., Magesh, T., Sukhi, Y., Jayasree, V., Jeeva, G., & Oviya, B. (2025) · International Conference Trends Material Science and Inventive Materials · doi:10.1109/ictmim65579.2025.10988335 · Cited by 2
“State-of-the-art detectors often struggle in highly dense drone scenes, adversely affecting vehicle detection accuracy, and thus needing scale-adaptive construction of anchors [2].”
Distributing and Processing Data from the Edge. A Case Study with Ultrasound Sensor Modules
Poza-Luján, J.-L., Uribe-Chavert, P., Sáenz-Peñafiel, J.-J., & Posadas-Yagüe, J.-L. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-86261-9_19 · Cited by 2
Feature Extraction Method of Art Visual Communication Image Based on 5G Intelligent Sensor Network
Liang, W. (2022) · Journal of Sensors · doi:10.1155/2022/8545345 · Cited by 2
Application of unmanned aerial vehicles in construction industry
Szóstak, M., & Nowobilski, T. (2022) · Transportation Overview - Przeglad Komunikacyjny · doi:10.35117/a_eng_22_02_03_05 · Cited by 2
Parking Occupancy Detection using Computer Vision Techniques
Katiyar, A., & Seema, S. (2024) · International Journal of Innovative Science and Research Technology (IJISRT) · doi:10.38124/ijisrt/ijisrt24apr234 · Cited by 3
Xu, X., Yang, P., Ran, B., Xian, H., & Liu, Y. (2020) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-191649 · Cited by 2
“Liketheevaluationindicesmethodin[11],theTrue Positive (TP) of an object was considered to occur when it was detected in its classes, while the False Positive (FP) was considered to occur when an shape in the class was wrongly detected as another.”
Real-Time Road Accident Scene Recognition Using Computer Vision Applied to Drone Imagery
Coulibaly, A., Ngom, I., Dembélé, J. M., Leahy, K., Diagne, I., Tall, M. M., Sadio, O., & Ndiaye, M. (2024) · IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES) · doi:10.1109/icares64249.2024.10768100 · Cited by 2
“Recently, the use of Unmanned Aerial Vehicles (UAVs) [19] – [21] and Deep Learning algorithms [22], [23] for remote sensing and monitoring applications has grown considerably.”
Luo, J., & Hu, Y. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105328 · Cited by 1
A Generic Model of Traffic Monitoring and Vehicle Counting Systems Based on Edge Computing
Heryanto, H., Hutagalung, M., Gamaliel, Y. Y., Angela, D., Pratama, D., Martina, I., & Nugroho, T. A. (2024) · JURNAL INFOTEL · doi:10.20895/infotel.v16i2.1105 · Cited by 1
“Using drones, the Root Mean Square Error (RMSE) value produced is 17.49 [7].”
MethodInfluentialA Review of 3D Face Reconstruction From a Single ImagePreprint
Wang, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09299 · Cited by 3
“[38] Wei Li, Hongliang Li, Qingbo Wu, Xiaoyu Chen, and King Ngi Ngan.”
BackgroundDense prediction and deep learning in complex visual scenes
Wang, Y. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/152009
Learning Selective Assignment Network for Scene-Aware Vehicle Detection
Wang, Z., Li, W., Wu, X. Y., & Sheng, L. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897860
“Recent vehicle detection methods [11, 12, 13, 14] have achieved significant progresses based on Convolutional Neural Networks ( CNNs ) [15].”
MethodSelf-citationA Study on Deep Learning Methods in the Concept of Industry 4.0
Şimşek, M. A., & Orman, Z. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-7852-0.ch007
Applying UAVs for indoor emergency risk evaluation
Mannini, L., Nigro, M., & Samà, M. (2023) · International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS) · doi:10.1109/mt-its56129.2023.10241383
Sy, B. (2024) · Southern space studies · doi:10.1007/978-3-031-64213-5_5
YOLOv11-DEC: An Improved YOLOv11 Model for UAV Detection in Complex Contexts
Song, Q., Liu, S., Dai, K., & Bai, K. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033339 · Cited by 1
AI-Powered Vehicle Count Prediction for Smart City Traffic Management
Hemavathi, N., Sumathi, R., & Savithramma, R. M. (2025) · International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE) · doi:10.1109/iccrtee64519.2025.11052998
“In order to efficiently handle crowded situations, the paper in [10] suggested an integrated framework for simultaneous vehicle recognition and counting in drone photos, combining attention mechanisms with scale-adaptive approaches.”
FedNSA: Federated Noise-Signature Alignment for Model-Heterogeneous UAV Vehicle Detection
Che, T., Zhou, Y., Li, T., Chang, Q., Yan, D., Zhou, H., & Jiang, Z. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11400797
“UAVs have recently been widely used for traffic monitoring tasks including vehicle identification, counting, tracking, and speed estimation [2]–[5].”
Multimodal Collaborative Perception for UAV-Based Traffic Monitoring
Wang, B. (2026) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-92-0052-8_9
MetaPKLot – new challenges and protocols for vision-based parking lot management
de Almeida, P. R. L., Alves, J. H., Kujavski, L. M., Alves, P. M. L., & Oliveira, L. S. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12398-0
“For an overview of such approaches, we refer the reader to [6 , 13, 14].”
Metadata
- Authors
- Li, W., Li, H., Wu, Q., Chen, X., & Ngan, K. N.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- Venue
- IEEE Transactions on Industrial Electronics
- Published
- 2019-12
- Volume
- 66
- Issue
- 12
- Pages
- 9651-9662
- ISSN
- 0278-0046 (ISSN-L)
- 1557-9948
- OpenAlex
- W2915476573
- Cited by
- 96
- References
- 49
- Citations by year
- 2026: 3 · 2025: 11 · 2024: 11 · 2023: 11 · 2022: 21 · 2021: 20 · 2020: 15 · 2019: 4
- FWCI
- 6.70
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Electronics (publishedVersion)
- Funders
- National Natural Science Foundation of China (61831005, 61525102, 61601102, 61871078)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- vehicle detection, vehicle counting, drone images, dense object detection, top-down attention, bottom-up attention, mutual information, industrial safety, unmanned aerial vehicles
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.