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
YOLO9000: 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
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“We deploy the saliency map for measuring the conditional entropy [31], [32].”
MethodR-FCN: Object Detection via Region-based Fully Convolutional Networks
Dai, J., Li, Y., He, K., & Sun, J. Z. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.06409 · Cited by 3,149
MatConvNet: Convolutional Neural Networks for MATLAB
Vedaldi, A., & Lenc, K. (2015) · Proceedings of the 23rd ACM international conference on Multimedia · doi:10.1145/2733373.2807412 · Cited by 2,444
DSSD : Deconvolutional Single Shot Detector
Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017) · arXiv · doi:10.48550/arxiv.1701.06659 · Cited by 1,624 · cited 1×
“The single-stage framework, such as YOLO [20]–[22] and singleshot multibox detector (SSD) [23], [24], applies object classifiers and bounding box regressors in an end-to-end manner without extracting proposals.”
MethodCross-scene crowd counting via deep convolutional neural networks
Zhang, C., Li, H., Wang, X., & Yang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298684 · Cited by 1,121
Self-citationThe Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., & Tian, Q. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_23 · Cited by 1,099
Simultaneous Detection and Segmentation
Hariharan, B., Arbeláez, P., Girshick, R., & Malik, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10584-0_20 · Cited by 1,085
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
Kong, T., Yao, A., Chen, Y., & Sun, F. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.98 · Cited by 934 · cited 2×
“Inspired by HyperNet [35], RON [36], and FPN [37], we explore three different connections: (1) reverse res 5 cx to res 4 b 22 x ; (2) reverse res 5 cx to res 3 b 3 x ; and (3) reverse res 4 b 22 x to res 3 b 3 x .”
MethodWhat Makes for Effective Detection Proposals?
Hosang, J., Benenson, R., Dollar, P., & Schiele, B. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2465908 · Cited by 727 · cited 1×
“Compared with the average recall, these metrics are more suitable for the detection task, while considering the recall and false detection rate [44], [45].”
Hu, P., & Ramanan, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.166 · Cited by 705
Intelligent multi-camera video surveillance: A review
Wang, X. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.07.005 · Cited by 694
Feature selection using Joint Mutual Information Maximisation
Bennasar, M., Hicks, Y., & Setchi, R. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.07.007 · Cited by 659
Drone-Based Object Counting by Spatially Regularized Regional Proposal Network
Hsieh, M.-R., Lin, Y.-L., & Hsu, W. H. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.446 · Cited by 547 · cited 10×
“1) Datasets: We perform our method and the state-of-theart methods on the three recent drone-based object counting and detection benchmarks: CARPK [10], VisDrone2018 [42], and UAVDT [43].”
BackgroundMethodInfluentialCrowdNet: A Deep Convolutional Network for Dense Crowd Counting
Boominathan, L., Kruthiventi, S. S. S., & Babu, R. V. (2016) · Proceedings of the 24th ACM international conference on Multimedia · doi:10.1145/2964284.2967300 · Cited by 503
RON: Reverse Connection with Objectness Prior Networks for Object Detection
Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., & Chen, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.557 · Cited by 442
Cao, C., Liu, X., Yang, Y., Yu, Y., Wang, J., Wang, Z., Huang, Y., Wang, L., Huang, C., Xu, W., et al. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.338 · Cited by 392
Vision meets drones: A challenge
Zhu, P., Wen, L., Bian, X., Ling, H., & Hu, Q. (2018) · arXiv · doi:10.48550/arxiv.1804.07437 · Cited by 352 · cited 6×
“1) Datasets: We perform our method and the state-of-theart methods on the three recent drone-based object counting and detection benchmarks: CARPK [10], VisDrone2018 [42], and UAVDT [43].”
MethodInfluentialPKLot—A robust dataset for parking lot classification
de Almeida, P. R. L., Oliveira, L. S., Britto, A. S., Silva, E. J., & Koerich, A. L. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.02.009 · Cited by 312 · cited 2×
“For the counting task, most early methods focus on counting the objects of known location in a static environment with fixed cameras [11], [12].”
MethodBoosting bottom-up and top-down visual features for saliency estimation
Borji, A. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247706 · Cited by 266
Robust Control of Four-Rotor Unmanned Aerial Vehicle With Disturbance Uncertainty
Islam, S., Liu, P. X., & El Saddik, A. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2365441 · Cited by 259
An End-to-End TextSpotter with Explicit Alignment and Attention
He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., & Sun, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00527 · Cited by 234
Kang, D., Ma, Z., & Chan, A. B. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2837153 · Cited by 213
Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation
Roy, A., & Todorović, S. (2017) · 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/cvpr.2017.770 · Cited by 122
Visual Saliency Based on Conditional Entropy
Li, Y., Zhou, Y., Yan, J., Niu, Z., & Yang, J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12307-8_23 · Cited by 87
Biologically Inspired Features for Scene Classification in Video Surveillance
Huang, K., Tao, D., Yuan, Y., Li, X., & Tan, T. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2009.2037923 · Cited by 82
Statistical Hypothesis Detector for Abnormal Event Detection in Crowded Scenes
Yuan, Y., Feng, Y., & Lu, X. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2572609 · Cited by 73
Representation of Mutual Information Via Input Estimates
Palomar, D. P., & Verdú, S. (2007) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.889728 · Cited by 69
Robust Pose Estimation for Multirotor UAVs Using Off-Board Monocular Vision
Fu, Q., Quan, Q., & Cai, K. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2696482 · Cited by 56
Salient Region Detection by Fusing Bottom-Up and Top-Down Features Extracted From a Single Image
Tian, H., Fang, Y., Zhao, Y., Lin, W., Ni, R., & Zhu, Z. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2350914 · Cited by 54
A Vision-Aided Approach to Perching a Bioinspired Unmanned Aerial Vehicle
Luo, C. L., Yu, L., & Ren, P. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2764849 · Cited by 49
Fast Classification of Empty and Occupied Parking Spaces Using Integral Channel Features
Ahrnbom, M., Åström, K., & Nilsson, M. G. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.200 · Cited by 43
Exemplar-Driven Top-Down Saliency Detection via Deep Association
He, S., & Lau, R. W. H. (2016) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2016.617 · Cited by 39
Toward a Blind Quality Metric for Temporally Distorted Streaming Video
Wu, Q., Li, H., Meng, F., & Ngan, K. N. (2018) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2017.2786023 · Cited by 34
Self-citationSeeds-Based Part Segmentation by Seeds Propagation and Region Convexity Decomposition
Meng, F., Li, H., Wu, Q., Ngan, K. N., & Cai, J. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2739919 · Cited by 21
Self-citationHDPA: Hierarchical deep probability analysis for scene parsing
Yuan, Y., Jiang, Z., & Wangm, Q. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019367 · Cited by 5
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].”
Method
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.