Skip to content
2000
Volume 19, Issue 3
  • ISSN: 2666-2558
  • E-ISSN: 2666-2566

Abstract

Introduction

In the field of object detection, small object detection has been a challenging problem. Existing CenterNet mainly focuses on deep features while ignoring shallow features, and there is also strong similarity object interference, which leads to insufficient detection ability for small objects. To solve these problems, this paper proposes a small object detection method AR-CenterNet based on the adaptive enhanced context model and residual attention mechanism.

Methods

Firstly, to enhance the feature representation capability, an Adaptive Enhanced Context Model (AEC) is designed, which balances the contextual information of shallow features at different scales. context information of different scales of shallow features and fuses them with deeper features by different scales of convolutional expansion. In addition, to reduce the influence of strong interference objects, the RAM (Residual Attention Mechanism) module is proposed, which reduces the interference of surrounding features by introducing the residual attention mechanism, recognizes the channel and spatial attributes of the small object features by using the coordinate attention mechanism, and preserves the original feature information through the jump connection.

Results and Discussion

Experimental results show that AR-CenterNet achieves excellent small object detection performance on PASCAL VOC, RSOD, and KITTI datasets.

Conclusion

The method has important application value in the field of intelligent transportation.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/rascs/10.2174/0126662558375299250315001228
2025-05-07
2026-03-03

  • From This Site

    /content/journals/rascs/10.2174/0126662558375299250315001228
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. RokhB. AzarpeyvandA. KhanteymooriA. A comprehensive survey on model quantization for deep neural networks in image classification.ACM Trans. Intell. Syst. Technol.202314615010.1145/3623402
     [Google Scholar]
  2. MamievaD. AbdusalomovA.B. MukhiddinovM. WhangboT.K. Improved face detection method via learning small faces on hard images based on a deep learning approach.Sensors202323150210.3390/s23010502 36617097
     [Google Scholar]
  3. LiuF. ChenD. WangF. LiZ. XuF. Deep learning based single sample face recognition: A survey.Artif. Intell. Rev.20235632723274810.1007/s10462‑022‑10240‑2
     [Google Scholar]
  4. WangH. XuY. WangZ. CaiY. ChenL. LiY. Centernet-auto: A multi-object visual detection algorithm for autonomous driving scenes based on improved centernet.IEEE Trans. Emerg. Top. Comput. Intell.20237374275210.1109/TETCI.2023.3235381
     [Google Scholar]
  5. FengD. HarakehA. WaslanderS.L. A review and comparative study on probabilistic object detection in autonomous driving.IEEE Trans. Intell. Transp. Syst.20222389961998010.1109/TITS.2021.3096854
     [Google Scholar]
  6. QianR. LaiX. LiX. 3d object detection for autonomous driving: A survey.Pattern Recognit.202213010879610.1016/j.patcog.2022.108796
     [Google Scholar]
  7. BenensonR. OmranM. HosangJ. Ten years of pedestrian detection, what have we learned?European Conference on Computer Vision SpringerCham20 March 2015613627
     [Google Scholar]
  8. MaoJ. XiaoT. JiangY. What can help pedestrian detection?2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Honolulu, HI, USA20176034604310.1109/CVPR.2017.639
     [Google Scholar]
  9. LiC. PourtaherianA. van OnzenoortL. TenW.E.T. de WithP.H.N. Infant facial expression analysis: Towards a real-time video monitoring system using r-cnn and hmm.IEEE J. Biomed. Health Inform.20212551429144010.1109/JBHI.2020.3037031 33170787
     [Google Scholar]
  10. WangL. BaoY. LiH. Compact cnn based video representation for efficient video copy detectionInternational Conference on Multimedia Modeling SpringerCham31 December 201657658710.1007/978‑3‑319‑51811‑4_47
     [Google Scholar]
  11. GirshickR. DonahueJ. DarrellT. Visual information processing for deep-sea visual monitoring system.Cognitive Robotics20211311
     [Google Scholar]
  12. ZhangJ. LiuB. ZhangH. ZhangL. WangF. ChenY. A small object detection network for remote sensing based on CS-PANet and DSAN.Multi. Tools Appl.20248328720797209610.1007/s11042‑024‑18397‑4
     [Google Scholar]
  13. LiuJ. LiuC. WuY. XuH. SunZ. An improved method based on deep learning for insulator fault detection in diverse aerial images.Energies20211414436510.3390/en14144365
     [Google Scholar]
  14. QiJ. JiaoL. Bird nest detection on transmission tower based on improved SSD algorithm.Comput. Syst. Appl.20202905202208
     [Google Scholar]
  15. ZhangJ. LiD. ShiX. WangF. LiL. ChenY. DCTnet: A double-channel transformer network for peach disease detection using UAVs.Complex Intell. Syst.202511111110.1007/s40747‑024‑01749‑w
     [Google Scholar]
  16. YanL.Q. WangQ.F. ZhaoJ.H. GuanQ. Radiance field learners as UAV first-person viewers.Computer Vision-ECC2024V2024119
     [Google Scholar]
  17. WangG. ChenY. AnP. HongH. HuJ. HuangT. UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios.Sensors20232316719010.3390/s23167190 37631727
     [Google Scholar]
  18. YavariabdiA. KusetogullariH. CicekH. UAV detection in airborne optic videos using dilated convolutions.J. Opt.202150456958210.1007/s12596‑021‑00770‑3
     [Google Scholar]
  19. YavariabdiA. KusetogullariH. CelikT. CicekH. FastUAV-net: A multi-UAV detection algorithm for embedded platforms.Electronics202110672410.3390/electronics10060724
     [Google Scholar]
  20. GirshickR. DonahueJ. DarrellT. Rich feature hierarchies for accurate object detection and semantic segmentationProceedings of the IEEE conference on computer vision and pattern recognitionOH, USA23-28 June 201458058710.1109/CVPR.2014.81
     [Google Scholar]
  21. GirshickR. Fast r-cnnIEEE International Conference on Computer Vision SantiagoChile07-13 December 20151440144810.1109/ICCV.2015.169
     [Google Scholar]
  22. RenS. HeK. GirshickR. Faster r-cnn: Towards realtime object detection with region proposal networksNIPS’15: Proceedings of the 29th International Conference on Neural Information Processing SystemsMontreal, Canada07 December 20159199
     [Google Scholar]
  23. HeH. XuH. ZhangY. GaoK. LiH. MaL. LiJ. Mask R-CNN based automated identification and extraction of oil well sites.Int. J. Appl. Earth Obs. Geoinf.202211210287510.1016/j.jag.2022.102875
     [Google Scholar]
  24. LiuW. AnguelovD. ErhanD. Ssd: Single shot multibox detectorEuropean Conference on Computer Vision SpringerCham17 September 20162137
     [Google Scholar]
  25. RedmonJ. DivvalaS. GirshickR. You only look once: Unified, real-time object detection2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Las Vegas, NV, USA27-30 June 201677978810.1109/CVPR.2016.91
     [Google Scholar]
  26. NingthoujamR. PritamdasK. SinghL.S. Edge detective weights initialization on Darknet-19 model for YOLOv2-based facemask detection.Neural Comput. Appl.20243635223652237810.1007/s00521‑024‑10427‑4
     [Google Scholar]
  27. HurtikP. MolekV. HulaJ. VajglM. VlasanekP. NejezchlebaT. Poly-YOLO: Higher speed, more precise detection and instance segmentation for YOLOv3.Neural Comput. Appl.202234108275829010.1007/s00521‑021‑05978‑9
     [Google Scholar]
  28. JiS.J. LingQ.H. HanF. An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information.Comput. Electr. Eng.202310510849010.1016/j.compeleceng.2022.108490
     [Google Scholar]
  29. LawH. DengJ. Cornernet: Detecting objects as paired keypointsProceedings of the European Conference on Computer Vision2018734750
     [Google Scholar]
  30. WangR. CheungC.F. CenterNet-based defect detection for additive manufacturing.Expert Syst. Appl.202218811600010.1016/j.eswa.2021.116000
     [Google Scholar]
  31. LinT.Y. Feature pyramid networks for object detectionProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Honolulu, HI, USA21-26 July 201793694410.1109/CVPR.2017.106
     [Google Scholar]
  32. LuY. HanC. WangQ. FanH. KongZ. LiuD. ChenY. Optical flow as spatial-temporal attention learners.IEEE Trans. Pattern Anal. Mach. Intell.20244612114911150610.1109/TPAMI.2024.3463648 39361459
     [Google Scholar]
  33. LiuF. LiuJ. WangB. WangX. LiuC. SiamBRF: Siamese broad-spectrum relevance fusion network for aerial tracking.IEEE Geosci. Remote Sens. Lett.2024211510.1109/LGRS.2024.3351429
     [Google Scholar]
  34. QiG. ZhangY. WangK. MazurN. LiuY. MalaviyaD. Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion.Remote Sens.202214242010.3390/rs14020420
     [Google Scholar]
  35. ZhuZ. ZhengR. QiG. LiS. LiY. GaoX. Small object detection method based on global multi-level perception and dynamic region aggregation.IEEE Trans. Circ. Syst. Video Tech.20243410100111002210.1109/TCSVT.2024.3402097
     [Google Scholar]
  36. LiY. ZhouZ. QiG. HuG. ZhuZ. HuangX. Remote sensing micro-object detection under global and local attention mechanism.Remote Sens.202416464410.3390/rs16040644
     [Google Scholar]
  37. ZhuZ. WangS. GuS. LiY. LiJ. ShuaiL. QiG. Driver distraction detection based on lightweight networks and tiny object detection.Math. Biosci. Eng.20232010182481826610.3934/mbe.2023811 38052557
     [Google Scholar]
  38. CaiZ. VasconcelosN. Cascade R-CNN: Delving into high quality object detection2018 IEEE/CVF Conference on Computer Vision and Pattern RecognitionSalt Lake City, UT, USA18-23 June 20186154616210.1109/CVPR.2018.00644
     [Google Scholar]
  39. NohJ. BaeW. LeeW. Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection2019 IEEE/CVF International Conference on Computer Vision (ICCV) Seoul, Korea (South)27 October 2019 - 02 November 20199724973310.1109/ICCV.2019.00982
     [Google Scholar]
  40. LiuZ. GaoG. SunL. HRDNet: High-resolution detection network for small objects2021 IEEE International Conference on Multimedia and Expo (ICME)Shenzhen, China05-09 July 20211610.1109/ICME51207.2021.9428241
     [Google Scholar]
  41. LiZ. PengC. YuG. Detnet: A backbone network for object detectionarXiv preprint1804.062152018
     [Google Scholar]
  42. ZhangJ. ZhangH. LiuB. QuG. WangF. ZhangH. ShiX. Small object intelligent detection method based on adaptive recursive feature pyramid.Heliyon202397e1773010.1016/j.heliyon.2023.e17730 37539280
     [Google Scholar]
  43. SunH. ZhouM. ChenW. XieW. Tr-detr: Task-reciprocal transformer for joint moment retrieval and highlight detection.Proc. Conf. AAAI Artif. Intell.20243854998500710.1609/aaai.v38i5.28304
     [Google Scholar]
  44. HuJ. ShenL. SunG. Squeeze-and-excitation networks2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Salt Lake CityUT, USA18-23 June 20187132714110.1109/CVPR.2018.00745
     [Google Scholar]
  45. ParkJ. WooS. LeeJ.Y. Bam: Bottleneck attention modulearXiv preprint1807.065142018
     [Google Scholar]
  46. WooS. ParkJ. LeeJ.Y. Cbam: Convolutional block attention moduleEuropean Conference on Computer Vision SpringerCham06 October 2018319
     [Google Scholar]
  47. HouQ. ZhouD. FengJ. Coordinate attention for efficient mobile network designIEEE/CVF Conference on Computer Vision and Pattern RecognitionNashville, TN, USA20-25 June 2021137081371710.1109/CVPR46437.2021.01350
     [Google Scholar]
  48. YangX.Y. WangY.X. RafiT. LiuD.F. Towards automatic oracle prediction for AR testing: Assessing virtual object placement quality under real-world scenes [C]Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis ViennaAustria11 September 202471772910.1145/3650212.3680315
     [Google Scholar]
  49. MahaurB. MishraK.K. Small-object detection based on YOLOv5 in autonomous driving systems.Pattern Recognit. Lett.202316811512210.1016/j.patrec.2023.03.009
     [Google Scholar]
  50. BosquetB. CoresD. SeidenariL. BreaV.M. MucientesM. BimboA.D. A full data augmentation pipeline for small object detection based on generative adversarial networks.Pattern Recognit.202313310899810.1016/j.patcog.2022.108998
     [Google Scholar]
  51. ZhangJ. LinX. ZhangW. WangK. TanX. HanJ. Semi-detr: Semi-supervised object detection with detection transformersProceedings of the IEEE/CVF conference on computer vision and pattern recognitionVancouver, BC, Canada17-24 June 2023238092381810.1109/CVPR52729.2023.02280
     [Google Scholar]
  52. LiuS. QiL. QinH. Path aggregation network for instance segmentationProceedings of the IEEE Conference on Computer Vision and Pattern Recognition Salt Lake CityUT, USA18-23 June 20188759876810.1109/CVPR.2018.00913
     [Google Scholar]
  53. GhiasiG. LinT.Y. LeQ.V. Nas-fpn: Learning scalable feature pyramid architecture for object detectionProceedings of the IEEE/CVF Conference on Computer Vision and Pattern RecognitionLong Beach, CA, USA15-20 June 20197029703810.1109/CVPR.2019.00720
     [Google Scholar]
  54. TanM. PangR. LeQ.V. Efficientdet: Scalable and efficient object detection2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Seattle, WA, USA13-19 June 2020107781078710.1109/CVPR42600.2020.01079
     [Google Scholar]
  55. LiF. ZengA. LiuS. ZhangH. LiH. ZhangL. NiL.M. Lite detr: An interleaved multi-scale encoder for efficient detrProceedings of the IEEE/CVF conference on computer vision and pattern recognitionVancouver, BC, Canada17-24 June 2023185581856710.1109/CVPR52729.2023.01780
     [Google Scholar]
  56. ChenL.C. PapandreouG. KokkinosI. MurphyK. YuilleA.L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs.IEEE Trans. Pattern Anal. Mach. Intell.201840483484810.1109/TPAMI.2017.2699184 28463186
     [Google Scholar]
  57. ChenL.C. PapandreouG. SchroffF. Rethinking atrous convolution for semantic image segmentationarXiv1706.055872017
     [Google Scholar]
  58. ChengZ.Y. ChoiH.J. LiangJ. FengS.W. Fusion is not enough: Single modal attack on fusion models for 3D object detectionThe Twelfth International Conference on Learning Representations2024125
     [Google Scholar]
  59. ZhaoH. ShiJ. QiX. Pyramid scene parsing network2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Honolulu, HI, USA21-26 July 20176230623910.1109/CVPR.2017.660
     [Google Scholar]
  60. LiuS. HuangD. WangY. Receptive field block net for accurate and fast object detectionComputer Vision – ECCV 2018: 15th European Conference MunichGermanySeptember 8-14, 201840441910.1007/978‑3‑030‑01252‑6_24
     [Google Scholar]
  61. LiY. ChenY. WangN. Scale-aware trident networks for object detection2019 IEEE/CVF International Conference on Computer Vision (ICCV)Seoul, Korea (South)27 October 2019 - 02 November 20196053606210.1109/ICCV.2019.00615
     [Google Scholar]
  62. LuY. ZhangJ. SunS. GuoQ. CaoZ. FeiS. YangB. ChenY.V. Label-Efficient video object segmentation with motion clues.IEEE Trans. Circ. Syst. Video Tech.20243486710672110.1109/TCSVT.2023.3298853
     [Google Scholar]
  63. HeK. ZhangX. RenS. Deep residual learning for image recognitionIEEE Conference on Computer Vision and Pattern Recognition Las VegasNV, USA27-30 June 201677077810.1109/CVPR.2016.90
     [Google Scholar]
  64. BellS. ZitnickC.L. BalaK. Inside-outside net: Detecting objects in context with skip pooling and recurrent neuralnetworks2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Las Vegas, NV, USA27-30 June 20162874288310.1109/CVPR.2016.314
     [Google Scholar]
  65. TanX. Fassd: A feature fusion and spatial attention-based single shot detector for small object detectionElectronics9, Electronics2020153610.3390/electronics9091536
     [Google Scholar]
  66. PanH. JiangJ. ChenG. TDFSSD: Top-down feature fusion single shot MultiBox detector.Sig. Proc. Image Commun.20208911598710.1016/j.image.2020.115987
     [Google Scholar]
  67. DaiJ. LiY. HeK. R-FCN: Object detection via regionbased fully convolutional networksarXiv1605.064092016
     [Google Scholar]
  68. LiuZ. MaoH. WuC.Y. A convnet for the 2020sProceedings of the IEEE/CVF conference on computer vision and pattern recognitionNew Orleans, LA, USA18-24 June 2022119661197610.1109/CVPR52688.2022.01167
     [Google Scholar]
  69. YinY. LiH. FuW. Faster-YOLO: An accurate and faster object detection method.Digit. Sig. Process.202010210275610276710.1016/j.dsp.2020.102756
     [Google Scholar]
  70. JocherG. StokenA. ChaurasiaA. ultralytics/yolov5: v6.0 - YOLOv5n 'Nano' models, Roboflow integration, TensorFlow export, OpenCV DNN supportAvailable from: https://zenodo.org/records/5563715
  71. ZhangH. WangY. DayoubF. Varifocalnet: An iou-aware dense object detector2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Nashville, TN, USA20-25 June 20218510851910.1109/CVPR46437.2021.00841
     [Google Scholar]
  72. DaiY. LiuW. WangH. XieW. LongK. Yolo-former: Marrying yolo and transformer for foreign object detection.IEEE Trans. Instrum. Meas.20227111410.1109/TIM.2022.3219468
     [Google Scholar]
  73. ZhangH. DuQ. QiQ. ZhangJ. WangF. GaoM. A recursive attention-enhanced bidirectional feature pyramid network for small object detection.Multimed. Tools Appl.2023829139991401810.1007/s11042‑022‑13951‑4
     [Google Scholar]
/content/journals/rascs/10.2174/0126662558375299250315001228
Loading
An Adaptive Enhanced Residual Attention Method for Small Object Detection
Recent Advances in Computer Science and Communications 19, E26662558375299 (2026); https://doi.org/10.2174/0126662558375299250315001228
/content/journals/rascs/10.2174/0126662558375299250315001228
/content/journals/rascs/10.2174/0126662558375299250315001228
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): adaptive enhanced context model; AR-CenterNet; KITTI; PASCAL VOC; residual attention mechanism; Small object detection

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test