Target Detection in Ground Based Images with Limited Dataset Based on Deep Learning

Document Type : Original Article

Authors

1 Master's degree, Imam Hussein (AS) University, Tehran, Iran

2 Assistant Professor, Imam Hussein (AS) University, Tehran, Iran

3 PhD Student, Imam Hossein (AS) University, Tehran, Iran

Abstract

The YOLO object detection algorithm is one of the most famous and widely used algorithms in the field of computer vision. This algorithm learns from abundant training images and can achieve remarkable performance in target detection. However, in special conditions such as military, medical, and hazardous environments where acquiring real target images is time-consuming and challenging, there are limitations that researchers seek alternative solutions to address the data scarcity issue and improve the accuracy of the algorithm. One innovative approach to solving this problem is the use of artificially generated data produced by game engines. This method reduces the reliance on real data and improves the performance and accuracy of the algorithm. By utilizing synthetic data, the limitation of the number of training data for the algorithm is overcome, and the algorithm's performance in complex and dangerous conditions is enhanced. Additionally, the use of synthetic data leads to a reduction in time, human resources, and costs required for data collection. In general, the use of synthetic data as an alternative solution in training object detection algorithms has gained attention from researchers and users due to advantages such as time reduction, reduction in human resources, and cost reduction. To achieve desirable performance in tank identification, artificially generated data produced by the Unreal Engine game engine has been used. The generated dataset has been tested on four versions of the YOLOv5 network, namely YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x, and their results have been reported.

Keywords

Main Subjects

Smiley face

 

References

  [1]      Ali, S.; Abdullah, A.; Athar, A.; Ali, M.; Hussain, A.; Kim, H.-C. “Computer Vision-Based Military Tank Recognition Using Object Detection Technique: An Application of the YOLO Framework”;International Conference on Advanced Innovations in Smart Cities (ICAISC),   2023,DOI:10.1109/icaisc56366.2023.10085552.
  [2]      Jang, J.; Lee, H.; Kim, J.-C. “CarFree: Hassle-Free Object Detection Dataset Generation Using Carla Autonomous Driving Simulator”; Applied Sciences, 2021, DOI:10.3390/app12010281.  
  [3]      Man, K.; Chahl, J. “A Review of Synthetic Image Data and Its Use in Computer Vision”; Journal of Imaging, 2022, DOI:10.3390/jimaging8110310.  
  [4]      Zou, Z.; Chen, K.; Shi, Z.; Guo, Y.; Ye, J. “Object Detection in 20 Years: A Survey”; Proceedings of the IEEE, 2023, DOI:10.1109/jproc.2023.3238524.
  [5]      Rasmussen, I.; Kvalsvik, S.; Andersen, P.-A.; Aune, T. N.; Hagen, D. “Development of a Novel Object Detection System Based on Synthetic Data Generated from Unreal Game Engine”; Applied Sciences, 2022, DOI:10.3390/app12178534. 
  [6]      Jaipuria, N.; et al. “Deflating Dataset Bias Using Synthetic Data Augmentation”; IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, DOI:10.1109/cvprw50498.2020.00394.
  [7]      Aljundi, R.; Tuytelaars, T. “Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction”; Computer Vision – ECCV 2016 Workshops, 2016, DOI:10.1007/978-3-319-49409-8_43.
  [8]      Tsirikoglou, A.; Eilertsen, G.; Unger, J. “A Survey of Image Synthesis Methods for Visual Machine Learning”; Computer Graphics Forum, 2020, DOI:10.1111/cgf.14047.  
                 [9]      Fayzi, A.; Dadashtabar, K.; Tohidi Far, A. “Detection and Tracking of Firearms and Cold Weapons Using Deep Learning Networks”;Journal of Advanced Defense Science & Technology, 2023. https://dor.isc.ac/dor/20.1001.1.26762935.1401.13.4.2.1
[10]      Farajollahi, A.; Rostami, M.; Parvin, H.; Nazarpour, B.; Lak, M. “Face Detection and Identification in Drones with Deep Learning”; Journal of Advanced Defense Science & Technology, 2022.
[11]      Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. “You Only Look Once: Unified, Real-Time Object Detection”; 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, DOI:10.1109/cvpr.2016.91.
[12]      Sarda, A.; Dixit, S.; Bhan, A. “Object Detection for Autonomous Driving Using YOLO Algorithm”; International Conference on Intelligent Engineering and Management (ICIEM), 2021, DOI:10.1109/iciem51511.2021.9445365. 
[13]      Redmon, J.; Farhadi, A. “YOLO9000: Better, Faster, Stronger”; 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, DOI:10.1109/cvpr.2017.690.
[14]      Liu, Z.; Chen, Z.; Li, Z.; Hu, W. “An Efficient Pedestrian Detection Method Based on YOLOv2”; Mathematical Problems in Engineering, 2018, DOI:10.1155/2018/3518959.
[15]      Kivrak, O.; Gürbüz, M. Z. “Performance Comparison of YOLOv3, YOLOv4, and YOLOv5 Algorithms: A Case Study for Livestock Recognition”; European Journal of Science and Technology, 2022, DOI:10.31590/ejosat.1111288. 
[16]      Francies, M. L.; Ata, M. M.; Mohamed, M. A. “A Robust Multiclass 3D Object Recognition Based on Modern YOLO Deep Learning Algorithms”; Concurrency and Computation: Practice and Experience, 2021, DOI:10.1002/cpe.6517. 
[17]      Yao, G.; Sun, Y.; Wong, M.; Lv, X. “A Real-Time Detection Method for Concrete Surface Cracks Based on Improved YOLOv4”; Symmetry, 2021, DOI:10.3390/sym13091716.  
              [18]      Bahrami, M.; Asghari, A.; Binesh Marvasti, M.; Ansariyan, S. “Providing an Improved Unmanned Aerial Vehicle Detection System to Increase Detection Speed Using Deep Learning”; Electronic and Cyber Defense, 2023,41,81-96  https://dor.isc.ac/dor/20.1001.1.23224347.1402.11.1.7.8
[19]      Qian, S.; Dai, S. “Identification of High-Speed Railway Trackside Equipments Based on YOLOv4”; China Automation Congress (CAC), 2022, DOI:10.1109/cac57257.2022.10055473.
[20]      https://github.com/ultralytics/yolov5, Nov 2022.  
[21]      https://github.com/open-mmlab/mmyolo/tree/ma, Aug 2023. 
[22]      Shorten, C.; Khoshgoftaar, T. M. “A Survey on Image Data Augmentation for Deep Learning”; Journal of Big Data, 2019, DOI:10.1186/s40537-019-0197-0. 
[23]      Freedman, E. “Game Engine Culture”; The Persistence of Code in Game Engine Culture, 2020, DOI:10.4324/9780429434242-1.  
              [24]      Akbarian, H.; Sedaaghi, M. H. “Recognition of Acoustic Emitted from Surface Vessels Using MobileNet Convolutional Algorithm”; Journal of Advanced Defense Science & Technology, 2023. 51,39-50.https://dor.isc.ac/dor/20.1001.1.26762935.1402.14.1.4.4
Journal of Advanced Defense Science & Technology
Volume 15, Issue 1 - Serial Number 55
Spring2024
June 2025
Pages 27-35

Files

History

  • Receive Date: 28 March 2024
  • Revise Date: 22 April 2024
  • Accept Date: 01 May 2024
  • Publish Date: 31 May 2024

Share

How to cite

Statistics