YOLOV8: An Enhanced Object Detection Model for Distance Estimation

Authors

  • Urvashi Verma, Anshul Kalia, Sumesh Sood

Keywords:

YOLOv8-CAW, Coordinate Attention (CA) module, Wise-Intersection over Union (WIoU) loss function, Object detection, Distance estimation.

Abstract

The rapid evolution of deep learning has transformed computer vision, yet research on leveraging this technology for distance estimation remains limited. Such investigations could greatly benefit various applications, notably anomaly detection. This study introduces an enhanced detection model, YOLOV8-CAW, which Integrates Coordinate Attention and Wise-loU Into the YOLOV8 framework to improve detection accuracy. Incorporating a distance estimation algorithm yields comprehensive outputs, combining detection results with accurate distance calculations. Experimental results demonstrate significant performance enhancements, with improvements in recall (0.4%), precision (2.2%), and Mean Average Precision (mAP) (1.5%) within the 0.5 to 0.95 threshold range while maintaining inference speeds comparable to the baseline model on the PASCAL VOC dataset. Additionally, distance estimation achieves an approximate average accuracy of 90%, indicating promising outcomes. The effective combination of computer vision and separate estimation presents unused roads for viable applications, highlighting the potential of this approach in real-world scenarios.

Downloads

Download data is not yet available.

References

J. Ai, Z. Qu, Z. Zhao, Y. Zhang, J. Shi and H. Yan, "An SAR Target Classification Algorithm Based on the Central Coordinate Attention Module," in IEEE Sensors Journal, vol. 24, no. 2, pp. 1941-1952, 15 Jan.15, 2024, doi: 10.1109/JSEN.2023.3338218.

M. Zhao, G. Zuo and G. Huang, "Collaborative Learning of Deep Reinforcement Pushing and Grasping based on Coordinate Attention in Clutter," 2022 International Conference on Virtual Reality, Human-Computer Interaction and Artificial Intelligence (VRHCIAI), Changsha, China, 2022, pp. 156-161, doi: 10.1109/VRHCIAI57205.2022.00034.

Y. Ren, X. Jiang, T. Qi, J. Li, M. Yan and X. Feng, "Low-Illumination Image Enhancement Based on End-to-End Network Using Attention Module," 2023 2nd International Conference on Image Processing and Media Computing (ICIPMC), Xi'an, China, 2023, pp. 9-14, doi: 10.1109/ICIPMC58929.2023.00009.

K. -C. Wang et al., "CA-Wav2Lip: Coordinate Attention-based Speech To Lip Synthesis In The Wild," 2023 IEEE International Conference on Smart Computing (SMARTCOMP), Nashville, TN, USA, 2023, pp. 1-8, doi: 10.1109/SMARTCOMP58114.2023.00018.

H. Liu, N. Zhang, T. Tian and J. Tian, "Mafe-Net:Multi-Scale Adaptive Feature Enhancement Network for Infrared Weak Vehicle Targets Detection," IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023, pp. 6604-6607, doi: 10.1109/IGARSS52108.2023.10282461.

Y. Wu, J. Li and J. Yang, "Using Improved DeepLabV3+ for Complex Scene Segmentation," 2023 IEEE 6th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), Shenyang, China, 2023, pp. 855-860, doi: 10.1109/AUTEEE60196.2023.10408693.

Y. Wang, C. Cao, Y. Li, Q. Dong, H. Li and J. Sun, "Radiofrequency Fingerprint Feature Extraction and Recognition Using a Coordinate Attention-Guided Deep Residual Shrinkage Network," 2023 International Conference on Networking and Network Applications (NaNA), Qingdao, China, 2023, pp. 551-557, doi: 10.1109/NaNA60121.2023.00097.

W. Sheng, S. Liu and P. Liu, "Speech noise reduction algorithm based on CA-DCDCCRN," 2023 2nd International Joint Conference on Information and Communication Engineering (JCICE), Chengdu, China, 2023, pp. 151-156, doi: 10.1109/JCICE59059.2023.00039.

X. Xiang, D. Tian, N. Lv and Q. Yan, "FCDNet: A Change Detection Network Based on Full-Scale Skip Connections and Coordinate Attention," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 6511605, doi: 10.1109/LGRS.2022.3184179.

H. Zhang, A. Xiong, L. Lai, C. Chen and J. Liang, "AMME-YOLOv7: Improved YOLOv7 Based on Attention Mechanism and Multiscale Expansion for Electric Vehicle Driver and Passenger Helmet Wearing Detection," 2023 IEEE International Conference on Smart Internet of Things (SmartIoT), Xining, China, 2023, pp. 223-227, doi: 10.1109/SmartIoT58732.2023.00039.

S. Jia, X. Zhang and W. Han, "Audio-Visual Speech Enhancement Based on Multiscale Features and Parallel Attention," 2024 23rd International Symposium INFOTEH-JAHORINA (INFOTEH), East Sarajevo, Bosnia and Herzegovina, 2024, pp. 1-6, doi: 10.1109/INFOTEH60418.2024.10495981.

J. Liao, J. Wu, L. Zhu and H. Kang, "A Pavement Cracks detection algorithm based on CCA-YOLOv5s," 2023 35th Chinese Control and Decision Conference (CCDC), Yichang, China, 2023, pp. 471-476, doi: 10.1109/CCDC58219.2023.10327095.

Z. Deng, Y. Li, S. He, Y. Wang and X. Wang, "A High-Resolution Human Pose Estimation Method with Coordinate Attention," 2022 9th International Conference on Digital Home (ICDH), Guangzhou, China, 2022, pp. 299-306, doi: 10.1109/ICDH57206.2022.00053.

Y. Ren, X. Jiang, T. Qi, J. Li, M. Yan and X. Feng, "Low-Illumination Image Enhancement Based on End-to-End Network Using Attention Module," 2023 2nd International Conference on Image Processing and Media Computing (ICIPMC), Xi'an, China, 2023, pp. 9-14, doi: 10.1109/ICIPMC58929.2023.00009.

J. Ai, Z. Qu, Z. Zhao, Y. Zhang, J. Shi and H. Yan, "An SAR Target Classification Algorithm Based on the Central Coordinate Attention Module," in IEEE Sensors Journal, vol. 24, no. 2, pp. 1941-1952, 15 Jan.15, 2024, doi: 10.1109/JSEN.2023.3338218.

Downloads

Published

26.03.2024

How to Cite

Urvashi Verma. (2024). YOLOV8: An Enhanced Object Detection Model for Distance Estimation. International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 3852 –. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6156

Issue

Section

Research Article