ABSTRACT
The present study seeks to improve upon the study conducted, with the researchers employing a different depth estimation computation method and an enhanced object detection model. The constituents will use their captured data with the OpenCV library to train the Model, whose architecture is YOLOv5. The constituents have also contributed data where the camera view is obstructed by natural illumination or weather to determine whether the Model also detects vehicles in an obstructed view. Since the previous study relied on trial-and-error methods to estimate depth, the Model's constituents will employ the Triangle Similarity method [7]. The Model is operational because of the input data passing through the YOLOv5 Architecture, head, neck, and back. Once the vehicle is identified, its focal point will be used to ascertain its distance, continuously updated in real-time. Since YOLOv3 was used as the Model for object detection in the previous study, using the YOLOv5 architecture has improved the accuracy, according to the constituents. Using Triangle Similarity, the previous study's trial-and-error technique for depth estimation was improved. Given that the previous study relied solely on trial-and-error methods for depth estimation, this study may have room for improvement [14].
- Hsieh Cheng-Hsiung, Lin Dung-Ching, Wang Cheng-Jia, Chen Zong-Ting, and Liaw Jiun-Jian. 2020. (January 2020) Retrieved October 18, 2021, from https://ezproxy.mapua.edu.ph:2068/document/8949265Google Scholar
- Lai Yeong-Kang. 2019. (December 2019) Retrieved October 19, 2021, from https://ezproxy.mapua.edu.ph:2068/document/8605622Google Scholar
- M. Ning, Y. Lu, W. Hou, and M. Matskin, "YOLOv4-object: an Efficient Model and Method for Object Discovery," 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), 2021, pp. 31-36, doi: 10.1109/COMPSAC51774.2021.00016.Google ScholarCross Ref
- Zhao Cong Cong 2019.(December 2019) Retrieved October 19, 2021 from https://ezproxy.mapua.edu.ph:2068/document/8941515Google Scholar
- Lu Yonghui. 2020. (August 2020) Retrieved October 19, 2021, from https://ezproxy.mapua.edu.ph:2068/document/9164580Google Scholar
- Wu Tian-Hao. 2020. (July 2020) Retrieved October 19, 2021, from https://ezproxy.mapua.edu.ph:2068/document/9486316Google Scholar
- A. M. Ibrahim, R. M. Hassan, A. E. Tawfiles, T. Ismail and M. S. Darweesh, "Real-Time Collision Warning System Based on Computer Vision Using Mono Camera," 2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2020, pp. 60-64, doi: 10.1109/NILES50944.2020.9257941.Google ScholarCross Ref
- S. Saleh, C. Rellan, and S.P. Surana, "Collision Warning Based on Multi-Object Detection and Distance Estimation," Conference: International Symposium on Computer Science, Computer Engineering and Educational TechnologyAt: Ulaanbaatar, MongoliaVolume: ISBN: 978-3-95908-223-5, Oct. 2020.Google Scholar
- Ultralytics. (n.d.) YOLOv5: State-of-the-art object detection https://ultralytics.com/yolov5Google Scholar
- Alizadeh, P, “Object Distance Measurement Using a Single Camera for Robotic Applications,” 2015, Laurentian University, Sudbury, Ontario, Canada: The Faculty of Graduate Studies.Google Scholar
- Nepal, U and Eslamiat, H, "Comparing YOLOv3, YOLOv4, and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs," 2022 Basel, Switzerland: MDPI, https:// doi.org/10.3390/s22020464Google ScholarCross Ref
- D. E. Saputra, A. S. M. Senjaya, J. Ivander, and A. W. Chandra, "Experiment on Distance Measurement Using Single Camera," 2021 4th International Conference on Information and Communications Technology (ICOIACT), 2021, pp. 80-85, doi: 10.1109/ICOIACT53268.2021.9564010.Google ScholarCross Ref
- M. Pratama, W. Budi, S. A. Dimyani, A. Praptijanto, A. Nur and Y. Putrasari, "Performance of Inter-vehicular Distance Estimation: Pose from Orthography and Triangle Similarity," 2019 International Conference on Sustainable Energy Engineering and Application (ICSEEA), 2019, pp. 37-41, doi: 10.1109/ICSEEA47812.2019.8938648.Google ScholarCross Ref
- Wang, Y., & Liu, J. (2019). Distance Estimation of Objects from a Single Monocular Image Using Triangle Similarity 2019 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), Kuala Lumpur, Malaysia https://doi.org/10.1109/ICSIPA47852.2019.8977788Google ScholarCross Ref
- Shrestha, R., & Park, D. (2020). Object Detection-Based Distance Measurement Using Triangle Similarity Electronics, 9(6), 983 https://doi.org/10.3390/electronics9060983Google ScholarCross Ref
- Shrestha, R., & Park, D. (2020). Distance Estimation of Objects from Stereo Images Using Triangle Similarity and Feature Extraction Symmetry, 12(7), 1193 https://doi.org/10.3390/sym12071193Google ScholarCross Ref
- A. Bochkovskiy, CY Wang, HY. Mark Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection,"https://arxiv.org/pdf/2004.10934.pdfGoogle Scholar
Index Terms
- Distance Estimation of Vehicles using Triangle Similarity and Feature Extraction
Recommendations
Vehicles overtaking detection using RGB-D data
Outstanding breakthrough in traffic video surveillance has been made with the development of computer vision techniques. However, there are still some problems to be solved due to the limitations of two-dimensional (2D) video data. With the popularity ...
Driver drowsiness estimation using facial wrinkle feature
SIGGRAPH '13: ACM SIGGRAPH 2013 PostersIn recent years, the rate of fatal motor vehicle accidents caused by distracted driving resulting from factors such as sleeping at the wheel has been increasing. Therefore, an alert system that detects driver drowsiness and prevents accidents as a ...
Motorcycle Helmet Detection and Usage Classification in the Philippines using YOLOv5 Algorithm
CIIS '22: Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent SystemsMotorcycles are becoming the primary option for mobility worldwide, and the number of motorcycle riders has been exponentially increasing over the years. In the Philippines, it is reported that the increase in registered motorcycles was greater than the ...
Comments