Penerapan Gamma Correction Dalam Peningkatan Pendeteksian Objek Malam Pada Algoritma YOLOv5
-
Viviana Fransisca
*
Universitas Pradita, Tangerang,
Indonesia
- Handri Santoso Universitas Pradita, Tangerang, Indonesia (*) Corresponding Author
Abstract
YOLOv5 (You Only Look Once) is a popular object detection method used in the field of computer vision. YOLOv5 is often used to detect objects in images and videos in real-time with high speed and accuracy. This method is easy to use because it is open-source, so it can be directly used to create a model that fits the object you want to detect. YOLOv5 can easily recognize objects detected during the day, but this method has difficulties when it is made to detect objects at night. With the improvisation of the YOLOv5 method which can accurately detect objects at night, other researchers who wish to conduct research related to object detection at night can use the exact technique to produce more accurate object detection. This study uses the Gamma Correction method by adding a Gamma of 2 so that the trained image dataset becomes bright and YOLOv5 can recognize objects at night more easily. As a result, an improvised technique using Gamma Correction can make YOLOv5 recognize objects and make detections at night more accurately, where the average accuracy obtained before improvisation is 0.846, while after improvisation the results obtained are 0.918. From these average results, it can be stated that the gamma correction method can improve the accuracy results in object detection on YOLOv5
Downloads
References
E. Guney, C. Bayilmis, and B. Cakan, “An Implementation of Real-Time Traffic Signs and Road Objects Detection Based on Mobile GPU Platforms,” IEEE Access, vol. 10, pp. 86191–86203, 2022, doi: 10.1109/ACCESS.2022.3198954.
X. Jiang, A. Hadid, Y. Pang, E. Granger, and X. Feng, Deep learning in object detection and recognition. Springer Singapore, 2019. doi: 10.1007/978-981-10-5152-4.
Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” May 2019, [Online]. Available: http://arxiv.org/abs/1905.05055
C. Y. Cao, J. C. Zheng, Y. Q. Huang, J. Liu, and C. F. Yang, “Investigation of a promoted you only look once algorithm and its application in traffic flow monitoring,” Applied Sciences (Switzerland), vol. 9, no. 17, Sep. 2019, doi: 10.3390/app9173619.
C. Tung et al., “Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting Conditions,” Dec. 2018, [Online]. Available: http://arxiv.org/abs/1812.11901
L. Jiao et al., “A survey of deep learning-based object detection,” IEEE Access, vol. 7, pp. 128837–128868, 2019, doi: 10.1109/ACCESS.2019.2939201.
W. Liu, Z. Wang, B. Zhou, S. Yang, and Z. Gong, “Real-time Signal Light Detection based on Yolov5 for Railway,” in IOP Conference Series: Earth and Environmental Science, IOP Publishing Ltd, May 2021. doi: 10.1088/1755-1315/769/4/042069.
W. Wu et al., “Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image,” PLoS One, vol. 16, no. 10 October, Oct. 2021, doi: 10.1371/journal.pone.0259283.
J. H. Kim, N. Kim, Y. W. Park, and C. S. Won, “Object Detection and Classification Based on YOLO-V5 with Improved Maritime Dataset,” J Mar Sci Eng, vol. 10, no. 3, Mar. 2022, doi: 10.3390/jmse10030377.
X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios.” 2021, pp. 2778-2788. doi: https://doi.org/10.1109/ICCV51829.2021.00286
Y. Li, M. Ni, and Y. Lu, “Insulator defect detection for power grid based on light correction enhancement and YOLOv5 model,” Energy Reports, vol. 8, pp. 807–814, Nov. 2022, doi: 10.1016/j.egyr.2022.08.027.
Q. Cai, S. Zhong, and K. Chen, “Target detection in rural river image based on YOLO v5 model with the cross-stitch unit,” 2021 6th International Conference on Image, Vision and Computing (ICIVC), pp. 36-42, Jul. 2021, doi: https://doi.org/10.1109/ICIVC52351.2021.9527005
B. Montenegro and M. Flores-Calero, “Pedestrian detection at daytime and nighttime conditions based on YOLO-v5,” Ingenius, vol. 2022, no. 27, pp. 85–95, Jan. 2022, doi: 10.17163/ings.n27.2022.08.
J. Wei, Q. Zhijie, X. Bo, and Z. Dean, “A nighttime image enhancement method based on retinex and guided filter for object recognition of apple harvesting robot,” Int J Adv Robot Syst, vol. 15, no. 1, Jan. 2018, doi: 10.1177/1729881417753871.
Y. Zhang, Z. Guo, J. Wu, Y. Tian, H. Tang, and X. Guo, “Real-Time Vehicle Detection Based on Improved YOLO v5,” Sustainability (Switzerland), vol. 14, no. 19, Oct. 2022, doi: 10.3390/su141912274.
M. Ramdhan, “Metode penelitian.” Cipta Media Nusantara. 2021.
G. Finlayson and J. McVey, “TM-Net: A Neural Net Architecture for Tone Mapping,” J Imaging, vol. 8, no. 12, Dec. 2022, doi: 10.3390/jimaging8120325.
S. Ruuska, W. Hämäläinen, S. Kajava, M. Mughal, P. Matilainen, and J. Mononen, “Evaluation of the confusion matrix method in the validation of an automated system for measuring feeding behaviour of cattle,” Behavioural Processes, vol. 148, pp. 56–62, Mar. 2018, doi: 10.1016/j.beproc.2018.01.004.
R. Kannan and V. Vasanthi, “Machine learning algorithms with ROC curve for predicting and diagnosing the heart disease,” in SpringerBriefs in Applied Sciences and Technology, Springer Verlag, 2019, pp. 63–72. doi: 10.1007/978-981-13-0059-2_8.
A. C. J. W. Janssens and F. K. Martens, “Reflection on modern methods: Revisiting the area under the ROC Curve,” Int J Epidemiol, vol. 49, no. 4, pp. 1397–1403, Aug. 2020, doi: 10.1093/ije/dyz274.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Penerapan Gamma Correction Dalam Peningkatan Pendeteksian Objek Malam Pada Algoritma YOLOv5
Pages: 59−69
Copyright (c) 2023 Viviana Fransisca, Handri Santoso
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
