Perbandingan Instance Segmentation Image pada Yolo8
DOI:
https://doi.org/10.25126/jtiik.1148288Abstrak
Seorang pejalan kaki sangat rawan terhadap kecelakaan di jalan. Deteksi pejalan kaki merupakan salah satu cara untuk mengidentifikasi atau megklasifikasikan antara orang, jalan atau yang lainnya. Instance segmentation adalah salah satu proses untuk melakukan segmentasi antara orang dan jalan. Instance segmentation dan penggunaan yolov8 merupakan salah satu implementasi dalam deteksi pejalan kaki. Perbandingan segmentasi pada dataset Penn-Fundan Database menggunakan yolov8 dengan model yolov8n-seg, yolov8s-seg, yolov8m-seg, yolov8l-seg, yolov8x-seg. Penelitian ini menggunakan dataset publik pedestrian atau pejalan kaki dengan objek multi person yang diambil dari dataset Penn-Fudan Database. Dataset mempunyai 2 kelas, yaitu orang dan jalan. Hasil perbandingan penggunaan model yolov8 model segmentasi yang terbaik adalah menggunakan model yolov8l-seg. Hasil penelitian didapatkan Instance segmentation valid box pada data orang, mAP50 tertinggi pada yolov8l-seg dengan nilai 0,828 dan mAP50-95 adalah 0,723. Instance segmentation valid mask pada orang nilai mAP50 tertinggi pada yolov8l-seg dengan nilai 0,825 dan mAP50-95 adalah 0,645. Pada penelitian ini, yolov8l-seg menjadi nilai terbaik dibandingkan versi yang lain, karena berdasarkan nilai mAP tertinggi pada valid mask sebesar 0,825.
Abstract
A pedestrian is very vulnerable to road accidents. Pedestrian detection is one way to identify or classify between people, roads or others. Instance segmentation is one of the processes to segment people and roads. Instance segmentation and the use of yolov8 is one of the implementations in pedestrian detection. Comparison of segmentation on Penn-Fundan Database dataset using yolov8 with yolov8n-seg, yolov8s-seg, yolov8m-seg, yolov8l-seg, yolov8x-seg models. This research uses a public pedestrian dataset with multi-person objects taken from the Penn-Fudan Database dataset. The dataset has 2 classes, namely people and roads. The results of the comparison using the yolov8 model, the best segmentation model is using the yolov8l-seg model. The results obtained Instance segmentation valid box on people data, the highest mAP50 on yolov8l-seg with a value of 0.828 and mAP50-95 is 0.723. Instance segmentation valid mask on people the highest mAP50 value on yolov8l-seg with a value of 0.825 and mAP50-95 is 0.645. In his study, yolov8l-seg is the best value compared to other versions, because based on the highest mAP value on the valid mask of 0.825.
Downloads
Referensi
ALZUBAIDI, ET AL., 2021. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal Big Data, Volume 8, pp. 1-74. https://doi.org/10.1186/s40537-021-00444-8
ANAGNOSTIS, A., TAGARAKIS, A. C., KATERIS, D. & MOYSIADIS, V., 2021. Orchard mapping with deep learning semantic segmentation. Sensor, Volume 21, pp. 1-20. https://doi.org/10.3390/s21113813
BOCHKOVSKIY, A., WANG, C. Y. & LIAO, H. M., 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint, p. arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934
CHEN, X., GIRSHICK, R., HE, K. & DOLLAR, P., 2019. Tensormask: A foundation for dense object segmentation. s.l., In Proceedings of the IEEE/CVF international conference on computer vision, pages 2061–2069. https://doi.org/10.1109/ICCV.2019.00215
DUMITRIU, A. et al., 2023. Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results. s.l., In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1261-1271). https://doi.org/10.1109/CVPRW59228.2023.00133
FANG, Y. ET Al., 2022. Eva: Exploring the limits of masked visual representation learning at scale. Computer Vision and Pattern Recognition, Volume arXiv preprint arXiv:2211.07636. https://doi.org/10.1109/CVPR52729.2023.01855
HE, K., GKIOXARI, G., DOLLAR, P. & GIRSHICK, R., 2017. Mask R-CNN. s.l., In Proceedings of the IEEE international conference on computer vision, pages 2961–2969. https://doi.org/10.48550/arXiv.1703.06870
INUI, A. et al ., 2023. Detection of elbow OCD in the ultrasound image by artificial intelligence using YOLOv8. Applied Sciences, 13(13), p. 7623. https://doi.org/10.3390/app13137623
JOCHER, G., 2022. YOLOv5 by Ultralytics. [Online]
Available at: https://github.com/ultralytics/yolov5/
[Diakses 4 November 2023].
JOCHER, G., CHAURASIA, A. & QIU, J., 2023. YOLO by Ultralytics. [Online]
Available at: https://github. com/ultralytics/ultralytics
[Diakses 2 November 2023].
LI, C. et al., 2023. YOLOv6 v3.0: A Full-Scale Reloading. Computer Vision and Pattern Recognition, Volume arXiv:2301.05586. https://doi.org/10.48550/arXiv.2301.05586
LI, C. et al ., 2022. Yolov6: A single-stage object detection framework for industrial applications. Computer Vision and Pattern Recognition, Volume arXiv:2209.02976. https://doi.org/10.48550/ARXIV.2209.02976
LI, F. et al., 2022. Mask DINO: Towards a unified transformer-based framework for object detection and segmentation. Computer Vision and Pattern Recognition, Volume arXiv:2206.02777. https://doi.org/10.48550/arXiv.2206.02777
LIU, Z. et al., 2022. Swin transformer v2: Scaling up capacity and resolution. arXiv preprint arXiv:2206.02777, In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR52688.2022.01170
LOU, H. et al., 2023. DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor. Electrics, 12(10), p. 2323. https://doi.org/10.3390/electronics12102323
RAJENDAR, S. et al., 2022. Prediction of stopping distance for autonomous emergency braking using stereo camera pedestrian detection. Materials Today: Proceedings, 51(1), pp. 1224-1228. https://doi.org/10.1016/j.matpr.2021.07.211
REDMON, J., DIVVALA, S., GIRSHICK, R. & FARHADI, A., 2022. You only look once: Unified, real-time object detection. s.l., IEEE conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2016.91
SETIYADI, A., UTAMI, E. & ARIATMANTO, D., 2023. Analisa Kemampuan Algoritma YOLOv8 Dalam Deteksi Objek Manusia Dengan Metode Modifikasi Arsitektur. J-SAKTI (Jurnal Sains Komputer dan Informatika), 7(2), pp. 891-901. https://doi.org/10.30645/j-sakti.v7i2.694
WANG, C. Y., BOCHKOVSKIY, A. & LIAO, H. M., 2022. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. s.l., IEEE. https://doi.org/10.1109/CVPR52729.2023.00721
WANG, C. Y. et al., 2017. Yolo9000: Better, faster, stronger. Computer Vision and Pattern Recognition (IEEE), pp. 6517-6525. https://doi.org/10.1109/CVPR.2017.690
WEI, Y., HU, H. & XIE, Z., 2022. Image as a foreign language: BEiT pretraining for all vision and visionlanguage tasks. Computer Vision and Pattern Recognition, Volume arXiv:2208.10442. https://doi.org/10.48550/arXiv.2208.10442
WEI, Y., HU, H., XIE, Z. & ZHANG, Z., 2022. Contrastive learning rivals masked image modeling in fine-tuning via feature distillation. Computer Vision and Pattern Recognition, Volume arXiv:2205.14141. https://doi.org/10.48550/arXiv.2205.14141
XIE, E. et al., 2020. Polarmask: Single shot instance segmentation with polar representation. s.l., In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12193–12202. https://doi.org/10.1109/CVPR42600.2020.01221
XIE, E. et al., 2020. Sipmask: Spatial information preservation for fast image and video instance segmentation. Glasgow, UK, In Computer Vision–ECCV 2020: 16th European Conference. https://doi.org/10.1007/978-3-030-58568-6_1
ZHAO, X. & SONG, Y., 2023. Improved Ship Detection with YOLOv8 Enhanced with MobileViT and GSConv. Electronics, 12(22), p. 4666. https://doi.org/10.3390/electronics12224666
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Jurnal Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
Artikel ini berlisensi Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Penulis yang menerbitkan di jurnal ini menyetujui ketentuan berikut:
- Penulis menyimpan hak cipta dan memberikan jurnal hak penerbitan pertama naskah secara simultan dengan lisensi di bawah Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) yang mengizinkan orang lain untuk berbagi pekerjaan dengan sebuah pernyataan kepenulisan pekerjaan dan penerbitan awal di jurnal ini.
- Penulis bisa memasukkan ke dalam penyusunan kontraktual tambahan terpisah untuk distribusi non ekslusif versi kaya terbitan jurnal (contoh: mempostingnya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan penerbitan awalnya di jurnal ini.
- Penulis diizinkan dan didorong untuk mem-posting karya mereka online (contoh: di repositori institusional atau di website mereka) sebelum dan selama proses penyerahan, karena dapat mengarahkan ke pertukaran produktif, seperti halnya sitiran yang lebih awal dan lebih hebat dari karya yang diterbitkan. (Lihat Efek Akses Terbuka).
