Evaluting the Performance of the Yolov7 Algorithm :A Comparative Study of iPhone and Samsung Smartphones Under Varying Lighting Conditions
DOI:
https://doi.org/10.37376/sjuob.v38i1.7321Keywords:
environmental lighting, object detection, YOLOv7, smartphoneAbstract
This study evaluates the performance of the YOLOv7 algorithm for real-time object detection, emphasizing the impact of smartphone hardware capabilities (iPhone vs. Samsung) and environmental lighting conditions (day vs. night). Through extensive testing on diverse datasets, including urban scenes from Ajdabiya city, YOLOv7 demonstrated robust accuracy for high-contrast, well-represented objects such as cars (up to 0.96 accuracy) and appliances (e.g., microwave: 0.91). However, significant variability was observed in detecting occluded or small-scale objects (e.g., people: 0.33–0.88; plant pot: 0.28) and underrepresented classes (e.g., fire extinguishers: undetected). Hardware-specific disparities emerged: iPhones outperformed Samsung devices in low-light scenarios (person detection: 0.88 vs. 0.85), while Samsung exhibited superior dynamic range for trucks (0.90 vs. 0.89). Environmental factors, such as glare and overexposure, further exacerbated detection inconsistencies, particularly for traffic lights (nighttime range: 0.34–0.52). The study identifies critical gaps in YOLOv7’s generalizability, including sensitivity to dataset bias and environmental conditions, and underscores the need for hardware-aware preprocessing and dataset diversification. Future research should prioritize adaptive thresholding techniques and context-specific calibration to enhance reliability in real-world applications such as urban surveillance and autonomous systems.Downloads
References
Szeliski R. Computer Vision: Algorithms and Applications. 2nd ed. Springer; 2022. DOI: https://doi.org/10.1007/978-3-030-34372-9
Badue C, Guidolini R, Carneiro RV, et al. Self-driving cars: A survey. Expert Syst Appl. 2021;165:113816. DOI: https://doi.org/10.1016/j.eswa.2020.113816.
He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. Proc IEEE Conf Comput Vis Pattern Recognit. 2016;770-8.DOI: https://doi.org/10.1109/CVPR.2016.90.
Wang CY, Bochkovskiy A, Liao HYM. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. arXiv. 2022. Available from: https://arxiv.org/abs/2207.02696.
Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. arXiv. 2016. Available from: https://arxiv.org/abs/1506.02640.
Mittelstadt B, Floridi L. The ethics of big data: Current and foreseeable issues in biomedical contexts. Sci Eng Ethics. 2016;22(2):303-41. DOI: https://doi.org/10.1007/s11948-015-9652-2.
Girshick R. Fast R-CNN. Proc IEEE Int Conf Comput Vis. 2015;1440-8. DOI: https://doi.org/10.1109/ICCV.2015.169.
Kang, S., Hu, Z., Liu, L., Zhang, K., & Cao, Z. (2025). Object Detection YOLO Algorithms and Their Industrial Applications: Overview and Comparative Analysis. Electronics, 14(6), 1104. https://doi.org/10.3390/electronics14061104
Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector. Proc Eur Conf Comput Vis. 2016;21-37. DOI: https://doi.org/10.1007/978-3-319-46448-0_2.
Redmon J, Farhadi A. YOLOv3: An Incremental Improvement. arXiv. 2018. Available from: https://arxiv.org/abs/1804.02767.
Bojarski M, Del Testa D, Dworakowski D, et al. End-to-end learning for self-driving cars. arXiv. 2016. Available from: https://arxiv.org/abs/1604.07316.
Zhao ZQ, Zheng P, Xu ST, Wu X. Object Detection with Deep Learning: A Review. IEEE Trans Neural Netw Learn Syst. 2019;30(11):3212-32. DOI: https://doi.org/10.1109/TNNLS.2018.2876865.
Russakovsky O, Deng J, Su H, et al. ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis. 2015;115(3):211-52. DOI: https://doi.org/10.1007/s11263-015-0816-y.
Lowe DG. Distinctive Image Features from Scale-Invariant Keypoints. Int J Comput Vis. 2004;60(2):91-110. DOI: https://doi.org/10.1023/B:VISI.0000029664.99615.94.
Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. Proc Int Conf Mach Learn. 2019;6105-14. DOI: https://doi.org/10.48550/arXiv.1905.11946.
Lucas BD, Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision. Proc 7th Int Jt Conf Artif Intell. 1981;674-9.
Taigman Y, Yang M, Ranzato M, Wolf L. DeepFace: Closing the Gap to Human-Level Performance in Face Verification. Proc IEEE Conf Comput Vis Pattern Recognit. 2014;1701-8. DOI: https://doi.org/10.1109/CVPR.2014.220.
Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. DOI: https://doi.org/10.1038/s41591-018-0300-7.
Jouppi NP, Young C, Patil N, et al. In-datacenter performance analysis of a tensor processing unit. ACM SIGARCH Comput Archit News. 2017;45(2):1-12. DOI: https://doi.org/10.1145/3140659.3080246.
Deng J, Dong W, Socher R, et al. ImageNet: A large-scale hierarchical image database. Proc IEEE Conf Comput Vis Pattern Recognit. 2009;248-55. DOI: https://doi.org/10.1109/CVPR.2009.5206848.
Lin TY, Goyal P, Girshick R, et al. Focal Loss for Dense Object Detection. Proc IEEE Int Conf Comput Vis. 2017;2980-8. DOI: 10.1109/ICCV.2017.324.
Huang J, Rathod V, Sun C, et al. Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors. Proc IEEE Conf Comput Vis Pattern Recognit. 2017;7310-1.
He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. Proc IEEE Int Conf Comput Vis. 2017;2961-9. DOI: 10.1109/ICCV.2017.322.
Tan M, Pang R, Le QV. EfficientDet: Scalable and Efficient Object Detection. Proc IEEE Conf Comput Vis Pattern Recognit. 2020;10781-90. DOI: 10.1109/CVPR42600.2020.01081.
LeCun Y, Boser B, Denker JS, et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Comput. 1989;1(4):541-51. DOI: https://doi.org/10.1162/neco.1989.1.4.541.
Cortes C, Vapnik V. Support-Vector Networks. Mach Learn. 1995;20(3):273-97. DOI: https://doi.org/10.1007/BF00994018.
Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Adv Neural Inf Process Syst. 2015;28:91-9.
Iren E. Comparison of YOLOv5 and YOLOv6 models for plant leaf disease detection. Eng Technol Appl Sci Res. 2024;14(2):13714-9. DOI: 10.48001/etasmr.2024.13714.
Ennaama S, Silkan H, Bentajer A, Tahiri A. Enhanced real-time object detection using YOLOv7 and MobileNetv3. Eng Technol Appl Sci Res. 2025;15(1):19181-7. DOI: 10.48001/etasmr.2025.19181.
Wang Z, Yuan G, Zhou H, Ma Y, Ma Y, Chen D. Improved YOLOv7 model for insulator defect detection [Preprint]. arXiv:2502.07179 https://arxiv.org/abs/2502.07179.
Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88. DOI: https://doi.org/10.1016/j.media.2017.07.005.
Wijaya, R.S., Santonius, S., Wibisana, A., Jamzuri, E.R. and Nugroho, M.A.B., 2024. Comparative Study of YOLOv5, YOLOv7 and YOLOv8 for Robust Outdoor Detection. Journal of Applied Electrical Engineering, 8(1), pp.37-43.
Wang X, Gao H, Jia Z, Li Z. BL-YOLOv8: An improved road defect detection model based on YOLOv8. Sensors. 2023 Oct 10;23(20):8361.
Cao L, Zheng X, Fang L. The semantic segmentation of standing tree images based on the Yolo V7 deep learning algorithm. Electronics. 2023 Feb 13;12(4):929
Wang C, Bochkovskiy A, Liao HYM. Scaled-YOLOv4: Scaling cross stage partial network. arXiv. 2021. Available from: https://arxiv.org/abs/2011.08036. DOI: 10.48550/arXiv.2011.08036.
Li C, Li L, Jiang H, et al. YOLOv6: A single-stage object detection framework for industrial applications. arXiv. 2022. Available from: https://arxiv.org/abs/2209.02976. DOI: 10.48550/arXiv.2209.02976.
Downloads
Published
How to Cite
License
Copyright (c) 2025 Scientific Journal of University of Benghazi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
