CURRENT STATE OF OBJECT CLASSIFICATION METHODS ON RESOURCE-CONSTRAINED PLATFORMS.
Keywords:
object classification, resource-constrained platforms, embedded systems, CNN, edge AI.Abstract
This article presents an analysis of the current state of object classification methods on resource-constrained computing platforms based on established scientific literature. Systems operating in embedded and edge computing environments are subject to strict limitations in terms of computational power, memory capacity, and energy consumption, which impose high requirements on object classification algorithms. The paper reviews both traditional and deep learning–based approaches to object classification, with particular attention to lightweight neural network architectures such as MobileNet, EfficientNet, and ShuffleNet. The analysis is conducted exclusively on the basis of peer-reviewed scientific articles and authoritative textbooks.
References
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Szeliski, R. (2022). Computer Vision: Algorithms and Applications. Springer.
Dalal, N., & Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. CVPR.
Lowe, D. G. (2004). Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision (IJCV).
Howard, A., et al. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861.
Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ICML.
Zhang, X., et al. (2018). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. CVPR.
Han, S., Mao, H., & Dally, W. (2016). Deep Compression: Compressing Deep Neural Networks. ICLR.
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal.
