Quantized Object Detection for Real-Time Inference on Embedded GPU Architectures

Deploying deep learning-based object detection models like YOLOv4 on resource-constrained embedded ar-chitectures presents several challenges, particularly regarding computing performance, memory usage, and energy consumption. This study examines the quantization of the YOLOv4 model to facilitate real-time inference on lightweight edge devices, focusing on NVIDIA’s Jetson Nano and AGX. We utilize post-training quantization techniques to reduce both model size and computational complexity, all while striving to maintain acceptable detection accuracy. Experimental results indicate that an 8-bit quantized YOLOv4 model can achieve near real-time performance with minimal accuracy loss. This makes it well-suited for embedded applications such as autonomous navigation. Additionally, this research highlights the trade-offs between model compression and detection performance, proposing an optimization method tailored to the hardware constraints of embedded architectures.

@article{Guerrouj2025,
  title     = {Quantized Object Detection for Real-Time Inference on Embedded GPU Architectures},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {16},
  number    = {5},
  year      = {2025},
  publisher = {The Science and Information Organization},
  author    = {Fatima Zahra Guerrouj and Sergio Rodriiguez Florez and Abdelhafid El Ouardi and Mohamed Abouzahir and Mustapha Ramzi},
  doi       = {10.14569/IJACSA.2025.0160503},
  url       = {https://doi.org/10.14569/IJACSA.2025.0160503}
}