Abstract
Continuous video analytics requires accurate localization at low latency within embedded power budgets. This paper presents a hardware-software design methodology that reuses codec motion vectors (MVs) between detector invocations. Two alternative models support translation and scale changes: analytical motion-vector propagation (Analytical-MV) and learned propagation using a convolutional neural network (CNN) (CNN-MV). The learned model uses convolutional operations and independent object updates suited to parallel execution on an edge graphics processing unit (GPU). Analytical-MV combines a harmonic-mean precision-recall score (F1) of 0.909 with a mean end-to-end latency of 9.03 ms and an energy consumption of 0.177 J per frame, yielding the lowest latency and energy among the evaluated configurations. Relative to detection on every frame, it reduces mean latency by 25.9% and energy per frame by 36.4%. CNN-MV offers a different trade-off: its fastest configuration raises recall from 0.871 for Analytical-MV to 0.890 and lowers mean power from 19.64 to 17.32 W, while achieving a latency of 18.42 ms and an energy consumption of 0.319 J per frame. It is therefore useful when recall or operating power is more important than minimum latency and energy. Execution on a deep learning accelerator (DLA) further reduces time-averaged GPU utilization relative to GPU execution. Host-processing optimization substantially improves both latency and energy, demonstrating the value of jointly designing temporal models and their execution pipelines.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Majeed, A. A., Meribout, M., & Joseph, N. (2026). Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection. https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection
MLA 9
Majeed, Ashiyana Abdul, et al. "Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection." https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection.
Chicago (author–date)
Majeed, Ashiyana Abdul, Mahmoud Meribout, and Neethu Joseph. 2026. "Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection." https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection.
Harvard
Majeed, A. A., Meribout, M. and Joseph, N. (2026) 'Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection', Available at: https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection.
Vancouver
Majeed AA, Meribout M, Joseph N. Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection. https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection
IEEE
A. A. Majeed, M. Meribout, and N. Joseph, "Analytical and Convolutional Neural Network-Based Motion-Vector Propagation for Efficient Video Object Detection," https://omanscience.com/en/articles/analytical-and-convolutional-neural-network-based-motion-vector-propagation-for-efficient-video-object-detection.