This paper presents AdaMask, a machine-centric video streaming framework for remote deep neural network (DNN) inference. The objective is to optimize the accuracy of …
M Wigness, T Abdelzaher, S Russell… - IoT for Defense and …, 2022 - Wiley Online Library
The internet of battlefield things (IoBT) is expected to be a major feature of future tactical wireless networks. Multiple challenges arise from the expected scale, heterogeneity …
On-board computing capacity remains a key bottleneck in modern machine inference pipelines that run on embedded hardware, such as aboard autonomous drones or cars. To …
This paper explores criticality-based real-time scheduling of neural-network-based machine inference pipelines in cyber-physical systems (CPS) to mitigate the effect of algorithmic …
F Restuccia, A Biondi - 2021 IEEE Real-Time Systems …, 2021 - ieeexplore.ieee.org
This work focuses on the time-predictable execution of Deep Neural Networks (DNNs) accelerated on FPGA System-on-Chips (SoCs). The modern DPU accelerator by Xilinx is …
This paper presents a self-cueing real-time frame-work for attention prioritization in AI- enabled visual perception systems that minimizes a notion of state uncertainty. By attention …
The ubiquity of smartphone cameras and IoT cameras, together with the recent boom of deep learning and deep neural networks, proliferate various computer vision driven mobile …
S Liu, T Wang, H Guo, X Fu, P David… - 2022 IEEE 42nd …, 2022 - ieeexplore.ieee.org
This paper presents a real-time multi-view scheduling framework for DNN-based live video analytics at the edge to minimize frame processing latency. The work is motivated by …
Perception of obstacles remains a critical safety concern for autonomous vehicles. Real- world collisions have shown that the autonomy faults leading to fatal collisions originate from …