Self-Cueing Real-Time Attention Scheduling in Criticality-Aware Visual Machine Perception
Self-Cueing Real-Time Attention Scheduling in Criticality-Aware Visual Machine Perception
复制标题
DOI：
10.1109/rtas54340.2022.00022
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Shengzhong Liu;Xinzhe Fu;Maggie B. Wigness;P. David;Shuochao Yao;L. Sha;T. Abdelzaher
中科院分区：
文献类型：
--
作者：
Shengzhong Liu;Xinzhe Fu;Maggie B. Wigness;P. David;Shuochao Yao;L. Sha;T. Abdelzaher
本文提出了一种自提示的实时框架，用于在人工智能视觉感知系统中进行注意力优先级排序，最大限度地减少状态不确定性的概念。注意力优先级是指以关键意识的方式在其他部分之前检查场景的某些部分。通过自我提示，我们指的是不需要外部提示传感器来优先考虑注意力，从而简化设计。我们表明，注意力优先级可以节省资源，从而使资源有限的嵌入式平台上更有效和响应的实时对象跟踪。该系统由两个组件组成：首先，基于光流的模块决定要在子帧级别上查看的区域以及它们的关键性。其次，一种新的批量比例平衡（BPB）调度策略决定如何调度这些区域以供深度神经网络（DNN）检查，以及如何在GPU上并行执行。我们在NVIDIA Jetson Xavier平台上实现了该系统，并通过使用真实驾驶数据集的广泛评估，以经验证明了所提出的架构的优越性。
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 prioritization we refer to inspecting some parts of the scene before others in a criticality-aware fashion. By self-cueing, we refer to not needing external cueing sensors for prioritizing attention, thereby simplifying design. We show that attention prioritization saves resources, thus enabling more efficient and responsive real-time object tracking on resource-limited embedded platforms. The system consists of two components: First, an optical flow-based module decides on the regions to be viewed on a subframe level, as well as their criticality. Second, a novel batched proportional balancing (BPB) scheduling policy decides how to schedule these regions for inspection by a deep neural network (DNN), and how to parallelize execution on the GPU. We implement the system on an NVIDIA Jetson Xavier platform, and empirically demonstrate the superiority of the proposed architecture through an extensive evaluation using a real-word driving dataset.