Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
复制标题
DOI：
10.1109/islped52811.2021.9502480
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Abhinav Goel;Caleb Tung;Xiao Hu;Haobo Wang;James C. Davis;G. Thiruvathukal;Yung-Hsiang Lu
中科院分区：
文献类型：
--
作者：
Abhinav Goel;Caleb Tung;Xiao Hu;Haobo Wang;James C. Davis;G. Thiruvathukal;Yung-Hsiang Lu
低功耗计算机视觉在嵌入式设备上有很多应用。描述了一种用于对象重新识别(ReID)问题的低功耗技术：将查询图像与先前见过的图像库进行匹配。最先进的技术依赖于大型、计算密集型的深度神经网络(DNN)。我们提出了一种新的分层DNN结构，该结构利用训练数据集中的属性标签来执行有效的对象Reid。在层次结构中的每个节点，一个小的DNN标识查询图像的不同属性。每个叶节点处的小DNN被专门化以重新标识图库的子集-仅具有沿从根到叶的路径标识的属性的图像。因此，在用几个小的DNN处理之后，查询图像被准确地重新识别。我们将我们的方法与最先进的对象Reid技术进行了比较。在精确度损失$\sim\$的情况下，我们的方法实现了显著的资源节约：内存减少74%，操作减少72%，查询延迟减少67%，能源消耗减少65%。
Low-power computer vision on embedded devices has many applications. This paper describes a low-power technique for the object re-identification (reID) problem: matching a query image against a gallery of previously-seen images. State-of-the-art techniques rely on large, computationally-intensive Deep Neural Networks (DNNs). We propose a novel hierarchical DNN architecture that uses attribute labels in the training dataset to perform efficient object reID. At each node in the hierarchy, a small DNN identifies a different attribute of the query image. The small DNN at each leaf node is specialized to re-identify a subset of the gallery-only the images with the attributes identified along the path from the root to a leaf. Thus, a query image is re-identified accurately after processing with a few small DNNs. We compare our method with state-of-the-art object reID techniques. With a $\sim 4\%$ loss in accuracy, our approach realizes significant resource savings: 74% less memory, 72% fewer operations, and 67% lower query latency, yielding 65% less energy consumption.