Toward Intelligent Surveillance as an Edge Network Service (iSENSE) Using Lightweight Detection and Tracking Algorithms
Toward Intelligent Surveillance as an Edge Network Service (iSENSE) Using Lightweight Detection and Tracking Algorithms
复制标题
使用轻量级检测和跟踪算法实现智能监控作为边缘网络服务 (iSENSE)
DOI：
--
复制
发表时间：
2019
影响因子：
8.1
通讯作者：
Timothy R. Faughnan
中科院分区：
文献类型：
--
作者：
S. Nikouei;Yu Chen;Sejun Song;Baek;Timothy R. Faughnan
边缘计算将信息技术领域扩展到云计算所定义的边界之外。边缘计算在传感器附近执行计算，有望解决许多带宽和延迟敏感应用中的挑战。尽管最近许多基于机器学习（ML）算法的智能视频监控方法已经可用，但将这些智能算法有效地迁移到边缘仍然具有挑战性。在本文中，我们提出了一种智能监控作为边缘网络服务（iSENSE），它通过测试两种流行的人体物体检测方案来探索将ML移动到边缘的可行性。此外，还引入了一个轻量级的卷积神经网络（L-CNN），通过利用深度可分离卷积来提高计算执行。为了提高边缘的性能，我们提出了一种混合轻量级跟踪算法，Kerman（Kernelized Kalman filter），这是一种基于决策树的混合核相关滤波算法，专为人-目标跟踪而设计。我们通过使用不同类型的单板计算机在边缘上实现了Kerman和L-CNN算法。使用真实校园监控视频和开放图像集对所提出的iSENSE系统进行了验证。实验结果表明，在边缘设备资源有限的情况下，本文提出的算法能够对人体目标进行实时跟踪，并具有较好的准确性。
Edge computing extends the realm of information technology beyond the boundaries defined by cloud computing. Performing computation near the sensors, edge computing is promising to address the challenges in many bandwidth-and delay-sensitive applications. Although recently many smart video surveillance approaches based on Machine Learning (ML) algorithms become available, it is still challenging to efficiently migrate those smart algorithms to edge. In this paper, we propose an intelligent Surveillance as an Edge Network Service (iSENSE), which explores the feasibility of moving ML to the edge by testing two popular human-object detection schemes. Besides, a lightweight Convolutional Neural Network (L-CNN) is introduced to improve computational execution by leveraging the depth-wise separable convolution. To enhance performance on edge, we propose a hybrid lightweight tracking algorithm, Kerman (Kernelized Kalman filter), which is a decision tree based hybrid Kernelized Correlation Filter algorithm designed for human-object tracking. We have implemented both Kerman and L-CNN algorithms on edge by using different types of single board computers. The proposed iSENSE system was validated using both real-world campus surveillance video and open image sets. The experimental results present that the proposed algorithms can track the human objects in real-time with a good accuracy with limited resource in edge devices.