| Title | Enabling Adaptive Deep Neural Networks for Video Surveillance in Distributed Edge Clouds |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Wu, Qiong, Zhang, Haitao, Du, Peilun, Li, Ye, Guo, Jianli, He, Chenze |
| Conference Name | 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS) |
| Date Published | dec |
| Keywords | adaptive deep neural networks, adaptive DNN model selection method, cloud computing, Computation offloading, computational complexity, computing delay, deep neural networks, distributed edge clouds, edge computing, feature extraction, feature similarity, graph theory, Human Behavior, image segmentation, input video segment, intelligent video surveillance task scheduling problem, learning (artificial intelligence), Metrics, network cameras, network delay, neural nets, NP-hard, pubcrawl, remote clouds, Resiliency, resource allocation, scheduling, task scheduling, two-stage delay-aware graph searching approach, video signal processing, video surveillance |
| Abstract | In the field of video surveillance, the demands of intelligent video analysis services based on Deep Neural Networks (DNNs) have grown rapidly. Although most existing studies focus on the performance of DNNs pre-deployed at remote clouds, the network delay caused by computation offloading from network cameras to remote clouds is usually long and sometimes unbearable. Edge computing can enable rich services and applications in close proximity to the network cameras. However, owing to the limited computing resources of distributed edge clouds, it is challenging to satisfy low latency and high accuracy requirements for all users, especially when the number of users surges. To address this challenge, we first formulate the intelligent video surveillance task scheduling problem that minimizes the average response time while meeting the performance requirements of tasks and prove that it is NP-hard. Second, we present an adaptive DNN model selection method to identify the most effective DNN model for each task by comparing the feature similarity between the input video segment and pre-stored training videos. Third, we propose a two-stage delay-aware graph searching approach that presents a beneficial trade-off between network delay and computing delay. Experimental results demonstrate the efficiency of our approach. |
| DOI | 10.1109/ICPADS47876.2019.00080 |
| Citation Key | wu_enabling_2019 |
Enabling Adaptive Deep Neural Networks for Video Surveillance in Distributed Edge Clouds