Deep Learning Hyper-Parameter Optimization for Video Analytics in Clouds

A system to perform video analytics is proposed using a dynamically tuned convolutional network. Videos are fetched from cloud storage, preprocessed, and a model for supporting classification is developed on these video streams using cloud-based infrastructure. A key focus in this paper is on tuning hyper-parameters associated with the deep learning algorithm used to construct the model. We further propose an automatic video object classification pipeline to validate the system. The mathematical model used to support hyper-parameter tuning improves performance of the proposed pipeline, and outcomes of various parameters on system's performance is compared. Subsequently, the parameters that contribute toward the most optimal performance are selected for the video object classification pipeline. Our experiment-based validation reveals an accuracy and precision of 97% and 96%, respectively. The system proved to be scalable, robust, and customizable for a variety of different applications.

I. Introduction

Video analytics plays a vital role in detecting and tracking temporal and spatial events in video streams. A number of preinstalled cameras, as shown in Fig. 1, produces video data. This data needs processing to generate useful clusters such as classification and tracking of a marked person. As shown in Fig. 2, video data captured from different cameras can be used to locate a person of interest. The mapping of the person is then associated with particular locations visited along with the time spent at each location. The large amounts of data makes it nearly impossible for human operators to manually process this data. Fig. 1.

Video capture infrastructure.

Fig. 2.

Mapping of marked person.