A Distributed Automatic Video Annotation Platform

Abstract

In the era of digital devices and the Internet, thousands of videos are taken and share through the Internet. Similarly, CCTV cameras in the digital city produce a large amount of video data that carry essential information. To handle the increased video data and generate knowledge, there is an increasing demand for distributed video annotation. Therefore, in this paper, we propose a novel distributed video annotation platform that explores the spatial information and temporal information. Afterward, we provide higher-level semantic information. The proposed framework is divided into two parts: spatial annotation and spatiotemporal annotation. Therefore, we propose a spatiotemporal descriptor, namely, volume local directional ternary pattern-three orthogonal planes (VLDTP–TOP) in a distributed manner using Spark. Moreover, we developed several state-of-the-art appearance-based and spatiotemporal-based feature descriptors on top of Spark. We also provide the distributed video annotation services for the end-users so that they can easily use the video annotation and APIs for development to produce new video annotation algorithms. Due to the lack of a spatiotemporal video annotation dataset that provides ground truth for both spatial and temporal information, we introduce a video annotation dataset, namely, STAD which provides ground truth for spatial and temporal information. An extensive experimental analysis was performed in order to validate the performance and scalability of the proposed feature descriptors, which proved the excellence of our proposed approach.

A Survey on Sports Video Annotation Frameworks

“…Sports video annotation is still considered as hot research area among researchers due to its knowledge generating capabilities [14] and commercial value [11]. It conveys additional useful information for all kinds of videos [12].…”

“…Design of conventional or small scale framework for large scale dataset is becoming impractical [6]. The motive of video annotation and its framework is to relate the video features (low-level) and semantic labels (high-level) [3,13,14]. Moreover the framework should define semantic meaning of objects, events and context [8].…”

“…Getahun and Birara [8] used audio element of scenes to assist identification of object and event using high level architecture. Islam et al [14] highlighted the importance of distributed framework for AVA. The concept is spatio and spatio-temporal oriented that provides application based solution for users.…”

Study of Various Types of Data Annotation

“…Annotating or labeling a still image automatically has been an active area of research that acts as an antecedent to annotating a video clip in many ways [15]. It may be considered that labeling a video as the process of diminishing or minimizing the gap between low-level features with a high-level semantics [16].…”