Abstract

Satheesh Kumar D.*, Shanub Hussain K., Srinaveen K., Viswajith J., Yadukrishnan O.

ABSTRACT

These instructions give you guidelines for preparing papers for the Journals of The World Academy of Research in Science and Engineering. Use this document as a template if you are using Microsoft Word 6.0 or later. Otherwise, use this document as an instruction set. Define all symbols used in the abstract. Do not cite references in the abstract. Due to object detection's close relationship with video analysis and image understanding, much research attention has been paid to deep learning-based object detection frameworks in recent years. These frameworks behave differently in network architecture, training strategy and optimization function, etc.A top-down tree structure is used to represent the significance of part elements of a scene image with the effort of data processing. The proposed representation is trained using a network called LSTM (Long Short-Term Memory) network.