Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection

11/19/2018
by   Ziqi Zhou, et al.
0

The existing still-static deep learning based saliency researches do not consider the weighting and highlighting of extracted features from different layers, all features contribute equally to the final saliency decision-making. Such methods always evenly detect all "potentially significant regions" and unable to highlight the key salient object, resulting in detection failure of dynamic scenes. In this paper, based on the fact that salient areas in videos are relatively small and concentrated, we propose a key salient object re-augmentation method (KSORA) using top-down semantic knowledge and bottom-up feature guidance to improve detection accuracy in video scenes. KSORA includes two sub-modules (WFE and KOS): WFE processes local salient feature selection using bottom-up strategy, while KOS ranks each object in global fashion by top-down statistical knowledge, and chooses the most critical object area for local enhancement. The proposed KSORA can not only strengthen the saliency value of the local key salient object but also ensure global saliency consistency. Results on three benchmark datasets suggest that our model has the capability of improving the detection accuracy on complex scenes. The significant performance of KSORA, with a speed of 17FPS on modern GPUs, has been verified by comparisons with other ten state-of-the-art algorithms.

READ FULL TEXT

page 1

page 3

page 7

research
10/16/2018

Salient Object Detection in Video using Deep Non-Local Neural Networks

Detection of salient objects in image and video is of great importance i...
research
12/08/2014

What is a salient object? A dataset and a baseline model for salient object detection

Salient object detection or salient region detection models, diverging f...
research
02/02/2017

Video Salient Object Detection via Fully Convolutional Networks

This paper proposes a deep learning model to efficiently detect salient ...
research
12/08/2019

SaLite : A light-weight model for salient object detection

Salient object detection is a prevalent computer vision task that has ap...
research
05/07/2021

Salient Objects in Clutter

This paper identifies and addresses a serious design bias of existing sa...
research
01/22/2020

A Fixation-based 360° Benchmark Dataset for Salient Object Detection

Fixation prediction (FP) in panoramic contents has been widely investiga...
research
03/08/2022

Semantic Distillation Guided Salient Object Detection

Most existing CNN-based salient object detection methods can identify lo...

Please sign up or login with your details

Forgot password? Click here to reset