Dynamic Fusion Network for RGBT Tracking

09/16/2021
by   Jingchao Peng, et al.
0

For both visible and infrared images have their own advantages and disadvantages, RGBT tracking has attracted more and more attention. The key points of RGBT tracking lie in feature extraction and feature fusion of visible and infrared images. Current RGBT tracking methods mostly pay attention to both individual features (features extracted from images of a single camera) and common features (features extracted and fused from an RGB camera and a thermal camera), while pay less attention to the different and dynamic contributions of individual features and common features for different sequences of registered image pairs. This paper proposes a novel RGBT tracking method, called Dynamic Fusion Network (DFNet), which adopts a two-stream structure, in which two non-shared convolution kernels are employed in each layer to extract individual features. Besides, DFNet has shared convolution kernels for each layer to extract common features. Non-shared convolution kernels and shared convolution kernels are adaptively weighted and summed according to different image pairs, so that DFNet can deal with different contributions for different sequences. DFNet has a fast speed, which is 28.658 FPS. The experimental results show that when DFNet only increases the Mult-Adds of 0.02 non-shared-convolution-kernel-based fusion method, Precision Rate (PR) and Success Rate (SR) reach 88.1

READ FULL TEXT
research
03/12/2021

Siamese Infrared and Visible Light Fusion Network for RGB-T Tracking

Due to the different photosensitive properties of infrared and visible l...
research
04/09/2023

RGB-T Tracking Based on Mixed Attention

RGB-T tracking involves the use of images from both visible and thermal ...
research
01/26/2022

A Joint Convolution Auto-encoder Network for Infrared and Visible Image Fusion

Background: Leaning redundant and complementary relationships is a criti...
research
01/21/2022

Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking

We address the problem of multi-modal object tracking in video and explo...
research
02/04/2019

End-to-end feature fusion siamese network for adaptive visual tracking

According to observations, different visual objects have different salie...
research
08/25/2023

Fusion of Infrared and Visible Images based on Spatial-Channel Attentional Mechanism

In the study, we present AMFusionNet, an innovative approach to infrared...
research
03/18/2022

Towards Robust 2D Convolution for Reliable Visual Recognition

2D convolution (Conv2d), which is responsible for extracting features fr...

Please sign up or login with your details

Forgot password? Click here to reset