Training and visible light infrared visual tracking method based on adapter mutual learning model

A technology for learning models and training methods, applied in the field of computer vision, can solve the problems of insufficient modal fusion in the RGBT tracking method, and achieve the effects of overcoming parameter redundancy, suppressing noise, and improving tracking performance.

Active Publication Date: 2020-03-10
ANHUI UNIVERSITY
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide training based on the adapter mutual learning model an

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Training and visible light infrared visual tracking method based on adapter mutual learning model
  • Training and visible light infrared visual tracking method based on adapter mutual learning model
  • Training and visible light infrared visual tracking method based on adapter mutual learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 , image 3 , Figure 4 , figure 1 It is a flow block diagram of Embodiment 1 of the present invention; image 3 It is a flowchart of the network model in the present invention; Figure 4 It is a flow chart of the adapter mutual learning module in the present invention; the training process based on the adapter mutual learning model includes the following steps;

[0056] S11. Build a network model; the network model is composed of multi-level adapter modules, Concatnate functions, and instance adapters connected in series in sequence. The multi-level adapter modules output feature maps of different modalities and obtain a whole by splicing the Concatnate function according to the channel dimension. The feature map is passed to the instance adapter for calculation;

[0057] image 3 It is a flow chart of the adapter mutual learning module in the present invention; as image 3 , in this embodiment, the multi-level adapter modules are respectively co...

Embodiment 2

[0084] Such as figure 2 , image 3 and Figure 4 , figure 2 It is a flow block diagram of Embodiment 2 of the present invention; image 3 It is a flowchart of the network model in the present invention; Figure 4 It is a flow chart of the adapter mutual learning module in the present invention; the visible light infrared vision tracking method based on the adapter mutual learning model comprises the following steps:

[0085] S21. Input the currently tracked video frame, and use Gaussian sampling to obtain candidate samples of the current frame around the target position predicted in the previous frame;

[0086] The first frame image provided by the tracking video sequence is used as the previous frame; from the previous frame and the truth box that frames the target location area, several samples are randomly generated according to the Gaussian distribution, and several iterations of training are performed to complete the network model initialization.

[0087] Specific...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a training and visible light infrared visual tracking method based on an adapter mutual learning model. The method comprises the following steps: S11, constructing a network model; S12, training the whole network model by using the manually labeled visible light thermal infrared data set; S21, obtaining a candidate sample of the current frame; S22, predicting a target position according to the candidate sample; and S23, judging whether the current frame is tracked successfully or not. According to the invention, an adapter mutual learning module is introduced on the basis of multiple adapters (including a mode adapter, a general adapter and an instance adapter) to realize bidirectional cross-modal information transmission, so that the complementary advantages of different feature learning modes in RGBT tracking are fully utilized to further improve the traceability.

Description

technical field [0001] This application relates to the field of computer vision, in particular to the training of adapter-based mutual learning models and the visible light infrared vision tracking method. Background technique [0002] Object tracking is a hot issue in the field of computer vision; object tracking is also one of the key technologies for unmanned driving, intelligent transportation and intelligent monitoring. [0003] The current method based on detection and tracking is mainly to train a binary classifier, which can effectively distinguish the background and the foreground. First, set a specific threshold under the condition of the bounding box (bounding box) of the first frame in the video sequence. To determine the positive and negative samples; in the subsequent frames of the video, Gaussian sampling is still performed near the predicted result of the previous frame, and the obtained samples are classified into positive and negative samples. The highest s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/20G06K9/62G06N3/04
CPCG06V10/143G06V2201/07G06N3/048G06N3/045G06F18/253G06F18/214
Inventor 李成龙钱存鹿安东汤进
Owner ANHUI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap