Infrared Image Captioning with Wearable Device

Wearable devices have garnered widespread attention as a mobile solution, and various intelligent modules based on wearable devices are increasingly being integrated. Additionally, image captioning is an important task in computer vision that maps images to text. Existing image captioning achievements are based on high-quality visible images. However, higher target complexity and insufficient light can lead to reduced captioning performance and mistakes. In this paper, we present an infrared image captioning framework designed to solve the problem of invalid visible image captioning in special conditions. Remarkably, we integrate the infrared image captioning model into the wearable device. Volunteers perform offline and real-time environmental analysis tasks in the real world to evaluate the framework's effectiveness in multiple scenarios. The results indicate that both the accuracy of infrared image captioning and the feedback from wearable device users are promising.

Authors

• Chenjun Gao
• Yanzhi Dong
• Xiaohu Yuan
• Yifei Han
• Huaping Liu

Keywords

• Performance evaluation
• Computer vision
• Automation
• Fuses
• Wearable computers
• Real-time systems
• Generators
• Wearable Devices
• Image Captioning
• Visible Images
• Real-world Tasks
• Real-time Tasks
• Deep Learning
• Visible Light
• Convolutional Neural Network
• Visual Impairment
• Image Features
• Validation Set
• Infrared Imaging
• Excellent Stability
• Recurrent Neural Network
• Environmental Awareness
• Color Word
• Color Channels
• Light Pollution
• Outdoor Scenes
• Field Of Image Processing
• Visually Impaired People
• MS COCO Dataset
• List Of Stop Words
• Visible Light Images
• Cycle Consistency Loss
• Active Task