Explore Hybrid Modeling for Moving Infrared Small Target Detection
Abstract: Moving infrared small target detection, crucial in contexts like traffic management and maritime rescue, encounters challenges from factors such as complex backgrounds, target occlusion, camera shake, and motion blur. Existing algorithms fall short in comprehensively addressing these issues by finding mathematical models, impeding generalization in complex and dynamic motion scenes. In this paper, we propose a method for finding models of moving infrared small target detection via smoothed-particle hydrodynamics (SPH) and Markov decision processes (MDP). SPH can simulate the motion trajectories of targets and background scenes, while MDP can optimize detection system strategies for optimal action selection based on contexts and target states. Specifically, we develop an SPH-inspired image-level enhancement algorithm which models the image sequence of infrared video as a 3D spatiotemporal graph in SPH. In addition, we design an MDP-guided temporal feature perception module. This module selects reference frames, aggregates features from both reference frames and the current frame. The previous and current frames are modeled as an MDP tailored for multi-frame infrared small target detection tasks, aiding in detecting the current frame. Conducted extensive experiments on two public dataset: DAUB and DATR, the proposed STME-Net surpasses the state-of-the-art methods in terms of objective metrics and visual quality.
Primary Subject Area: [Experience] Multimedia Applications
Relevance To Conference: Visible images may struggle to detect objects in low-light conditions or complex scenes, but infrared images, as an alternative modality to visible imaging, offer a solution to these challenges. By studying infrared small target detection, it can be applied to multimodal fields such as visible light images, videos, etc. Recent conferences have witnessed abundant research in the domain of infrared small target detection [1,2,3,4].
1.Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement. ACM MM2023
2.DANet: Multi-scale UAV Target Detection with Dynamic Feature Perception and Scale-aware Knowledge Distillation. ACM MM2023
3.Exploring Feature Compensation and Cross-level Correlation for Infrared Small Target Detection. ACM MM 2022
4.RKformer: Runge-Kutta Transformer with Random-Connection Attention for Infrared Small Target Detection. ACM MM 2022
Submission Number: 790
Loading