Real-Time Infrared Small Target Detection Based on 1-D Bidirectional Vector Feature Measure in a Novel SRD Mode for Complex Scenes

Real-time infrared (IR) small target detection is of great significance for practical engineering projects. The existing algorithms mainly focus on single-frame detection (SFD) and multiframe detection (MFD), which have a certain degree of latency. This letter proposes a novel single-row detection (SRD) method based on 1-D bidirectional vector feature measure (1BVFM). A 1-D bidirectional vector (1BV) model is defined, and based on this, a 1BV contrast (1BVC) operator is established to suppress the background. At the same time, a 1BV gradient (1BVG) operator is established to enhance the target. By integrating 1BVC and 1BVG, the background suppression effect is enhanced and the target saliency is improved. The experimental results show that the algorithm proposed in this letter has certain advantages. It is a robust IR small target detection method that can be used for optoelectronic detection equipment.