Mathematical study of neural feedback roles in small target motion detection

Abstract

Building an efficient and reliable small target motion detection visual system is challenging for artificial intelligence robotics because a small target only occupies few pixels and hardly displays visual features in images. Biological visual systems that have evolved over millions of years could be ideal templates for designing artificial visual systems. Insects benefit from a class of specialized neurons, called small target motion detectors (STMDs), which endow them with an excellent ability to detect small moving targets against a cluttered dynamic environment. Some bio-inspired models featured in feed-forward information processing architectures have been proposed to imitate the functions of the STMD neurons. However, feedback, a crucial mechanism for visual system regulation, has not been investigated deeply in the STMD-based neural circuits and its roles in small target motion detection remain unclear. In this paper, we propose a time-delay feedback STMD model for small target motion detection in complex backgrounds. The main contributions of this study are as follows. First, a feedback pathway is designed by transmitting information from output-layer neurons to lower-layer interneurons in the STMD pathway and the role of the feedback is analyzed from the view of mathematical analysis. Second, to estimate the feedback constant, the existence and uniqueness of solutions for nonlinear dynamical systems formed by feedback loop are analyzed via Schauder's fixed point theorem and contraction mapping theorem. Finally, an iterative algorithm is designed to solve the nonlinear problem and the performance of the proposed model is tested by experiments. Experimental results demonstrate that the feedback is able to weaken background false positives while maintaining a minor effect on small targets. It outperforms existing STMD-based models regarding the accuracy of fast-moving small target detection in visual clutter. The proposed feedback approach could inspire the relevant modeling of robust motion perception robotics visual systems.

Small target detection with remote sensing images based on an improved YOLOv5 algorithm

“…A squeeze-and-excitation YOLOv3 algorithm has been designed for small target detection in remote sensing images with low computation costs (Zhou et al, 2021). Moreover, Ling et al (2022) have developed a new time-delay feedback model to detect small target motion in complex dynamic backgrounds. An indoor small target detection algorithm is described in Huang L. et al (2022) based on multi-scale feature fusion to improve the accuracy and speed of the target detection.…”

Small object intelligent detection method based on adaptive recursive feature pyramid

“…To solve these problems, the researchers optimize the small object detection method based on various optimization strategies, such as data enhancement [14] , [15] , [16] , [17] , [18] , multi-scale learning [19] , [20] , [21] , [22] , context learning [23] , [24] , [25] , [26] , [27] , and generative confrontation learning [28] , [29] , [30] , [31] , [32] , [33] , [34] , which are analyzed as follows:…”