Water surface target motion detecting method simulating compound eye visual mechanism and polarization imaging

Abstract

The invention discloses a water surface target motion detecting method simulating a compound eye visual mechanism and polarization imaging. The water surface target motion detecting method comprises the three steps of polarization image collecting calculating, bionic target detecting and bionic motion target matching. The bionic method simulating the dragonfly compound eye visual mechanism is adopted to realize water surface target detecting and tracking, and during the calculating process, scene and target information is converted to 'compressive sensing' features with an impulse sequence as formal representation. Later target detecting and target matching tracking are both conducted based on the impulse sequence, multiple targets in a scene are detected, matched and tracked by the utilization of response time sequences of impulses and impulse sequence modes of the impulses, and at last detecting of target motion and estimation of motion vectors of the target motion are realized. The water surface target motion detecting method can be used in water surface target motion detection under a complex water surface optical environment stably and reliably and calculating efficiency is high.

Description

technical field [0001] The invention relates to a motion detection method of a water surface target simulating compound eye vision mechanism and polarization imaging, in particular to a motion imaging measurement method of a water surface target, which belongs to the technical field of computer vision. Background technique [0002] Optical imaging detection and motion parameter estimation of water surface targets such as oceans, lakes, and rivers have been widely used in many fields. At present, the research on optical imaging for water surface target detection mostly focuses on light intensity or spectral information. However, due to the changeable natural and climatic conditions and the variable optical properties of the target, it cannot be considered that the detection of water surface targets based on this optical imaging method is universal and optimal. As a result, some research has gradually turned to other optical properties, the most typical of which is optical po...

AI Technical Summary

Problems solved by technology

However, the high complexity of the background model calculation and the variability of the natural background seriously affect the generalization of the method.

[0004] In comparison, the non-background modeling target detection algorithm does not require a cumbersome modeling process, and sometimes achieves greater success in target detection only based on the information reflected in the water surface image itself, but because there is no support from the background model, so The distinction between background information and target information is the key to this method

Images