Method for detecting moving target region aiming at underwater microscopic video

Abstract

The invention discloses a method for detecting a moving target region aiming at underwater microscopic video. The method comprises the following steps of: (1) acquiring the microscopic video, and generating scale invariant feature transform (SIFT) characteristic point vectors; (2) reducing the dimensions of the SIFT characteristic point vectors; (3) establishing an initialized hybrid Gaussian background model; and (4) matching the SIFT characteristic point low-dimensional vectors one by one, updating the hybrid Gaussian background model, and segmenting a foreground region from an image. According to the method, the SIFT characteristic point vectors of the video image are generated by using an SIFT algorithm, the background model in an SIFT characteristic point vector region is established through the hybrid Gaussian model, and target organisms in the video image are segmented by using the background model and the current video and adopting a background matching algorithm based on the SIFT characteristic point vector region, so that interference of movement of non-target objects to the detection can be effectively eliminated, and the detection accuracy of the target organisms is improved.

Description

technical field [0001] The invention belongs to the technical field of video image processing, and in particular relates to a moving target area detection method for underwater microscopic video. Background technique [0002] The underwater intelligent biometric identification system can automatically find the target organism by using the microscopic video image, and complete the tasks of identification and tracking of the target organism. The key technology is the detection of the moving target organism. As an important part of moving target recognition, motion detection refers to extracting the changing area (possibly the target creature) in the video from the background image. However, due to the influence of illumination, shadow and chaotic interference, the background image changes dynamically, which makes the accurate detection of target organisms a very difficult task. [0003] At present, the commonly used target detection methods are Temporal Difference, Optical Fl...

AI Technical Summary

Problems solved by technology

However, for underwater microscopic videos, in addition to the influence of lighting conditions caused by water surface fluctuations, there are also a large number of non-target objects in the background, such as sediment particles, biological debris or debris, underwater biological excrement, etc. These non-target objects Floating aimlessly in the water due to the influence of the current

Using the traditional mixed Gaussian model background modeling method, these non-target objects floating in the background will also be segmented into target organisms, which will greatly interfere with subsequent target biometric recognition

Images