Multi-target trajectory anomaly processing method and system in micro-manipulation

Abstract

The invention relates to a multi-target trajectory anomaly processing method and system in micro-manipulation. The method comprises the following steps: acquiring detection information of a (k-1)th frame of image of object movement, and performing Kalman filtering initialization on the detection information of the (k-1)th frame of image; predicting the detection information of the kth frame of image according to the detection information of the (k-1)th frame of image; performing target association on each element of the detection sequence in the kth frame of image detection information and the Kalman filter of each target by using a Hungary algorithm to obtain matching information, the matching information including correct matching information and wrong matching information; according to the correct matching information, performing Kalman filtering updating on the successfully matched target to obtain the optimal state estimation information of the target; obtaining missing detection information and new target appearance information; and carrying out abnormal condition processing on the target according to the missing detection information, the new target appearance information and the error matching information. The track association success rate of a missing target can be improved, and the processing efficiency of an abnormal condition is improved.

Description

technical field [0001] The invention relates to the field of moving object tracking processing, in particular to a method and system for processing abnormality of multi-target tracks in micromanipulation. Background technique [0002] Visual tracking is a standard procedure for studying the function of model organisms, especially for the study of the function of model organisms after manipulation of the micromanipulator. After the micromanipulation is completed, the visual detection system detects the movement information of the target in each frame of the continuous video, such as position, body part orientation, etc., and generates trajectories based on these detection information for further analysis to study the physiological functions and microscopic properties of organisms. Operating effect. The system is widely used in many disciplines, such as genetics, drug development, toxicology testing, behavioral research, etc. The traditional manual marking method has high ti...

AI Technical Summary

Problems solved by technology

The traditional manual marking method has high time cost and low efficiency, and the detection results of existing automatic detection algorithms are often accompanied by noise and error information, such as limited field of view, target crossing caused by detection algorithms missing targets, etc., which may easily cause generated Trajectory error, which has a large negative impact on the research results

For example: as a typical model organism, zebrafish juveniles have a large movement uncertainty compared to other model organisms such as mice and fruit flies, which is more likely to cause errors in trajectory generation

After obtaining the detection information of zebrafish larvae, for zebrafish larvae between different frames, it is necessary to perform target recognition and track association. As a result, some zebrafish cannot associate tracks in certain frames, resulting in track matching errors, and this abnormal situation needs to be dealt with

Images