Real-time target tracking and detection method and system based on full convolution neural network

Abstract

The invention discloses a real-time target tracking detection method and system based on a full convolution neural network. The method comprises the following steps: S1, carrying out data enhancementprocessing to obtain a training sample; S2, combining the training sample and the target segmentation map corresponding to the first frame with the color channel dimension; 3, combining that target segmentation map corresponding to the second frame of the train sample and the transposed map in the color channel dimension; S4, constructing a full convolution countermeasure neural network, which iscomposed of a full convolution network and a discriminator network; S5, training a discriminator to judge whether the partition graph is the forged data or the real data generated by the full convolution network; 6, calculating a loss value 1 and a loss value 2 by using cross entropy between that partition map and its tag; S7, the steps S5 and S6 are alternated until the full convolution network generates an artificially drawn target partition map that is as close to the reality as possible. The invention relies on less data, fast operation speed and instantaneity, and can track the object inthe video at the same time of video shooting.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and relates to a real-time target tracking and detection method and system based on a fully convolutional neural network. Background technique [0002] Object tracking and detection has always been the focus of research in the field of image and video detection. It plays an important role in traffic image processing, crux tracking on medical images, and special video processing (such as mosaicing). [0003] Commonly used object tracking and detection methods include Struck, SCM, ASLA, KCF, TLD, and DCF, etc., but these methods have many shortcomings, such as low recognition accuracy for some, and only for specific categories of objects. When it is necessary to identify new When it comes to object types, the algorithm needs to be rewritten, which makes its development cycle longer, and most current filtering detection-based algorithms cannot achieve high semantic segmentation accuracy. [0...

AI Technical Summary

Problems solved by technology

[0003] Commonly used object tracking and detection methods include Struck, SCM, ASLA, KCF, TLD, and DCF, etc., but these methods have many shortcomings, such as low recognition accuracy for some, and only for specific categories of objects. When it is necessary to identify new For different types of objects, the algorithm needs to be rewritten, which makes its development cycle longer, and most current algorithms based on filter detection cannot achieve high semantic segmentation accuracy

[0004] In recent years, target tracking and detection algorithms based on deep learning have emerged. Although these algorithms have higher performance, they also have slow computing speed, difficult training, and strict requirements on the size of the input image.

In practical applications, there is often a need for multi-target detection. The general method can only track a single target. When multi-target tracking is required, it is necessary to use multi-thread synchronization to track each unit separately, or introduce other methods. Computing speed has a very bad effect

Images