A method and system for ship tracking

Abstract

The invention discloses a method and system for ship tracking. The ship tracking operator STMS based on multi-view learning mechanism and sparse representation mechanism makes use of an LoG operator,a HOG operator, an LBP operator, a Canny operator and a Gabor operator to extract ship features respectively, the ship features extracted from STMS ship tracking operator are sparsely expressed by sparse representation mechanism, the STMS model is established to represent the ship tracking targets, and the LASSO penalty mechanism is introduced to balance the tracking accuracy and computational complexity of the STMS model. The tracking performance of the STMS model is optimized by using the Frobenius normal form, and the ship tracking results are obtained by solving the STMS model with the accelerated approximate gradient method. The invention has better abstractness and robustness, can effectively cope with a variety of ship tracking challenges such as illumination change, imaging visualangle change, ship occlusion and ship imaging size change, and has smaller ship tracking error and good tracking effect.

Description

technical field [0001] The invention relates to a ship tracking method and system. Background technique [0002] As a basic task of visual perception of intelligent navigation, ship tracking can help intelligent ships to obtain dynamic information of ships of interest in the navigation environment, help intelligent ships to more accurately judge the risk of collision, and ensure the safe navigation of intelligent ships. [0003] At present, some scholars have achieved the purpose of ship tracking by using traditional image processing techniques. Existing tracking algorithms and models include optical flow method, Kalman tracking algorithm, Camshift and Meanshift, etc., which mainly identify and track targets based on a single feature in image sequences. These algorithms may not be suitable for intelligent navigation application scenarios. Ship tracking. For example, the recognition of a single feature becomes particularly difficult under conditions such as the influence of...

AI Technical Summary

Problems solved by technology

However, Hong et al. pointed out that when the tracking target deforms in the video sequence, the L1 tracking operator cannot obtain the ideal tracking effect.

[0005] Ship tracking for intelligent navigation visual perception tasks mainly faces the following challenges: 1. The tracking algorithm needs to have good robustness, especially under conditions such as illumination changes, bad weather, and different imaging perspectives. effect, and the traditional ship tracking method can not get the ideal tracking effect when faced with the above challenges

2. The ship tracking algorithm based on AIS, radar and other technical means regards the target ship as a particle, but in the ship tracking task for intelligent navigation visual perception, the tracked target ship cannot be regarded as a particle

Images