Ship target detecting and tracking method based on bridge collision avoidance

Abstract

The invention discloses a ship target detection and tracking method based on bridge collision avoidance, and the method comprises the following steps: collecting a video image of a ship through a camera, extracting ship features in the video image through a deep learning training model, and obtaining a ship type and a ship position frame; then according to the ship position frame measured in the step A, continuously detecting the current position of the ship through an IOU method, iterating the current position of the ship with the ship position of the previous frame, and obtaining the continuous position information of the ship in the moving process; and according to the continuously identified ship position information, depicting the motion track of the ship. According to the method, the position coordinates of the ships in the video image can be detected in real time, the ships are numbered and tracked independently, the problems of target loss and missing detection in the detection process are avoided, and the method has the advantages of being good in recognition effect and high in anti-interference capacity.

Description

technical field [0001] The invention relates to a ship detection method, in particular to a ship target detection and tracking method based on bridge anti-collision. Background technique [0002] In order to realize the bridge anti-collision function, it is often necessary to set up a ship detection mechanism at the bridge position. The ship detection mechanism is used to detect the current position of the ship. When the ship is close to the bridge position and there is a risk of colliding with the bridge, an alarm and Information collection, thereby reducing the possibility of ship collision and facilitating the tracing after the accident. At present, the commonly used ship detection technologies are mostly radar ultrasonic, infrared laser technology, and video image detection technology. Among them, video image detection technology has been more and more widely used because of its low detection cost and simple use compared with other technologies. application. [0003] T...

AI Technical Summary

Problems solved by technology

However, this differential method is easily affected by external conditions such as light and weather, and the recognition effect on slow-moving or stationary objects is poor, so it is prone to loss of tracking targets and missing detection problems.

[0004] In addition, the video image detection technology is also susceptible to interference items during the detection process. For example, when two ships appear in the detection range at the same time and

Images