Ship identification method based on AIS and video data fusion

An identity recognition and video data technology, applied in the field of ship traffic service system, can solve the problems such as the inability of the pan/tilt camera to rotate and zoom, other moving objects are mistakenly detected as ship targets, and easy to miss the detection of stationary or low-speed ship targets, etc. Wide application prospects and the effect of reducing labor costs
CN109460740AActive Publication Date: 2019-03-12SHANGHAI ADVANCED AVIONICS
8 Cites 25 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
SHANGHAI ADVANCED AVIONICS
Publication Date
2019-03-12

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a ship identification method based on AIS and video data fusion, which comprises the following steps: collecting ship samples and training a ship target classifier; Video frames captured by Pan-tilt camera are detected by ship target classifier. Filter the identified ship by comparing the identified ship depots; Collect AIS data and filter them from time and space; Linear extrapolation is used to estimate the current position of AIS target and convert it to image coordinate system. The matching target is matched with the converted AIS target, and the feature of the matched target is extracted and stored in the identified ship library. The experimental results show that the invention can quickly and accurately extract ship targets in the surveillance video and identify them, effectively reduce the human cost, and has a wide application prospect in the fields of ship traffic, port management and the like.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to an information processing method in the field of Vessel Traffic Service System (VTS), in particular to a vessel identification method based on fusion of AIS and video data. Background technique

[0002] Video surveillance has become an important means of information collection in the fields of ship traffic and port management because of its intuitive, timely, accurate and large amount of information.

[0003] The ship target extraction and identification method in surveillance video can effectively reduce labor costs and improve the intelligence of maritime management, which has extremely high research and application value.

[0004] The feature-based ship rapid identification method disclosed in patent document CN201210543644.6 trains a ship feature-based decision tree classifier through a manually marked ship feature library, and then uses the classifier to detect images in the video. This method can quickly extract the ship...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More