• ETRI Journal
• /
• v.38 no.4
• /
• pp.767-775
• /
• 2016

Automatic container code recognition from a captured image is used for tracking and monitoring containers, but often fails when the code is not captured clearly. In this paper, we increase the accuracy of container code recognition using multiple views. A character-level integration method combines recognized codes from different single views to generate a new code. A decision-level integration selects the most probable results from the codes from single views and the new integrated code. The experiment confirmed that the proposed integration works successfully. The recognition from single views achieved an accuracy of around 70% for the test images collected on a working pier, whereas the proposed integration method showed an accuracy of 96%.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.201-208
• /
• 2009

As the ubiquitous environment is created, the latest ports introduce U-Port services in managing ports generally and embody container's location identification system, port terminal management system, and advanced information exchange system etc. In particular, the location identification system for freight cars and containers provide in real time the information on the location and condition for them, and enables them to cope with an efficient vehicle operation management and its related problems immediately. However, such a system is insufficient in effectively handling with the troubles in a large-scale port including freight car's disorderly driving, parking, stop, theft, damage, accident, trespassing and controlling. In order to solve these problems, this study structures the vehicle positioning system and the image verification system unsing high resolution image compression and AVE/H.264 store and transmission technology, able to mark and identify the vehicle location on the digital map while a freight car has stayed in a port since the entry of an automatic gate, or able to identify the place of accident through image remotely.