A New Method of Inland River Overloaded Ship Identification Using Digital Image Processing
With the development of low-carbon economy, inland river transportation has been attracting more and more attention in China. At the same time, driven by some economic benefits, the ship overload phenomenon continues to occur. Therefore, overloaded ship detection has been a key factor for reducing marine traffic accidents. This paper presents a robust method for detecting overloaded ship and the proposed algorithm includes three stages: ship detection, ship tracking, and overloaded ship identification. Ship detection is a key step and the concept of ship tracking is built on the ship-segmentation method. According to the segmented ship shape, we propose a predict method based on Kalman filter to track each ship. The data of ship length and ship speed will be used to identify overloaded ship. The proposed method has been tested on a number of monocular ship image sequences and the experimental results show that the algorithm is robust and real-time.
KeywordsInland river Kalman filter Overloaded ship identification
The author thanks his colleagues for their influence. Thanks to the referees for their suggestions which have greatly improved the presentation of the paper. This work was supported by Transportation Construction Technology Project (201132820190) and Department of Transportation Industry tackling Project (2009353460640).
- 2.Ha DM, Lee JM, Kim YD (2004) Neural-edge-based ship detection and traffic parameter extraction. Image Vis Comput 22(6): 899–907Google Scholar
- 5.Obad D, Bošnjak-Cihlar Z (2004) Benefits of automatic identification system within framework of river information services. In: Proceedings Elmar—International Symposium Electronics in Marine Proceedings, vol 46(23), pp 143–147 Google Scholar