Container ship "CMA CGM Balzac" in the port of Zeebrugge Belgium.


The CSPR project is to recognize the container ship entering the harbor gate to control their access and manage according harbor assets to have the traffic flow efficient in addition to cost-minimizing purposes. Our team is currently working with the U.S. States government engineering team to exploit its usage at the Georgia Savannah harbor. This project is launched in 2007 and currently under extensive research reviews to specify its topics and coverage.


Container ships are cargo ships that carry all of their load in truck-size containers, in a technique called containerization. They form a common means of commercial intermodal freight transport. A brief introduction is found at Container Ship and longer one is at Container ship Information. Container ships are also categorized as Intermodal Frieght Transport or Cargo.

The introduction on the container ship and the purpose of ship recognition with following challenges will be described at Introduction.

Research reviews

Detailed research reviews over related research fields will be provided at Research reviews.

Challenging problems

Recognizing the container ship on the sea is a challenging task due to its exposure to the natural environments. The main problems that we in practice have to overcome are:

  • The distance between the observer and the cargo ships
  • The weather condition: dust, fog, rain, wave, trembling, etc.
  • The diversity of the ship shape, type, length, color, etc.
  • Limited sensor installation environment.

Literature reviews

  1. C. Tremblay and U. de Montrial, "Experiments on Individual Classifiers and on Fusion of a Set of Classifiers," in Information Fusion, 2002. Proceedings of the Fifth International Conference on, 2002, pp. 272-277. Pdf 16px.pngMedia:Experiments on Individual Classifiers and on Fusion of a Set of Classifiers.pdf
    • In the last decades many classification methods and fusers have been developed. Considerable gains have been achieved in the classification performance by fusing and combining different classifiers. We experiment a new method for ship infrared imagery recognition based on the fusion of individual results in order to obtain a more reliable decision. To optimize the results of every class of ship, we implemented individual classifiers using Dempster-Shafer(DS) method for each class i.e. an individual classifier returns if the ship belongs to the class or not. We compare the result of the DS classifier with the results of the individual classifier. The improvement recognition varies between 3% to 20% for a class. We then experiment a new method based on a fusion of a set of classifiers. The objective of a good fuser is to perform at least as good as the best classifier in any situation. For this purpose, we consider three classifiers: DS classifier, Bayes classifier and nearest neighbor classifier and one fuser: feedforward neural network fuser. We compare the results of the best classifier with the results of the fusion of a combination of classifiers. The fuser gives a performance equal or superior to the best classifier.

Related literuatures

  • Color vision
    1. K. B. Kim, "Recognition of Identifiers from Shipping Container Images Using Fuzzy Binarization and Enhanced Fuzzy Neural Network," LECTURE NOTES IN COMPUTER SCIENCE, vol. 3613, p. 761, 2005. Pdf 16px.pngMedia:Recognition of Identifiers from Shipping Container Images Using Fuzzy Binarization and Enhanced Fuzzy Neural Network.pdf
      • In this paper, we propose and evaluate a novel recognition algorithm for container identifiers that effectively overcomes these difficulties and recognizes identifiers from container images captured in various environments. The proposed algorithm, first, extracts the area containing only the identifiers from container images by using CANNY masking and bi-directional histogram method. The extracted identifier area is binarized by the fuzzy binarization method newly proposed in this paper. Then a contour tracking method is applied to the binarized area in order to extract the container identifiers, which are the target for recognition. This paper also proposes an enhanced fuzzy RBF network that adapts the enhanced fuzzy ART network for the middle layer. This network is applied to the recognition of individual codes. The results of experiment for performance evaluation on the real container images showed that the proposed algorithm performs better for extraction and recognition of container identifiers compared to conventional algorithms.
    2. S. Kumano, K. Miyamoto, M. Tamagawa, H. Ikeda, and K. Kan, "Development of a container identification mark recognition system," Electronics and Communications in Japan(Part II Electronics), vol. 87, pp. 38-50, 2004. Pdf 16px.pngMedia:Development of a container identification mark recognition system.pdf
      • This paper reports the development of a container identification mark or number recognition system designed for application to a container terminal. The recognition system recognizes the number or mark on the back surface of a container in an outdoor environment by photographing the mark by a camera system installed on the container gate. Containers in many cases differ in color as well as in layout depending on their owners; the layouts commonly contain one to four horizontal columns or rows of writing or more rarely vertical rows of writing. The container number recognition system is constructed from an illumination intensity sensor and illumination system for handling the outdoor illumination changes, a shutter speed control device, and devices such as filters for handling various container colors. In addition, the proposed system uses a character recognition scheme based on a dynamic design method for recognizing differing character string layouts in container marks or numbers. Field tests have been conducted to obtain a recognition rate of 92.8% for all data, a recognition rate of 97.9% for effective or appropriate data excluding data outside the field of vision, and an average recognition speed of less than 2 seconds.
  • Infrared vision
    1. C. J. S. deSilva, G. Lee, and R. Johnson, "All-aspect ship recognition in infrared images," Electronic Technology Directions to the Year 2000, 1995. Proceedings., pp. 194-198, 1995. Pdf 16px.pngMedia:All-aspect ship recognition in infrared images.pdf
      • The paper describes an investigation of the problem of identifying objects, in particular ships at sea, in infrared images obtained at a variety of angles and scales. The paper covers theoretical and experimental work relating to the choice of feature vectors to describe the images and the application of the this work to the development of a demonstration system.

Project status

  • 02-01-2007: Starts extensive research reviews to specify the project topics and coverage.

Project history

  • 02-01-2007: CSPR project wiki is established first at Pilho's Wiki.

Project members

External links


  • Literature reviews: Endnote update (02/01/2007) Please download this and unzip in your research directory. After use EndNote to see the list of related literatures. Every article includes their full texts in PDF.