Abstract
At night, buoys and other navigation marks disappear to be replaced by fixed or flashing lights. Navigation marks are seen as a set of lights in various colors rather than their familiar outline. Deciphering that the meaning of the lights is a burden to navigators, it is also a new challenging research direction of intelligent sensing of navigation environment. The study studied initiatively the intelligent recognition of lights on navigation marks at night based on multilabel video classification methods. To capture effectively the characteristics of navigation mark's lights, including both color and flashing phase, three different multilabel classification models based on binary relevance, label power set, and adapted algorithm were investigated and compared. According to the experiment's results performed on a data set with 8000 minutes video, the model based on binary relevance, named NMLNet, has highest accuracy about 99.23% to classify 9 types of navigation mark's lights. It also has the fastest computation speed with least network parameters. In the NMLNet, there are two branches for the classifications of color and flashing, respectively, and for the flashing classification, an improved MobileNet-v2 was used to capture the brightness characteristic of lights in each video frame, and an LSTM is used to capture the temporal dynamics of lights. Aiming to run on mobile devices on vessel, the MobileNet-v2 was used as backbone, and with the improvement of spatial attention mechanism, it achieved the accuracy near Resnet-50 while keeping its high speed.
Highlights
In recent years, various AI technologies have been utilized to research smart ship [1, 2] and intelligent navigation [3, 4], among which intelligent sensing of navigational environment is the first important ability [5]
Maxwell et al (2017) presented a multilabel classification method based on deep learning classifier to predict chronic diseases, such as diabetes, hypertension, and fatty liver, in patients, and the results showed that it gave much higher accuracy than SVM and multilabel k nearest neighbors (ML-KNN) [33]
Liu et at. (2019) proposed an LSTM-based network structure to detect multilabel events in a given surveillance video data set, and the experimental results showed that it outperform the SVM-based method for visual event detection [37]
Summary
Various AI technologies have been utilized to research smart ship [1, 2] and intelligent navigation [3, 4], among which intelligent sensing of navigational environment is the first important ability [5]. In 2019, we started a research on the recognition of navigation marks during daytime and proposed a classification model based on ResNet-50 and a multiple scale attention mechanism [9]. At night, navigation marks disappear, and the methods by observing their appearance from image will be not working anymore In this case, the lights on navigation marks become the most important feature to identify and ascertain their purpose. Erefore, this article studied the visual recognition of navigation mark’s lights based on video and multilabel classification methods, and its contributions are summarized as follows:. (3) We design a feature extraction network for the color characteristic of navigation mark’s light based on the attention mechanism. (4) we propose an NMLNet (Navigation Mark’s Light Network) to capture the light features including color and flashing characteristic from video for the classification of navigation mark’s lights.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
