YOLOv5 is one of the target detection algorithms with fast detection speed and high accuracy, but it has the problems of insufficient sensory field and low accuracy of small target detection. In order to solve above problems, an improved YOLOv5 network model, i.e., an improved YOLOv5-TI model based on the attention mechanism, is proposed. The attention module is added to the backbone network when extracting features to improve the target detection accuracy, and the input features are shifted windowed for self-attention calculation to effectively utilize the features and improve the small target detection accuracy; the proposed model YOLOv5-TI is experimented on the self-built inland infrared dataset, and the mAP value reaches 95.5%, and the results show that YOLOv5-TI can effectively improve the target detection accuracy. The inland vessels equipped with visual intelligent perception system can effectively identify the targets on water, and they have wide applications in the fields of surface exploration and autonomous search and rescue.
This paper proposes a new model for optimal selection of the emergency rescue ship, aiming to select the suitable surrounding ships within the accident sea area as the emergency rescue facilities. Firstly, the combined weights of indicators for the selection of emergency rescue ships need to be determined. The Analytic Hierarchy Process (AHP) method is used to determine the subjective weight. The Criteria Importance Through Inter-criteria Correlation (CRITIC) method is used to determine the objective weight. Based on the idea of game theory, the subjective and objective weights are fused to obtain the combined weight. Secondly, the Vlse Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method is introduced to sort the rescue ships. Finally, an example is used to verify that this model is reasonable and effective for the selection of maritime rescue ships.
KEYWORDS: Video, Video compression, Radar, Video coding, Standards development, Computer programming, Semantic video, Video surveillance, Image compression, Data storage
Data compression technology is one of the essential core technologies for remote measurement and control of future intelligent ships. The quality and volume of the compressed digital video of shipborne radar should meet the requirements of intelligent ships. The digital video compression technology of shipborne radar and the bandwidth of marine communication network are the main factors that affect radar digital video compression quality. In this paper, according to the content of the radar echo area, four ranges of shipborne radar digital video are selected, and the high-efficiency digital video coding standards H.264/AVC, H.265/HEVC, HEVC-SCC, VP9 and AVS2 are used for radars of different ranges. Digital video uses the same encoding configuration to conduct simulation experiments and compare compression performance. The simulation results show that the digital video quality of the shipborne radar compressed by these video coding standards will continue to change with the fluctuation of the network bandwidth. When the bitrate is low, the compression performance of the encoder is improved faster, while the compression performance of these video coding standards gradually approaches at a higher bitrate. The performance of the codec also depends on the complexity of the radar digital video content. The larger the range, the lower the content complexity and the better the performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.