We observe representative information of large, medium objects and the vast background overwhelm that of small objects, which leads to poor performance of small object detection. To this end, a new module has been proposed in this paper, named Background and Foreground Attention Maps(BFAM) module, composing of three sub-modules: segmentation, background and foreground attention sub-modules. The segmentation maps positions which have the top strong semantic information in the deep layer of the backbone to the bottom layer maintaining more small object details and mask them to obtain background map and foreground map. Apply two tailored attention sub-modules on them respectively and then fuse them with different weights to detect final results. Experiments demonstrate BFAM achieves promising gains in small object detection on PASCAL VOC 2012 and Seaship datasets.
In order to solve the problems of unbalanced sampling of track points in the track point distance-based ship track clustering algorithm, the abnormality of individual track points affecting the clustering effect, and the difficulty of accurately describing the spatial characteristics of ship tracks with the latitude and longitude data of track points, a Kmeans ship track clustering algorithm based on the similarity of track image features is proposed. The algorithm defines a similarity measure based on trajectory image features. The method converts ship trajectory latitude and longitude time series data into ship trajectory image data, extracts trajectory image features using ResNet-50, and uses the Euclidean distance between trajectory image features as a method to measure the similarity of ship trajectories. Using the similarity measure based on the trajectory image features, the ship trajectories are clustered by the Kmeans algorithm. Experimental results show that the proposed algorithm improves the accuracy by 10% over the traditional DTW-based K-centroid clustering algorithm, and can cluster a large number of complex ship trajectories, and the clustering results are consistent with the actual traffic flow.
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.