Abstract
High-resolution optical remote sensing data can be utilized to investigate the human behavior and the activities of artificial targets, for example ship detection on the sea. Recently, the deep convolutional neural network (DCNN) in the field of deep learning is widely used in image processing, especially in target detection tasks. Therefore, a complete processing system called the broad area target search (BATS) is proposed based on DCNN in this paper, which contains data import, processing and storage steps. In this system, aiming at the problem of onshore false alarms, a method named as Mask-Faster R-CNN is proposed to differentiate the target and non-target areas by introducing a semantic segmentation sub network into the Faster R-CNN. In addition, we propose a DCNN framework named as Saliency-Faster R-CNN to deal with the problem of multi-scale ships detection, which solves the problem of missing detection caused by the inconsistency between large-scale targets and training samples. Based on these DCNN-based methods, the BATS system is tested to verify that our system can integrate different ship detection methods to effectively solve the problems that existed in the ship detection task. Furthermore, our system provides an interface for users, as a data-driven learning, to optimize the DCNN-based methods.
Highlights
With the development of society and technology, measuring and monitoring human activity in the ocean area is becoming a topic of significance and increasing interest
A set of comparison experiments has been conducted in this part, which compares the Saliency-Faster R-CNN proposed in this paper to the baseline method (Faster R-CNN) to validate the accuracy and superiority of our method
SVM [55], as a classic machine learning method, can be combined with deep convolutional neural network (DCNN) for classification, relevant studies have proved that the classification accuracy of SVM is slightly less than the softmax used in the Fast R-CNN [13], Faster R-CNN [14] and Bengio’s research [56], in addition, the method based on SVM is not an end-to-end system, that is the reason for choosing Faster R-CNN as the benchmark method in our paper
Summary
With the development of society and technology, measuring and monitoring human activity in the ocean area is becoming a topic of significance and increasing interest In this topic, ship objects play an important role in both areas of the military and civilian, such as the maritime safety, marine traffic, border control, fisheries management, marine transport, etc. The background information and target categories of these images are complex, which include the different lighting conditions and cloud occlusions, and the dataset contains a variety of ship categories such as the cargo, cruise, carriers, etc. It ensures the diversity of the samples. The augmentation operations have been operated to improve the generalization ability of networks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
