SDGH-Net: Ship Detection in Optical Remote Sensing Images Based on Gaussian Heatmap Regression

Abstract

The ship detection task using optical remote sensing images is important for in maritime safety, port management and ship rescue. With the wide application of deep learning to remote sensing, a series of target detection algorithms, such as faster regions with convolution neural network feature (R-CNN) and You Only Look Once (YOLO), have been developed to detect ships in remote sensing images. These detection algorithms use fully connected layer direct regression to obtain coordinate points. Although training and forward speed are fast, they lack spatial generalization ability. To avoid the over-fitting problem that may arise from the fully connected layer, we propose a fully convolutional neural network, SDGH-Net, based on Gaussian heatmap regression. SDGH-Net uses an encoder–decoder structure to obtain the ship area feature map by direct regression. After simple post-processing, the ship polygon annotation can be obtained without non-maximum suppression (NMS) processing. To speed up model training, we added a batch normalization (BN) processing layer. To increase the receptive field while controlling the number of learning parameters, we introduced dilated convolution and added it at different rates to fuse the features of different scales. We tested the performance of our proposed method using a public ship dataset HRSC2016. The experimental results show that this method improves the recall rate of ships, and the F-measure is 85.05%, which surpasses all other methods we used for comparison.

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

“…A number of data augmentation methods [92] have been developed to increase the size and enrich the diversity of maritime training datasets, thus improving the robustness and the generalization ability of the detection models. In the maritime context, general data augmentation techniques, such as multi-angle rotation, color jittering, random translation, random cropping, horizontal flipping and adding random noises, have also been used in [158], [159], [160], [161] to increase the diversity of samples. In order to address the scarcity of real-world samples of small ships for training a deep learning based object detector, Chen et al [162] proposed to use a Gaussian Mixture Wasserstein GAN with Gradient Penalty (WGAN-GP) to generate synthetic small ships.…”

Glacier extraction based on high-spatial-resolution remote-sensing images using a deep-learning approach with attention mechanism

“…The attention mechanism can learn contextual information and capture internal correlations. Its basic idea is to ignore irrelevant information and focus on key information in operations (Woo et al, 2018). In this paper, we used the convolutional block attention module (CBAM) (Fig.…”

Ship Detection Based on Compressive Sensing Measurements of Optical Remote Sensing Scenes

“…Guo et al [11] proposed a rotational Libra R-CNN, which adds the balanced feature pyramid module and the intersection over union-balanced sampling module to overcome the limitation of dense distribution and different scales. Wang et al [12] proposed SDGH-Net, which avoids the over-fitting problem through Gaussian heatmap regression. Wang et al [13] proposed fused features and rebuilt (FFR) YOLOv3, which improves the speed and accuracy of ship detection in ORS images.…”

“…Then, the original scene is reconstructed using an image reconstruction algorithm [9,10]. Finally, the image-based ship detection algorithm [11][12][13][14] is used on the reconstructed scene to get the ship detection result. However, the process of reconstructing the measurements to the original scene is computationally costly, memory demanding, and time-consuming.…”