Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images

Nie, Xuan; Duan, Mengyang; Ding, Haoxuan; Hu, Bingliang; Wong, Edward K.

doi:10.1109/access.2020.2964540

Cited by 142 publications

(67 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms have been applied to many machine vision-related fields, such as the visual recognition of robots and autopilot cars, the defect recognition of online products, and automatic recognition of security systems, etc. [ 62 , 63 , 64 ]. Mask R-CNN is an extension of Faster R-CNN, which detects the mask at the pixel level for each object detected rather than the bounding box.…”

Section: Field Deployment and Resultsmentioning

confidence: 99%

The Artificial Intelligence of Things Sensing System of Real-Time Bridge Scour Monitoring for Early Warning during Floods

Lin

Lee

Chang

et al. 2021

Sensors

View full text Add to dashboard Cite

Scour around bridge piers remains the leading cause of bridge failure induced in flood. Floods and torrential rains erode riverbeds and damage cross-river structures, causing bridge collapse and a severe threat to property and life. Reductions in bridge-safety capacity need to be monitored during flood periods to protect the traveling public. In the present study, a scour monitoring system designed with vibration-based arrayed sensors consisting of a combination of Internet of Things (IoT) and artificial intelligence (AI) is developed and implemented to obtain real-time scour depth measurements. These vibration-based micro-electro-mechanical systems (MEMS) sensors are packaged in a waterproof stainless steel ball within a rebar cage to resist a harsh environment in floods. The floodwater-level changes around the bridge pier are performed using real-time CCTV images by the Mask R-CNN deep learning model. The scour-depth evolution is simulated using the hydrodynamic model with the selected local scour formulas and the sediment transport equation. The laboratory and field measurement results demonstrated the success of the early warning system for monitoring the real-time bridge scour-depth evolution.

show abstract

Section: Field Deployment and Resultsmentioning

confidence: 99%

The Artificial Intelligence of Things Sensing System of Real-Time Bridge Scour Monitoring for Early Warning during Floods

Lin

Lee

Chang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…X. Nie et al improved Mask R-CNN, proposing a ship detection method. This method added channel-wise and spatial attention mechanisms as well as a bottom-up architecture to improve detection accuracy [33]. Sun X et al proposed a ship detection model based on YOLO using spinning object detection technology.…”

Section: Related Workmentioning

confidence: 99%

An Approach on Image Processing of Deep Learning Based on Improved SSD

Jin

Liu

2021

Symmetry

View full text Add to dashboard Cite

Compared with ordinary images, each of the remote sensing images contains many kinds of objects with large scale changes, providing more details. As a typical object of remote sensing image, ship detection has been playing an essential role in the field of remote sensing. With the rapid development of deep learning, remote sensing image detection method based on convolutional neural network (CNN) has occupied a key position. In remote sensing images, the objects of which small scale objects account for a large proportion are closely arranged. In addition, the convolution layer in CNN lacks ample context information, leading to low detection accuracy for remote sensing image detection. To improve detection accuracy and keep the speed of real-time detection, this paper proposed an efficient object detection algorithm for ship detection of remote sensing image based on improved SSD. Firstly, we add a feature fusion module to shallow feature layers to refine feature extraction ability of small object. Then, we add Squeeze-and-Excitation Network (SE) module to each feature layers, introducing attention mechanism to network. The experimental results based on Synthetic Aperture Radar ship detection dataset (SSDD) show that the mAP reaches 94.41%, and the average detection speed is 31FPS. Compared with SSD and other representative object detection algorithms, this improved algorithm has a better performance in detection accuracy and can realize real-time detection.

show abstract

“…Shao et al [ 35 ] proposed a saliency-aware CNN framework and coastline segmentation method to improve the accuracy and robustness of ship detection under complex seashore surveillance conditions. Nie et al [ 36 ] proposed an improved Mask R-CNN model, which can accurately detect and segment ships from remote sensing images at the pixel level. Guo et al [ 37 ] proposed a novel SSD network structure to improve the semantic information by deconvoluting high-level features into a low-level feature and then fusing it with original low-level features, and the model performed well on both the PASCAL VOC and railway datasets.…”

Section: Related Workmentioning

confidence: 99%

NSD‐SSD: A Novel Real‐Time Ship Detector Based on Convolutional Neural Network in Surveillance Video

Sun

Liang

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the rapid development of the marine industry, intelligent ship detection plays a very important role in the marine traffic safety and the port management. Current detection methods mainly focus on synthetic aperture radar (SAR) images, which is of great significance to the field of ship detection. However, these methods sometimes cannot meet the real-time requirement. To solve the problems, a novel ship detection network based on SSD (Single Shot Detector), named NSD-SSD, is proposed in this paper. Nowadays, the surveillance system is widely used in the indoor and outdoor environment, and its combination with deep learning greatly promotes the development of intelligent object detection and recognition. The NSD-SSD uses visual images captured by surveillance cameras to achieve real-time detection and further improves detection performance. First, dilated convolution and multiscale feature fusion are combined to improve the small objects’ performance and detection accuracy. Second, an improved prediction module is introduced to enhance deeper feature extraction ability of the model, and the mean Average Precision (mAP) and recall are significant improved. Finally, the prior boxes are reconstructed by using the K-means clustering algorithm, the Intersection-over-Union (IoU) is higher, and the visual effect is better. The experimental results based on ship images show that the mAP and recall can reach 89.3% and 93.6%, respectively, which outperforms the representative model (Faster R-CNN, SSD, and YOLOv3). Moreover, our model’s FPS is 45, which can meet real-time detection acquirement well. Hence, the proposed method has the better overall performance and achieves higher detection efficiency and better robustness.

show abstract

Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images

Cited by 142 publications

References 39 publications

The Artificial Intelligence of Things Sensing System of Real-Time Bridge Scour Monitoring for Early Warning during Floods

The Artificial Intelligence of Things Sensing System of Real-Time Bridge Scour Monitoring for Early Warning during Floods

An Approach on Image Processing of Deep Learning Based on Improved SSD

NSD‐SSD: A Novel Real‐Time Ship Detector Based on Convolutional Neural Network in Surveillance Video

Contact Info

Product

Resources

About