Ship Detection in Harbour Surveillance based on Large-Scale Data and CNNs

Zwemer, Matthijs H.; Wijnhoven, Rob G. J.; With, Peter H. N. de

doi:10.5220/0006541501530160

Cited by 14 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, they used three object detectors (Faster R-CNN [18], SSD [20], and YOLO [21]) for detecting maritime vessels. In [30], a maritime vessel image dataset from a Vessel Tracking System (VST) is collected. This dataset contains authentic situations from traffic management operators.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection

Farahnakian

Heikkonen

2020

Remote Sensing

View full text Add to dashboard Cite

Object detection is a fundamental computer vision task for many real-world applications. In the maritime environment, this task is challenging due to varying light, view distances, weather conditions, and sea waves. In addition, light reflection, camera motion and illumination changes may cause to false detections. To address this challenge, we present three fusion architectures to fuse two imaging modalities: visible and infrared. These architectures can provide complementary information from two modalities in different levels: pixel-level, feature-level, and decision-level. They employed deep learning for performing fusion and detection. We investigate the performance of the proposed architectures conducting a real marine image dataset, which is captured by color and infrared cameras on-board a vessel in the Finnish archipelago. The cameras are employed for developing autonomous ships, and collect data in a range of operation and climatic conditions. Experiments show that feature-level fusion architecture outperforms the state-of-the-art other fusion level architectures.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection

Farahnakian

Heikkonen

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, at present CNN networks have proven consistently to outperform handcrafted features. Prior work by Zwemer et al [ 17 ] shows that the SSD detector is robust against large-scale variations of vessels. We select the SSD detector for our application because of the relatively low computational requirements and high accuracy that has been proven for the vessel detection problem.…”

Section: Related Workmentioning

confidence: 99%

“…Although these datasets do contain images of vessels, they are taken from very different camera viewpoints not matching with typical surveillance scenarios. The dataset proposed in [ 17 ] consists of vessels in surveillance scenarios with multiple camera viewpoints and can be used for training a vessel detector. However, this dataset lacks vessel trajectories and identifications of the vessels, so it cannot be used for training the re-ID network.…”

Section: Vessel Datasetsmentioning

confidence: 99%

Multi-Camera Vessel-Speed Enforcement by Enhancing Detection and Re-Identification Techniques

Zwemer

Groot

Wijnhoven

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents a camera-based vessel-speed enforcement system based on two cameras. The proposed system detects and tracks vessels per camera view and employs a re-identification (re-ID) function for linking vessels between the two cameras based on multiple bounding-box images per vessel. Newly detected vessels in one camera (query) are compared to the gallery set of all vessels detected by the other camera. To train and evaluate the proposed detection and re-ID system, a new Vessel-reID dataset is introduced. This extensive dataset has captured a total of 2474 different vessels covered in multiple images, resulting in a total of 136,888 vessel bounding-box images. Multiple CNN detector architectures are evaluated in-depth. The SSD512 detector performs best with respect to its speed (85.0% Recall@95Precision at 20.1 frames per second). For the re-ID of vessels, a large portion of the total trajectory can be covered by the successful detections of the SSD model. The re-ID experiments start with a baseline single-image evaluation obtaining a score of 55.9% Rank-1 (49.7% mAP) for the existing TriNet network, while the available MGN model obtains 68.9% Rank-1 (62.6% mAP). The performance significantly increases with 5.6% Rank-1 (5.7% mAP) for MGN by applying matching with multiple images from a single vessel. When emphasizing more fine details by selecting only the largest bounding-box images, another 2.0% Rank-1 (1.4% mAP) is added. Application-specific optimizations such as travel-time selection and applying a cross-camera matching constraint further enhance the results, leading to a final 88.9% Rank-1 and 83.5% mAP performance.

show abstract

“…When the target is found, p i is 1; otherwise, p i is 0. t i is the four coordinate parameters of the boundary box (t x , t y , t w , t h ) when predicting RPN, which corresponds to the coordinates of positive anchor point GT. L cls is the loss function of dichotomy (target/non-target), and L reg is the loss function of smooth L (1,2) , which is used to predict boundary box and GT box. .…”

Section: The Loss Function Of Training Rpn Includes Regression Calculmentioning

confidence: 99%

“…In addition, convolutional neural network (CNN) is also well applied to the ship identification. However, the latest data shows that the identification accuracy is not ideal [2], hence it is extremely urgent to improve the identification accuracy. Ship identification is also one of the research hotspots in the field of pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

A Ship Target Location and Mask Generation Algorithms Base on Mask RCNN

Shaodan¹,

Feng²,

Chen³

2019

IJCIS

View full text Add to dashboard Cite

Ship detection is a canonical problem in computer vision. Motivated by the observation that the major bottleneck of ship detection lies on the different scales of ship instances in images, we focus on improving the detection rate, especially for the smallsized ships which are relatively far from the camera. We use the Smooth function combined with L1 and L2 norm to optimize the region proposal network (RPN) loss function and reduce the deviation between the prediction frame and the actual target to ensure the accurate location of the ship target. With the Two-Way sampling combined with the shared weight to generate the mask, we solve the problems of inaccurate segmentation, target loss and small interference when Mask Region Convolution Neural Network (RCNN) is used to segment an instance. We create the experimental data sets from the deep learning annotation tool-Labelme. Experiments show that the improved Mask-RCNN model has a confidence rate of 82.17%. Serving as the basic network, the test accuracy rate of ResNetXt-101 is 3.3% higher than that of the original ResNet-101, which can better realize the function of ship target location and mask generation.

show abstract

Ship Detection in Harbour Surveillance based on Large-Scale Data and CNNs

Cited by 14 publications

References 14 publications

Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection

Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection

Multi-Camera Vessel-Speed Enforcement by Enhancing Detection and Re-Identification Techniques

A Ship Target Location and Mask Generation Algorithms Base on Mask RCNN

Contact Info

Product

Resources

About