A Transfer Learning-Based Approach to Marine Vessel Re-Identification
- URL: http://arxiv.org/abs/2207.14500v1
- Date: Fri, 29 Jul 2022 06:36:10 GMT
- Title: A Transfer Learning-Based Approach to Marine Vessel Re-Identification
- Authors: Guangmiao Zeng, Wanneng Yu, Rongjie Wang, Anhui Lin
- Abstract summary: This paper proposes a transfer dynamic alignment algorithm and simulates the swaying situation of vessels at sea.
It improves the mean average accuracy (mAP) by 10.2% and the first hit rate (Rank1) by 4.9% on average.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Marine vessel re-identification technology is an important component of
intelligent shipping systems and an important part of the visual perception
tasks required for marine surveillance. However, unlike the situation on land,
the maritime environment is complex and variable with fewer samples, and it is
more difficult to perform vessel re-identification at sea. Therefore, this
paper proposes a transfer dynamic alignment algorithm and simulates the swaying
situation of vessels at sea, using a well-camouflaged and similar warship as
the test target to improve the recognition difficulty and thus cope with the
impact caused by complex sea conditions, and discusses the effect of different
types of vessels as transfer objects. The experimental results show that the
improved algorithm improves the mean average accuracy (mAP) by 10.2% and the
first hit rate (Rank1) by 4.9% on average.
Related papers
- A Computer Vision Approach to Estimate the Localized Sea State [45.498315114762484]
This research focuses on utilizing sea images in operational envelopes captured by a single stationary camera mounted on the ship bridge.
The collected images are used to train a deep learning model to automatically recognize the state of the sea based on the Beaufort scale.
arXiv Detail & Related papers (2024-07-04T09:07:25Z) - Efficient Multi-branch Segmentation Network for Situation Awareness in Autonomous Navigation [0.0]
This study builds a dataset that captured perspectives from USVs and unmanned aerial vehicles in a maritime port environment.
Statistical analysis revealed a high correlation between the distribution of the sea and sky and row positional information.
A three-branch semantic segmentation network with a row position encoding module (RPEM) was proposed to improve the prediction accuracy between the sea and the sky.
arXiv Detail & Related papers (2024-03-30T13:38:07Z) - SafeSea: Synthetic Data Generation for Adverse & Low Probability
Maritime Conditions [24.312671086207228]
We introduce SafeSea, which is a stepping stone towards transforming actual sea images with various Sea State backgrounds.
This approach reduces the time and effort required to create synthetic datasets for training maritime object detection models.
arXiv Detail & Related papers (2023-11-24T01:10:12Z) - Dual Adversarial Resilience for Collaborating Robust Underwater Image
Enhancement and Perception [54.672052775549]
In this work, we introduce a collaborative adversarial resilience network, dubbed CARNet, for underwater image enhancement and subsequent detection tasks.
We propose a synchronized attack training strategy with both visual-driven and perception-driven attacks enabling the network to discern and remove various types of attacks.
Experiments demonstrate that the proposed method outputs visually appealing enhancement images and perform averagely 6.71% higher detection mAP than state-of-the-art methods.
arXiv Detail & Related papers (2023-09-03T06:52:05Z) - Histogram Layer Time Delay Neural Networks for Passive Sonar
Classification [58.720142291102135]
A novel method combines a time delay neural network and histogram layer to incorporate statistical contexts for improved feature learning and underwater acoustic target classification.
The proposed method outperforms the baseline model, demonstrating the utility in incorporating statistical contexts for passive sonar target recognition.
arXiv Detail & Related papers (2023-07-25T19:47:26Z) - Automatized marine vessel monitoring from sentinel-1 data using
convolution neural network [0.0]
We introduce wavelet transformation-based Convolution Neural Network approach to recognize objects from SAR images during the heavy naval traffic.
The information comprises Sentinel-1 SAR-C dual-polarization data acquisitions over the western coastal zones of India.
arXiv Detail & Related papers (2023-04-23T18:09:44Z) - Hierarchical Compositional Representations for Few-shot Action
Recognition [51.288829293306335]
We propose a novel hierarchical compositional representations (HCR) learning approach for few-shot action recognition.
We divide a complicated action into several sub-actions by carefully designed hierarchical clustering.
We also adopt the Earth Mover's Distance in the transportation problem to measure the similarity between video samples in terms of sub-action representations.
arXiv Detail & Related papers (2022-08-19T16:16:59Z) - Frustratingly Easy Transferability Estimation [64.42879325144439]
We propose a simple, efficient, and effective transferability measure named TransRate.
TransRate measures the transferability as the mutual information between the features of target examples extracted by a pre-trained model and labels of them.
Despite its extraordinary simplicity in 10 lines of codes, TransRate performs remarkably well in extensive evaluations on 22 pre-trained models and 16 downstream tasks.
arXiv Detail & Related papers (2021-06-17T10:27:52Z) - AOT: Appearance Optimal Transport Based Identity Swapping for Forgery
Detection [76.7063732501752]
We provide a new identity swapping algorithm with large differences in appearance for face forgery detection.
The appearance gaps mainly arise from the large discrepancies in illuminations and skin colors.
A discriminator is introduced to distinguish the fake parts from a mix of real and fake image patches.
arXiv Detail & Related papers (2020-11-05T06:17:04Z) - A Novel CNN-based Method for Accurate Ship Detection in HR Optical
Remote Sensing Images via Rotated Bounding Box [10.689750889854269]
A novel CNN-based ship detection method is proposed, by overcoming some common deficiencies of current CNN-based methods in ship detection.
We are able to predict the orientation and other variables independently, and yet more effectively, with a novel dual-branch regression network.
Experimental results demonstrate the great superiority of the proposed method in ship detection.
arXiv Detail & Related papers (2020-04-15T14:48:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.