Breaking The Ice: Video Segmentation for Close-Range Ice-Covered Waters

2024-11-07 · Corwin Grant Jeon MacMillan, K. Andrea Scott, Matthew Garvin, Zhao Pan

Rapid ice recession in the Arctic Ocean, with predictions of ice-free summers by 2060, opens new maritime routes but requires reliable navigation solutions. Current approaches rely heavily on subjective expert judgment, underscoring the need for automated, data-driven solutions. This study leverages machine learning to assess ice conditions using ship-borne optical data, introducing a finely annotated dataset of 946 images, and a semi-manual, region-based annotation technique. The proposed video segmentation model, UPerFlow, advances the SegFlow architecture by incorporating a six-channel ResNet encoder, two UPerNet-based segmentation decoders for each image, PWCNet as the optical flow encoder, and cross-connections that integrate bi-directional flow features without loss of latent information. The proposed architecture outperforms baseline image segmentation networks by an average 38% in occluded regions, demonstrating the robustness of video segmentation in addressing challenging Arctic conditions.

📄 PDF Abstract BibTeX arXiv:2411.05225

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation Optical Flow Estimation Segmentation Semantic Segmentation Video Segmentation Video Semantic Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Kaiming Initialization 설명 없음

D3S - A Discriminative Single Shot Segmentation Tracker

2020-06-01 · CVPR 2020 6 · Alan Lukezic, Jiri Matas, Matej Kristan

Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their l…

Object Object Tracking Segmentation Semantic Segmentation+4

D3S -- A Discriminative Single Shot Segmentation Tracker

2019-11-20 · Alan Lukežič, Jiří Matas, Matej Kristan

Object Object Tracking Segmentation Semantic Segmentation+3

Breaking the "Object" in Video Object Segmentation

2022-12-12 · CVPR 2023 1 · Pavel Tokmakov, Jie Li, Adrien Gaidon

The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually nothing of the original except for the ide…

Object Semantic Segmentation Video Object Segmentation Video Semantic Segmentation

Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation

2020-11-23 · Hala Lamdouar, Charig Yang, Weidi Xie, Andrew Zisserman

The objective of this paper is to design a computational architecture that discovers camouflaged objects in videos, specifically by exploiting motion information to perform object segmentation. We make the following thre…

Motion Segmentation Object Object Discovery Segmentation+1

Unsupervised Semantic Scene Labeling for Streaming Data

2017-07-01 · CVPR 2017 7 · Maggie Wigness, John G. Rogers III

We introduce an unsupervised semantic scene labeling approach that continuously learns and adapts semantic models discovered within a data stream. While closely related to unsupervised video segmentation, our algorithm i…

Scene Labeling Segmentation Video Segmentation Video Semantic Segmentation