Sea ice tracking is essential for many regional and local level applications, including modeling sea ice distribution, ocean atmosphere, climate dynamics, as well as safe navigation and sea operations. Most operational sea ice monitoring techniques rely on satellite-borne optical and synthetic aperture radar (SAR) sensors, augmented by scatterometer and passive microwave imagery. HereinIn this review, previous ice tracking works are studied and classified into two categories: traditional tracking methods and DL-based tracking. Specifically, traditional ice tracking methods can be broadened to include cross correlation-based, optical flow-based and so on.
1. Introduction
There are three major modules in general visual-based object tracking
[1][2][3][19,20,21], which are: (1) target representation scheme, defining a target that is of interest for further analysis, such as vehicles or ships; (2) search mechanism, estimating the state of the target objects; (3) model update step, updating the target representation or model to account for appearance variations. Because of the different features of remote sensing images, satellite video tracking has confronted several issues compared with traditional object tracking tasks or unmanned aerial vehicle (UAV)-based aerial image tracking. The challenges of employing object-tracking technology in satellite video datasets are listed as follows
[4][22]:
-
Small foreground size compared with the background: The width and height of high-resolution satellite video are usually more than 2000 pixels, while the interested target only takes up about 0.01% of the whole video frame pixels or even less. The large-size background expands the searching region of classic tracking algorithms while decreasing tracking performance. Furthermore, tracking targets of tiny size have fewer features and are similar to the environment, resulting in less tracking robustness and a large tracking error.
-
Low video frame rate: Because of onboard hardware limitations, the frame rate of satellite video is typically low, resulting in significant movement of the object targets between frames and further influencing tracking prediction and model update. For example, if the target is abruptly stopped, obscured, or shifted, existing tracking systems can easily miss it.
-
Sudden illumination change: Because the satellite video collection is collected at a high altitude in space, the light and atmospheric refraction rate vary with the orbital satellite’s motion, which could result in an abrupt change in frame lighting. The difference in light has a significant impact on the performance and accuracy of object tracking.
The summary of reviewed ice motion tracking methods is given in Table 18.
Table 18.
Summary of ice motion tracking methods.
Target |
Method |
Ref. |
Year |
Description |
Ice motion |
Traditional |
[5][4] |
2017 |
MCC tracker with hybrid example-based super-resolution model |
[6][128] |
2017 |
A faster cross-correlation based tracking with several updates |
[7][129] |
2018 |
A optical-flow based tracking with super-resolution enhancement |
[8][130] |
2019 |
A multi-step tracker for ice motion tracking |
[9][131] |
2020 |
Rotation-invariant ice floe tracking |
[10][132] |
2021 |
Integrating the cross-correlation with feature tracking |
[11][133] |
2022 |
Integrating locally consistent flow field filtering with cross-correlation |
DL-based |
[12][134] |
2019 |
An encoder-decoder network with LSTM to predict ice motion trajectory |
[13][135] |
2021 |
A CNN model to predict the arctic sea ice motions |
[14][136] |
2021 |
A multi-step machine learning approach to track icebergs |
2. Traditional Ice Tracking Methods
In 2017, Ref.
[5][4] utilized the maximum cross correlation (MCC) algorithm to estimate sea ice drift vectors and track the sea ice movements, in which a hybrid example-based super-resolution model was developed to enhance the image quality for better tracking performance. Meanwhile, Ref.
[6][128] proposed several marked updates to speed up the cross-correlation-based algorithm. These updates include swapping the image order and matching direction, introducing a priori ice velocity information, and applying a post-processing algorithm. Experiment results revealed the improvement of the overall tracking performance based on cross-correlation. Later, Ref.
[10][132] integrated the cross-correlation with feature tracking and proposed a fine-resolution hybrid sea ice tracking algorithm. The proposed method can be applied for regional fast ice mapping and large stamukhas detection to aid coastal research. Similarly, Ref.
[11][133] designed a locally consistent flow field filtering algorithm with a correlation coefficient threshold and achieved better performance in sea ice motion estimation using GF-3 imagery.
Except for the cross correlation-based tracking, Ref.
[7][129] introduced the optical flow algorithm to extract a dense motion vector field of the ice motion, achieving sub-pixel accuracy. An external example learning-based super-resolution method was applied to generate higher resolution tracking samples. This approach was successfully evaluated on the passive microwave, optical, and SAR, proving appropriate for multi-sensor applications and different spatial resolutions. Later, Ref.
[8][130] proposed a multi-step tracker for ice motion tracking. By comparing ice floes within consecutive images, the algorithm extracted the potential matches with thresholds and selected the best candidates based on the assessment of a similarity metric. The approach was utilized to track ice floes with length scales ranging from 8 km to 65 km from the East Greenland Current (ECG) for 6.5 weeks in spring 2017. Compared with manual annotations, the absolute position and tracking errors associated with the method were 255 m and 0.65 cm, respectively. Furthermore, authors from
[9][131] designed a multi-step tracker for rotation-invariant ice floe tracking. Their approach consisted of ice floe extraction, ice floe description, and ice floe matching. The tracker enabled the identification of individual ice floes and the determination of their relative rotation from multiple Sentinel-2 images. Later, Ref.
[15][144] combined an on-ice seismic network with TerraSAR-X satellite imagery to track the ice cracking from 2012 to 2014 in Pine Island Glacier. The author applied a flexural gravity wave model and deconvolved the wave propagation effects, implying that water flow may limit the rate of crevasse opening.
3. Deep Learning (DL)-Based Tracking
Compared with the various ice motion trackers based on traditional methods, DL-based approaches have been proposed in recent years for ice motion trajectory prediction. In 2019, Ref.
[12][134] introduced an encoder-decoder network with L
ong short-term memory (LSTM
) units to predict sea ice motion in several days. The optical flow of ice motion, calculated from satellite passive microwave and scatterometer daily images, was fed to their network. According to the experiments, this method could forecast sea ice motion for up to 10 days in the future. Similarly, Ref.
[13][135] established a
convolutional neural network (CNN
) model and introduced previous day ice velocity, concentration, and present-day surface wind to track and predict the arctic sea ice motions. Results reveal that the designed CNN model computes the sea ice response with a correlation of 0.82 on average with respect to reality, which surpasses a set of local point-wise predictions and a leading thermodynamic-dynamical model. The ice motion tracking performance of CNN suggests the potential for combining DL with physics-based models to simulate sea ice. Later, Ref.
[14][136] suggested a multi-step machine learning approach to track icebergs via
synthetic aperture radar (SAR
) imagery. The proposed method consists of three stages, which are the graph-based superpixel segmentation model, the ensemble learning process with the heterogeneous model, and the incremental learning approach.
The authors collect SAR satellite image series
were collected from the Weddell Sea region to verify the approaches. The experiment results show that the majority of the tracked icebergs drifted between 1.3 km and 2679.2 km westward around the Antarctic continent at an average drift speed of
3.6±7.4
km/day.
Above all, the cross-correlation and optical flow algorithms play crucial roles in ice motion tracking. Integrating feature tracking with cross-correlation has been well studied and showed promising performance in ice motion tracking from remote sensing images. Furthermore, the success of the DL model in existing works suggests the feasibility and potential of combining machine learning with physics-based models to track and predict ice motion. However, considerably more work needs to be done to achieve competitive stability and accuracy in ice motion tracking compared with traditional methods.