More Like this

1. Fine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs

   https://doi.org/10.3390/rs13183562  

   Gonçalves, Bento C. ; Lynch, Heather J. ( September 2021 , Remote Sensing)

   null (Ed.)

   Fine-scale sea ice conditions are key to our efforts to understand and model climate change. We propose the first deep learning pipeline to extract fine-scale sea ice layers from high-resolution satellite imagery (Worldview-3). Extracting sea ice from imagery is often challenging due to the potentially complex texture from older ice floes (i.e., floating chunks of sea ice) and surrounding slush ice, making ice floes less distinctive from the surrounding water. We propose a pipeline using a U-Net variant with a Resnet encoder to retrieve ice floe pixel masks from very-high-resolution multispectral satellite imagery. Even with a modest-sized hand-labeled training set and the most basic hyperparameter choices, our CNN-based approach attains an out-of-sample F1 score of 0.698–a nearly 60% improvement when compared to a watershed segmentation baseline. We then supplement our training set with a much larger sample of images weak-labeled by a watershed segmentation algorithm. To ensure watershed derived pack-ice masks were a good representation of the underlying images, we created a synthetic version for each weak-labeled image, where areas outside the mask are replaced by open water scenery. Adding our synthetic image dataset, obtained at minimal effort when compared with hand-labeling, further improves the out-of-sample F1 score to 0.734. Finally, we use an ensemble of four test metrics and evaluated after mosaicing outputs for entire scenes to mimic production setting during model selection, reaching an out-of-sample F1 score of 0.753. Our fully-automated pipeline is capable of detecting, monitoring, and segmenting ice floes at a very fine level of detail, and provides a roadmap for other use-cases where partial results can be obtained with threshold-based methods but a context-robust segmentation pipeline is desired. 

   more » « less
2. Artificial intelligence for automated detection of large mammals creates path to upscale drone surveys

   https://doi.org/10.1038/s41598-023-28240-9  

   Lenzi, Javier ; Barnas, Andrew F. ; ElSaid, Abdelrahman A. ; Desell, Travis ; Rockwell, Robert F. ; Ellis-Felege, Susan N. ( January 2023 , Scientific Reports)

   Imagery from drones is becoming common in wildlife research and management, but processing data efficiently remains a challenge. We developed a methodology for training a convolutional neural network model on large-scale mosaic imagery to detect and count caribou (Rangifer tarandus), compare model performance with an experienced observer and a group of naïve observers, and discuss the use of aerial imagery and automated methods for large mammal surveys. Combining images taken at 75 m and 120 m above ground level, a faster region-based convolutional neural network (Faster-RCNN) model was trained in using annotated imagery with the labels: “adult caribou”, “calf caribou”, and “ghost caribou” (animals moving between images, producing blurring individuals during the photogrammetry processing). Accuracy, precision, and recall of the model were 80%, 90%, and 88%, respectively. Detections between the model and experienced observer were highly correlated (Pearson: 0.96–0.99,Pvalue < 0.05). The model was generally more effective in detecting adults, calves, and ghosts than naïve observers at both altitudes. We also discuss the need to improve consistency of observers’ annotations if manual review will be used to train models accurately. Generalization of automated methods for large mammal detections will be necessary for large-scale studies with diverse platforms, airspace restrictions, and sensor capabilities.

    

   more » « less
3. Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions

   https://doi.org/10.1080/01431161.2023.2248560  

   Pires de Lima, Rafael ; Vahedi, Behzad ; Hughes, Nick ; Barrett, Andrew P. ; Meier, Walter ; Karimzadeh, Morteza ( September 2023 , International Journal of Remote Sensing)

   Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, models trained with our largest training set have weighted F1 scores all greater than 0.95 for January and July test scenes. Specifically, the median weighted F1 score was 0.98, indicating high performance for both months. By comparison, a competitive baseline U-Net has a weighted average F1 score of ranging from 0.92 to 0.94 (median 0.93) for July, and 0.97 to 0.98 (median 0.97) for January. Multiclass ice type classification is more challenging, and even though our models achieve 2% improvement in weighted F1 average compared to the baseline U-Net, test weighted F1 is generally between 0.6 and 0.80. Our approach can efficiently segment full SAR scenes in one run, is faster than the baseline U-Net, retains spatial resolution and dimension, and is more robust against noise compared to approaches that rely on patch classification. 

   more » « less
4. A human mesh-centered approach to action recognition in the operating room

   https://doi.org/10.20517/ais.2024.19  

   Liu, Benjamin ; Soenens, Gilles ; Villarreal, Joshua ; Jopling, Jeffrey ; Van_Herzeele, Isabelle ; Rau, Anita ; Yeung-Levy, Serena ( June 2024 , Artificial Intelligence Surgery)

   Aim: Video review programs in hospitals play a crucial role in optimizing operating room workflows. In scenarios where split-seconds can change the outcome of a surgery, the potential of such programs to improve safety and efficiency is profound. However, leveraging this potential requires a systematic and automated analysis of human actions. Existing methods predominantly employ manual methods, which are labor-intensive, inconsistent, and difficult to scale. Here, we present an AI-based approach to systematically analyze the behavior and actions of individuals from operating rooms (OR) videos.

   Methods: We designed a novel framework for human mesh recovery from long-duration surgical videos by integrating existing human detection, tracking, and mesh recovery models. We then trained an action recognition model to predict surgical actions from the predicted temporal mesh sequences. To train and evaluate our approach, we annotated an in-house dataset of 864 five-second clips from simulated surgical videos with their corresponding actions.

   Results: Our best model achieves an F1 score and the area under the precision-recall curve (AUPRC) of 0.81 and 0.85, respectively, demonstrating that human mesh sequences can be successfully used to recover surgical actions from operating room videos. Model ablation studies suggest that action recognition performance is enhanced by composing human mesh representations with lower arm, pelvic, and cranial joints.

   Conclusion: Our work presents promising opportunities for OR video review programs to study human behavior in a systematic, scalable manner.

    

   more » « less
5. Corpus-Based Relation Extraction by Identifying and Refining Relation Patterns

   Sizhe Zhou, Suyu Ge ( September 2023 , Springer)

   Proc. 2023 European Conf. on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (Ed.)

   Automated relation extraction without extensive human-annotated data is a crucial yet challenging task in text mining. Existing studies typically use lexical patterns to label a small set of high-precision relation triples and then employ distributional methods to enhance detection recall. This precision-first approach works well for common relation types but struggles with unconventional and infrequent ones. In this work, we propose a recall-first approach that first leverages high-recall patterns (e.g., a per:siblings relation normally requires both the head and tail entities in the person type) to provide initial candidate relation triples with weak labels and then clusters these candidate relation triples in a latent spherical space to extract high-quality weak supervisions. Specifically, we present a novel framework, RCLUS, where each relation triple is represented by its head/tail entity type and the shortest dependency path between the entity mentions. RCLUS first applies high-recall patterns to narrow down each relation type’s candidate space. Then, it embeds candidate relation triples in a latent space and conducts spherical clustering to further filter out noisy candidates and identify high-quality weakly-labeled triples. Finally, RCLUS leverages the above-obtained triples to prompt-tune a pre-trained language model and utilizes it for improved extraction coverage. We conduct extensive experiments on three public datasets and demonstrate that RCLUS outperforms the weakly-supervised baselines by a large margin and achieves generally better performance than fully-supervised methods in low-resource settings. 

   more » « less