Glacial science could benefit tremendously from autonomous robots, but previous glacial robots have had perception issues in these colorless and featureless environments, specifically with visual feature extraction. This translates to failures in visual odometry and visual navigation. Glaciologists use near-infrared imagery to reveal the underlying heterogeneous spatial structure of snow and ice, and we theorize that this hidden near-infrared structure could produce more and higher quality features than available in visible light. We took a custom camera rig to Igloo Cave at Mt. St. Helens to test our theory. The camera rig contains two identical machine vision cameras, one which was outfitted with multiple filters to see only near-infrared light. We extracted features from short video clips taken inside Igloo Cave at Mt. St. Helens, using three popular feature extractors (FAST, SIFT, and SURF). We quantified the number of features and their quality for visual navigation by comparing the resulting orientation estimates to ground truth. Our main contribution is the use of NIR longpass filters to improve the quantity and quality of visual features in icy terrain, irrespective of the feature extractor used.
Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry
Chair of Cyber-Physical-Systems（网络物理系统教授职位）；Institute of Automatic Control（自动控制研究所）；Faculty of Mechanical Engineering（机械工程学院）；RWTH Aachen University（亚琛工业大学）
Ludwig Maximilian University Munich（慕尼黑路德维希·马克西米利安大学）；Data Reply GmbH Munich（慕尼黑Data Reply有限公司）；Siemens Corporate Technology Munich（慕尼黑西门子企业技术中心）
Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have previously shown that the combination of a visual model and a statistical semantic prior model can improve on the task of mapping images to their associated scene description. In this paper, we review the model and compare it to a novel conditional multi-way model for visual relationship detection, which does not include an explicitly trained visual prior model…
The Self-Organizing Map (SOM) is a brain-inspired neural model that is very promising for unsupervised learning, especially in embedded applications. However, it is unable to learn efficient prototypes when dealing with complex datasets. We propose in this work to improve the SOM performance by using extracted features instead of raw data. We conduct a comparative study on the SOM classification accuracy with unsupervised feature extraction using two different approaches: a machine learning approach with Sparse Convolutional Auto-Encoders using gradient-based learning, and a neuroscience appro…
University of Washington（华盛顿大学）；Northwestern University（西北大学）；Allen Institute for AI（艾伦人工智能研究所）
Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout information, e.g., each token's 2D position on the page, into language model pretraining. We introduce new methods that explicitly model VIsual LAyout (VILA) groups, i.e., text lines or text blocks, to further improve performance. In our I-VILA approach, we show that simply inserting special tokens denoting layout group boundaries into model inputs can lead to a 1.9% Macro F1 improvement in token classificati…
University of Science and Technology of China（中国科学技术大学）；The University of Hong Kong（香港大学）；Genmab Inc.（Genmab公司）
Due to lack of annotated pathological images, transfer learning has been the predominant approach in the field of digital pathology.Pre-trained neural networks based on ImageNet database are often used to extract "off the shelf" features, achieving great success in predicting tissue types, molecular features, and clinical outcomes, etc. We hypothesize that fine-tuning the pre-trained models using histopathological images could further improve feature extraction, and downstream prediction performance.We used 100,000 annotated HE image patches for colorectal cancer (CRC) to finetune a pretrained…
FS-Net: Full Scale Network and Adaptive Threshold for Improving Extraction of Micro-Retinal Vessel Structures
Skolkovo Institute of Science and Technology (Skoltech)（斯科尔科沃科学技术研究院（斯科尔泰克））；Artificial Intelligence Research Institute (AIRI)（人工智能研究院（AIRI））；University of Sharjah（沙迦大学）；Bian Que AI（扁鹊人工智能）；University College London（伦敦大学学院）；Research Institute for Medical and Health Sciences（医学与健康科学研究院）
Road network and building footprint extraction is essential for many applications such as updating maps, traffic regulations, city planning, ride-hailing, disaster response \textit{etc}. Mapping road networks is currently both expensive and labor-intensive. Recently, improvements in image segmentation through the application of deep neural networks has shown promising results in extracting road segments from large scale, high resolution satellite imagery. However, significant challenges remain due to lack of enough labeled training data needed to build models for industry grade applications. I…
Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
The clustering of autonomous driving scenario data can substantially benefit the autonomous driving validation and simulation systems by improving the simulation tests' completeness and fidelity. This article proposes a comprehensive data clustering framework for a large set of vehicle driving data. Existing algorithms utilize handcrafted features whose quality relies on the judgments of human experts. Additionally, the related feature compression methods are not scalable for a large data-set. Our approach thoroughly considers the traffic elements, including both in-traffic agent objects and m…
