scholarly journals ABOships—An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations

2021 ◽  
Vol 13 (5) ◽  
pp. 988
Author(s):  
Bogdan Iancu ◽  
Valentin Soloviev ◽  
Luca Zelioli ◽  
Johan Lilius
Keyword(s):  
Object Detection ◽  
The Other ◽  
Object Size ◽  
Atmospheric Conditions ◽  
Large Object ◽  
Detection Algorithms ◽  
Domain Specific ◽  
Vessel Detection ◽  
Feature Extractor ◽  
Essential Problem

Availability of domain-specific datasets is an essential problem in object detection. Datasets of inshore and offshore maritime vessels are no exception, with a limited number of studies addressing maritime vessel detection on such datasets. For that reason, we collected a dataset consisting of images of maritime vessels taking into account different factors: background variation, atmospheric conditions, illumination, visible proportion, occlusion and scale variation. Vessel instances (including nine types of vessels), seamarks and miscellaneous floaters were precisely annotated: we employed a first round of labelling and we subsequently used the CSRT tracker to trace inconsistencies and relabel inadequate label instances. Moreover, we evaluated the out-of-the-box performance of four prevalent object detection algorithms (Faster R-CNN, R-FCN, SSD and EfficientDet). The algorithms were previously trained on the Microsoft COCO dataset. We compared their accuracy based on feature extractor and object size. Our experiments showed that Faster R-CNN with Inception-Resnet v2 outperforms the other algorithms, except in the large object category where EfficientDet surpasses the latter.

scholarly journals AUTOMATIC SHADOW DETECTION IN AERIAL AND TERRESTRIAL IMAGES

2017 ◽  
Vol 23 (4) ◽  
pp. 578-590 ◽  
Author(s):  
Vander Luis de Souza Freitas ◽  
Barbara Maximino da Fonseca Reis ◽  
Antonio Maria Garcia Tommaselli
Keyword(s):  
Object Detection ◽  
Image Matching ◽  
Ground Truth ◽  
Position Estimation ◽  
Color Images ◽  
The Other ◽  
Object Size ◽  
Atmospheric Scattering ◽  
Spectrum Ratio ◽  
Almost All

Abstract: Shadows exist in almost all aerial and outdoor images, and they can be useful for estimating Sun position estimation or measuring object size. On the other hand, they represent a problem in processes such as object detection/recognition, image matching, etc., because they may be confused with dark objects and change the image radiometric properties. We address this problem on aerial and outdoor color images in this work. We use a filter to find low intensities as a first step. For outdoor color images, we analyze spectrum ratio properties to refine the detection, and the results are assessed with a dataset containing ground truth. For the aerial case we validate the detections depending of the hue component of pixels. This stage takes into account that, in deep shadows, most pixels have blue or violet wavelengths because of an atmospheric scattering effect.

Choose you own scientific experiment: Triggering debris flows and flash floods

2016 ◽  
Author(s):  
Thea Turkington
Keyword(s):  
Debris Flows ◽  
Flash Floods ◽  
The Other ◽  
Background Information ◽  
Atmospheric Conditions ◽  
Scientific Experiment

Landslides and flash floods result in many fatalities around the globe. Understanding what triggers these events is therefore vital, although how to approach this problem is not straight forward. After background information for the experiment and some guidelines, two options are presented to learn more about the triggers of debris flows: (A) using rainfall or (B) the atmospheric conditions. You can then choose the option that appears more useful and interesting to you (you can always go back and read the other experiment afterwards). The article then ends with a reflection on the results.

Annual Variability in Summer Evapotranspiration and Water Balance at a Subarctic Forest Site

1994 ◽  
Vol 25 (5) ◽  
pp. 331-344 ◽  
Author(s):  
Peter M. Lafleur
Keyword(s):  
Water Balance ◽  
Daily Precipitation ◽  
The Other ◽  
Forest Site ◽  
Net Radiation ◽  
Atmospheric Conditions ◽  
Surface Moisture ◽  
Equilibrium Evaporation ◽  
Subarctic Forest ◽  
Single Regression

Evapotranspiration (ET) and precipitation were measured during five summers (1989-1993 inclusive) at a subarctic forest site near Churchill, Manitoba, Canada. Mean daily ET varied from 2.14-3.18 mm d−1 during the five summers, while mean daily precipitation (P) ranged from 1.46-3.15 mm d−1. Yearly variability in summer ET was most influenced by availability of surface moisture, then by atmospheric conditions (i.e. temperature), and least of all by net radiation. In four of the five years total summer ET exceeded P resulting in significant soil water deficits and in the other year summer ET and P were similar in magnitude. The use of equilibrium evaporation (EE) as a predictor of ET was explored. Separate relationships between ET and EE were computed for all five years. Three statistically dissimilar groups of equations were found: 1989/1990, 1991/ 1992, and 1993. A single regression equation describing all years is presented.

A dual U-Net algorithm for automating feature extraction from satellite imagery

2021 ◽  
pp. 154851292098354
Author(s):  
Samuel Humphries ◽  
Trevor Parker ◽  
Bryan Jonas ◽  
Bryan Adams ◽  
Nicholas J Clark
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Satellite Images ◽  
Detection Algorithm ◽  
Military Operations ◽  
Detection Algorithms ◽  
Us Military ◽  
Standard Product ◽  
Different Types ◽  
Road Intersections

Quick identification of building and roads is critical for execution of tactical US military operations in an urban environment. To this end, a gridded, referenced, satellite images of an objective, often referred to as a gridded reference graphic or GRG, has become a standard product developed during intelligence preparation of the environment. At present, operational units identify key infrastructure by hand through the work of individual intelligence officers. Recent advances in Convolutional Neural Networks, however, allows for this process to be streamlined through the use of object detection algorithms. In this paper, we describe an object detection algorithm designed to quickly identify and label both buildings and road intersections present in an image. Our work leverages both the U-Net architecture as well the SpaceNet data corpus to produce an algorithm that accurately identifies a large breadth of buildings and different types of roads. In addition to predicting buildings and roads, our model numerically labels each building by means of a contour finding algorithm. Most importantly, the dual U-Net model is capable of predicting buildings and roads on a diverse set of test images and using these predictions to produce clean GRGs.

Field Assessment of Camera Based Drilling Dynamics

2021 ◽  
Author(s):  
Alexis Koulidis ◽  
Mohamed Abdullatif ◽  
Ahmed Galal Abdel-Kader ◽  
Mohammed-ilies Ayachi ◽  
Shehab Ahmed ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Real Time ◽  
Tracking Algorithm ◽  
Interest Points ◽  
Stick Slip ◽  
Detection Algorithms ◽  
Point Tracking ◽  
Surface Data ◽  
Field Assessment

Abstract Surface data measurement and analysis are an established mean of detecting drillstring low-frequency torsional vibration or stick-slip. The industry has also developed models that link surface torque and downhole drill bit rotational speed. Cameras provide an alternative noninvasive approach to existing wired/wireless sensors used to gather such surface data. The results of a preliminary field assessment of drilling dynamics utilizing camera-based drillstring monitoring are presented in this work. Detection and timing of events from the video are performed using computer vision techniques and object detection algorithms. A real-time interest point tracker utilizing homography estimation and sparse optical flow point tracking is deployed. We use a fully convolutional deep neural network trained to detect interest points and compute their accompanying descriptors. The detected points and descriptors are matched across video sequences and used for drillstring rotation detection and speed estimation. When the drillstring's vibration is invisible to the naked eye, the point tracking algorithm is preceded with a motion amplification function based on another deep convolutional neural network. We have clearly demonstrated the potential of camera-based noninvasive approaches to surface drillstring dynamics data acquisition and analysis. Through the application of real-time object detection algorithms on rig video feed, surface events were detected and timed. We were also able to estimate drillstring rotary speed and motion profile. Torsional drillstring modes can be identified and correlated with drilling parameters and bottomhole assembly design. A novel vibration array sensing approach based on a multi-point tracking algorithm is also proposed. A vibration threshold setting was utilized to enable an additional motion amplification function providing seamless assessment for multi-scale vibration measurement. Cameras were typically devices to acquire images/videos for offline automated assessment (recently) or online manual monitoring (mainly), this work has shown how fog/edge computing makes it possible for these cameras to be "conscious" and "intelligent," hence play a critical role in automation/digitalization of drilling rigs. We showcase their preliminary application as drilling dynamics and rig operations sensors in this work. Cameras are an ideal sensor for a drilling environment since they can be installed anywhere on a rig to perform large-scale live video analytics on drilling processes.

scholarly journals Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3415 ◽  
Author(s):  
Jinpeng Zhang ◽  
Jinming Zhang ◽  
Shan Yu
Keyword(s):  
Object Detection ◽  
Sampling Method ◽  
Ground Truth ◽  
Detection Accuracy ◽  
Two Stage ◽  
Baseline Model ◽  
Detection Algorithms ◽  
Imbalance Problem ◽  
Image Object Detection ◽  
Image Object

In the image object detection task, a huge number of candidate boxes are generated to match with a relatively very small amount of ground-truth boxes, and through this method the learning samples can be created. But in fact the vast majority of the candidate boxes do not contain valid object instances and should be recognized and rejected during the training and evaluation of the network. This leads to extra high computation burden and a serious imbalance problem between object and none-object samples, thereby impeding the algorithm’s performance. Here we propose a new heuristic sampling method to generate candidate boxes for two-stage detection algorithms. It is generally applicable to the current two-stage detection algorithms to improve their detection performance. Experiments on COCO dataset showed that, relative to the baseline model, this new method could significantly increase the detection accuracy and efficiency.

scholarly journals Object detection networks and augmented reality for cellular detection in fluorescence microscopy

2020 ◽  
Vol 219 (10) ◽  
Author(s):  
Dominic Waithe ◽  
Jill M. Brown ◽  
Katharina Reglinski ◽  
Isabel Diez-Sevilla ◽  
David Roberts ◽  
...  
Keyword(s):  
Augmented Reality ◽  
Fluorescence Microscopy ◽  
Object Detection ◽  
High Performance ◽  
Back Projection ◽  
Detection Algorithms ◽  
High Classification Accuracy ◽  
Fast Processing ◽  
Automate Detection ◽  
Very High

Object detection networks are high-performance algorithms famously applied to the task of identifying and localizing objects in photography images. We demonstrate their application for the classification and localization of cells in fluorescence microscopy by benchmarking four leading object detection algorithms across multiple challenging 2D microscopy datasets. Furthermore we develop and demonstrate an algorithm that can localize and image cells in 3D, in close to real time, at the microscope using widely available and inexpensive hardware. Furthermore, we exploit the fast processing of these networks and develop a simple and effective augmented reality (AR) system for fluorescence microscopy systems using a display screen and back-projection onto the eyepiece. We show that it is possible to achieve very high classification accuracy using datasets with as few as 26 images present. Using our approach, it is possible for relatively nonskilled users to automate detection of cell classes with a variety of appearances and enable new avenues for automation of fluorescence microscopy acquisition pipelines.

Sign in / Sign up

Export Citation Format

Share Document