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.

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.

Starość w nauczaniu św. Bazylego Wielkiego

Vox Patrum ◽  
2011 ◽  
Vol 56 ◽  
pp. 339-348
Author(s):  
Bogdan Czyżewski
Keyword(s):  
Old Age ◽  
Spiritual Maturity ◽  
The Other ◽  
Interesting Aspect ◽  
Other Hand ◽  
Physical Suffering ◽  
Way Of Thinking ◽  
Almost All

Although St. Basil did not live 50 years, the topic of the old age appears in his works quite often. On the other hand, it is clear that Basil does not discuss this issue in one par­ticular work or in the longer argumentation. The fragmentary statements about old age can be found in almost all his works, but most of them can be found in the correspondence of Basil. In this paper we present the most important ad the most interesting aspect of teach­ing of Basil the Great. As these certificates show that the bishop of Caesarea looked at the old age maturely, rationally estimated passage of time, which very often makes a man different. He experienced it, for example as a spiritual and physical suffering, which often were connected with his person. He saw a lot of aspect of the old age, especially its advan­tages – spiritual maturity and wisdom. What is more, he pointed also to passage of time, which leads a man to eternity, which should be prepared to, regardless how old he is. In his opinion fear is not seen opinions of St. Basil present really Christian way of thinking, well-balanced and calm.

scholarly journals Geometric property-based convolutional neural network for indoor object detection

2021 ◽  
Vol 18 (1) ◽  
pp. 172988142199332
Author(s):  
Xintao Ding ◽  
Boquan Li ◽  
Jinbao Wang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Geometric Property ◽  
Ground Truth ◽  
Geometric Constraints ◽  
Depth Information ◽  
Training Set ◽  
Object Knowledge ◽  
The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

Descriptions of the larvae of four species of Procladius from Great Slave Lake (Chironomidae:Diptera)

1978 ◽  
Vol 56 (9) ◽  
pp. 2055-2057 ◽  
Author(s):  
J. W. Moore ◽  
I. A. Moore
Keyword(s):  
Antennal Segment ◽  
The Other ◽  
Large Size ◽  
Great Slave Lake ◽  
Palpal Segment ◽  
Almost All

Descriptions of larvae of Procladius denticulatus, Procladius culiciformis, Procladius freemani, and Procladius bellus collected from Yellowknife Bay (lat., 62°25′; long., 114°20′) are given. Procladius denticulatus was separated from the other species by its large size, a character which always proved distinctive. Procladius culiciformis and P. freemani were separated from one another through several measurements including those of the basal antennal segment and the basal palpal segment. Almost all characters of the head were useful in distinguishing the much smaller P. bellus from the other species.

scholarly journals A Novel Method of Object Detection from a Moving Camera Based on Image Matching and Frame Coupling

PLoS ONE ◽  
2014 ◽  
Vol 9 (10) ◽  
pp. e109809 ◽  
Author(s):  
Yong Chen ◽  
Rong hua Zhang ◽  
Lei Shang
Keyword(s):  
Object Detection ◽  
Image Matching ◽  
Moving Camera ◽  
Novel Method

scholarly journals Geographical matching of volatile signals and pollinator olfactory responses in a cycad brood-site mutualism

2015 ◽  
Vol 282 (1816) ◽  
pp. 20152053 ◽  
Author(s):  
Terence N. Suinyuy ◽  
John S. Donaldson ◽  
Steven D. Johnson
Keyword(s):  
Choice Experiments ◽  
Local Region ◽  
The Other ◽  
Beetle Species ◽  
Olfactory Preference ◽  
Olfactory Responses ◽  
Volatile Emissions ◽  
Extant Species ◽  
Insect Pollinators ◽  
Almost All

Brood-site mutualisms represent extreme levels of reciprocal specialization between plants and insect pollinators, raising questions about whether these mutualisms are mediated by volatile signals and whether these signals and insect responses to them covary geographically in a manner expected from coevolution. Cycads are an ancient plant lineage in which almost all extant species are pollinated through brood-site mutualisms with insects. We investigated whether volatile emissions and insect olfactory responses are matched across the distribution range of the African cycad Encephalartos villosus . This cycad species is pollinated by the same beetle species across its distribution, but cone volatile emissions are dominated by alkenes in northern populations, and by monoterpenes and a pyrazine compound in southern populations. In reciprocal choice experiments, insects chose the scent of cones from the local region over that of cones from the other region. Antennae of beetles from northern populations responded mainly to alkenes, while those of beetles from southern populations responded mainly to pyrazine. In bioassay experiments, beetles were most strongly attracted to alkenes in northern populations and to the pyrazine compound in southern populations. Geographical matching of cone volatiles and pollinator olfactory preference is consistent with coevolution in this specialized mutualism.

Anna Karenina: The Dialectic of Prophecy

PMLA ◽  
1964 ◽  
Vol 79 (3) ◽  
pp. 266-282
Author(s):  
David H. Stewart
Keyword(s):  
Nineteenth Century ◽  
The Other ◽  
Moby Dick ◽  
Anna Karenina ◽  
Symbolic Value ◽  
Almost All ◽  
The Way

One of the most impressive features of Anna Karenina is the way in which Tolstoy draws the reader's imagination beyond the literal level of the narrative into generalizations that seem mythical in a manner difficult to articulate. With Dostoevsky or Melville, one sees immediately a propensity for exploiting the symbolic value of things. With Tolstoy, things try, as it were, to resist conversion: they strive to maintain their “thingness” as empirical entities. A character in Dostoevsky is usually only half man; the other half is Christ or Satan. Moby Dick is obviously only half whale; the other half is Evil or some principle of Nature. But Anna Karenina is emphatically Anna Karenina. Like almost all of Tolstoy's characters, she has a proficiency in the husbandry of identity; she jealously hoards her own unique reality, so that it becomes difficult to say of her that she is a “type” of nineteenth-century Russian lady or a “symbol” of modern woman or an “archetypical” Eve or Lilith.

scholarly journals Experimental Comparison between Event and Global Shutter Cameras

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1137
Author(s):  
Ondřej Holešovský ◽  
Radoslav Škoviera ◽  
Václav Hlaváč ◽  
Roman Vítek
Keyword(s):  
High Speed ◽  
Ground Truth ◽  
Motion Blur ◽  
Position Estimation ◽  
Estimation Accuracy ◽  
Experimental Comparison ◽  
Estimation Errors ◽  
Detection Rates ◽  
Ballistic Experiment ◽  
Event Camera

We compare event-cameras with fast (global shutter) frame-cameras experimentally, asking: “What is the application domain, in which an event-camera surpasses a fast frame-camera?” Surprisingly, finding the answer has been difficult. Our methodology was to test event- and frame-cameras on generic computer vision tasks where event-camera advantages should manifest. We used two methods: (1) a controlled, cheap, and easily reproducible experiment (observing a marker on a rotating disk at varying speeds); (2) selecting one challenging practical ballistic experiment (observing a flying bullet having a ground truth provided by an ultra-high-speed expensive frame-camera). The experimental results include sampling/detection rates and position estimation errors as functions of illuminance and motion speed; and the minimum pixel latency of two commercial state-of-the-art event-cameras (ATIS, DVS240). Event-cameras respond more slowly to positive than to negative large and sudden contrast changes. They outperformed a frame-camera in bandwidth efficiency in all our experiments. Both camera types provide comparable position estimation accuracy. The better event-camera was limited by pixel latency when tracking small objects, resulting in motion blur effects. Sensor bandwidth limited the event-camera in object recognition. However, future generations of event-cameras might alleviate bandwidth limitations.

Resolving the Lourinia armata (Claus, 1866) complex with remarks on the monophyletic status of Louriniidae, Monard 1927 (Copepoda: Harpacticoida)

Zootaxa ◽  
2021 ◽  
Vol 5051 (1) ◽  
pp. 346-386
Author(s):  
SÜPHAN KARAYTUĞ ◽  
SERDAR SAK ◽  
ALP ALPER ◽  
SERDAR SÖNMEZ
Keyword(s):  
Comparative Evaluation ◽  
Species Complex ◽  
Detailed Examination ◽  
The Other ◽  
Phylogenetic Position ◽  
Nicobar Island ◽  
Other Hand ◽  
The Family ◽  
Close Relationship ◽  
Almost All

An attempt was made to test if Lourinia armata (Claus, 1866)—as it is currently diagnosed—represents a species complex. Detailed examination and comparisons of several specimens collected from different localities suggest that L. armata indeed represents a complex of four closely related morphospecies that can be differentiated from one another by only detailed observations. One of the four species is identified as Lourinia aff. armata and the other three species are described as new to science and named as Lourinia wellsi sp. nov., L. gocmeni sp. nov., and L. aldabraensis sp. nov. Detailed review of previous species records indicates that the genus Lourinia Wilson, 1924 is distributed worldwide. Ceyloniella nicobarica Sewell, 1940, originally described from Nicobar Island and previously considered a junior subjective synonym of L. armata is reinstated as Lourinia nicobarica (Sewell, 1940) comb. nov. on the basis of the unique paddle-shaped caudal ramus seta V. It is postulated that almost all of these records are unreliable in terms of representing true Lourinia aff. armata described herein. On the other hand, the comparative evaluation of the illustrations and descriptions in the published literature indicates the presence of several new species waiting to be discovered in the genus Lourinia.                 It has been determined that, according to updated modern keys, the recent inclusion of the monotypic genus Archeolourinia Corgosinho & Schizas, 2013 in the Louriniidae is not justified since Archeolourinia shermani Corgosinho & Schizas, 2013 does not belong to this family but should be assigned to the Canthocamptidae. On the other hand, it has been argued that the exact phylogenetic position of the Louriniidae still remains problematic since none of the diagnostic characters supports the monophyly of the family within the Oligoarthra. It has also been argued that the close relationship between Louriniidae and Canthocamptidae is supported since both families share the homologous sexual dimorphism (apophysis) on P3 endopod. The most important characteristic that can possibly be used to define Louriniidae is the reduction of maxilliped.  

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.

Sign in / Sign up

Export Citation Format

Share Document