The effects of different levels of realism on the training of CNNs with only synthetic images for the semantic segmentation of robotic instruments in a head phantom

2020 ◽  
Vol 15 (8) ◽  
pp. 1257-1265
Author(s):  
Saul Alexis Heredia Perez ◽  
Murilo Marques Marinho ◽  
Kanako Harada ◽  
Mamoru Mitsuishi
Keyword(s):  
Semantic Segmentation ◽  
Synthetic Images ◽  
Robotic Instruments ◽  
Different Levels

scholarly journals Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3813
Author(s):  
Athanasios Anagnostis ◽  
Aristotelis C. Tagarakis ◽  
Dimitrios Kateris ◽  
Vasileios Moysiadis ◽  
Claus Grøn Sørensen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Automated Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Field Boundary ◽  
Different Seasons ◽  
Detection And Localization ◽  
Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

scholarly journals Importance-Aware Semantic Segmentation for Autonomous Driving System

2017 ◽  
Author(s):  
Bi-ke Chen ◽  
Chen Gong ◽  
Jian Yang
Keyword(s):  
Deep Neural Networks ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Learning Models ◽  
Safe Driving ◽  
Driving System ◽  
Backward Propagation ◽  
Autonomous Driving System ◽  
Propagation Rules ◽  
Different Levels

Semantic Segmentation (SS) partitions an image into several coherent semantically meaningful parts, and classifies each part into one of the pre-determined classes. In this paper, we argue that existing SS methods cannot be reliably applied to autonomous driving system as they ignore the different importance levels of distinct classes for safe-driving. For example, pedestrians in the scene are much more important than sky when driving a car, so their segmentations should be as accurate as possible. To incorporate the importance information possessed by various object classes, this paper designs an "Importance-Aware Loss" (IAL) that specifically emphasizes the critical objects for autonomous driving. IAL operates under a hierarchical structure, and the classes with different importance are located in different levels so that they are assigned distinct weights. Furthermore, we derive the forward and backward propagation rules for IAL and apply them to deep neural networks for realizing SS in intelligent driving system. The experiments on CamVid and Cityscapes datasets reveal that by employing the proposed loss function, the existing deep learning models including FCN, SegNet and ENet are able to consistently obtain the improved segmentation results on the pre-defined important classes for safe-driving.

scholarly journals Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation

2019 ◽  
Vol 33 ◽  
pp. 5581-5588 ◽  
Author(s):  
Yonghao Xu ◽  
Bo Du ◽  
Lefei Zhang ◽  
Qian Zhang ◽  
Guoli Wang ◽  
...  
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Great Success ◽  
Learning Models ◽  
Target Domain ◽  
Attention Networks ◽  
Source Domain ◽  
Benchmark Datasets ◽  
Different Levels

Recent years have witnessed the great success of deep learning models in semantic segmentation. Nevertheless, these models may not generalize well to unseen image domains due to the phenomenon of domain shift. Since pixel-level annotations are laborious to collect, developing algorithms which can adapt labeled data from source domain to target domain is of great significance. To this end, we propose self-ensembling attention networks to reduce the domain gap between different datasets. To the best of our knowledge, the proposed method is the first attempt to introduce selfensembling model to domain adaptation for semantic segmentation, which provides a different view on how to learn domain-invariant features. Besides, since different regions in the image usually correspond to different levels of domain gap, we introduce the attention mechanism into the proposed framework to generate attention-aware features, which are further utilized to guide the calculation of consistency loss in the target domain. Experiments on two benchmark datasets demonstrate that the proposed framework can yield competitive performance compared with the state of the art methods.

scholarly journals Semantic Text Segmentation from Synthetic Images of Full-Text Documents

2019 ◽  
Vol 18 (6) ◽  
pp. 1381-1406 ◽  
Author(s):  
Lukáš Bureš ◽  
Ivan Gruber ◽  
Petr Neduchal ◽  
Miroslav Hlaváč ◽  
Marek Hrúz
Keyword(s):  
Full Text ◽  
Network Architecture ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Rate ◽  
Semantic Segmentation ◽  
Text Documents ◽  
Text Corpora ◽  
Novel Approach ◽  
Synthetic Images

An algorithm (divided into multiple modules) for generating images of full-text documents is presented. These images can be used to train, test, and evaluate models for Optical Character Recognition (OCR). The algorithm is modular, individual parts can be changed and tweaked to generate desired images. A method for obtaining background images of paper from already digitized documents is described. For this, a novel approach based on Variational AutoEncoder (VAE) to train a generative model was used. These backgrounds enable the generation of similar background images as the training ones on the fly.The module for printing the text uses large text corpora, a font, and suitable positional and brightness character noise to obtain believable results (for natural-looking aged documents). A few types of layouts of the page are supported. The system generates a detailed, structured annotation of the synthesized image. Tesseract OCR to compare the real-world images to generated images is used. The recognition rate is very similar, indicating the proper appearance of the synthetic images. Moreover, the errors which were made by the OCR system in both cases are very similar. From the generated images, fully-convolutional encoder-decoder neural network architecture for semantic segmentation of individual characters was trained. With this architecture, the recognition accuracy of 99.28% on a test set of synthetic documents is reached.

scholarly journals Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation

2017 ◽  
Author(s):  
Tong Shen ◽  
Guosheng Lin ◽  
Chunhua Shen ◽  
Ian Reid
Keyword(s):  
Image Segmentation ◽  
Semantic Segmentation ◽  
Image Understanding ◽  
Network Module ◽  
Convolutional Network ◽  
Semantic Image Segmentation ◽  
Fully Convolutional Network ◽  
Multi Level ◽  
Different Levels ◽  
Semantic Labelling

Semantic image segmentation is a fundamental task in image understanding. Per-pixel semantic labelling of an image benefits greatly from the ability to consider region consistency both locally and globally. However, many Fully Convolutional Network based methods do not impose such consistency, which may give rise to noisy and implausible predictions. We address this issue by proposing a dense multi-label network module that is able to encourage the region consistency at different levels. This simple but effective module can be easily integrated into any semantic segmentation systems. With comprehensive experiments, we show that the dense multi-label can successfully remove the implausible labels and clear the confusion so as to boost the performance of semantic segmentation systems.

scholarly journals Incremental and Multi-Task Learning Strategies for Coarse-To-Fine Semantic Segmentation

Technologies ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 1 ◽  
Author(s):  
Mazen Mel ◽  
Umberto Michieli ◽  
Pietro Zanuttigh
Keyword(s):  
Neural Network ◽  
New York ◽  
Learning Strategies ◽  
Deep Neural Network ◽  
Semantic Segmentation ◽  
New York University ◽  
Multi Level ◽  
Segmentation Task ◽  
Coarse To Fine ◽  
Different Levels

The semantic understanding of a scene is a key problem in the computer vision field. In this work, we address the multi-level semantic segmentation task where a deep neural network is first trained to recognize an initial, coarse, set of a few classes. Then, in an incremental-like approach, it is adapted to segment and label new objects’ categories hierarchically derived from subdividing the classes of the initial set. We propose a set of strategies where the output of coarse classifiers is fed to the architectures performing the finer classification. Furthermore, we investigate the possibility to predict the different levels of semantic understanding together, which also helps achieve higher accuracy. Experimental results on the New York University Depth v2 (NYUDv2) dataset show promising insights on the multi-level scene understanding.

Dependence of Intergranular Fracture on Boundary Topography and Cohesion

1973 ◽  
Vol 31 ◽  
pp. 150-151
Author(s):  
J. E. Doherty ◽  
A. F. Giamei ◽  
B. H. Kear ◽  
C. W. Steinke
Keyword(s):  
Grain Boundary ◽  
Room Temperature ◽  
Nickel Base Superalloy ◽  
Boundary Shear ◽  
Room Temperature Ductility ◽  
Solid Solution Matrix ◽  
Nickel Base ◽  
Solution Matrix ◽  
Different Levels ◽  
Base Superalloy

Recently we have been investigating a class of nickel-base superalloys which possess substantial room temperature ductility. This improvement in ductility is directly related to improvements in grain boundary strength due to increased boundary cohesion through control of detrimental impurities and improved boundary shear strength by controlled grain boundary micros true tures.For these investigations an experimental nickel-base superalloy was doped with different levels of sulphur impurity. The micros tructure after a heat treatment of 1360°C for 2 hr, 1200°C for 16 hr consists of coherent precipitates of γ’ Ni3(Al,X) in a nickel solid solution matrix.

Immunoenzymatic demonstration of the simultaneous presence of transferrin, hemopexin and albumin in a same hepatocyte and their ultrastructural localization

1978 ◽  
Vol 36 (2) ◽  
pp. 88-89
Author(s):  
M. Kraemer ◽  
J. Foucrier ◽  
J. Vassy ◽  
M.T. Chalumeau
Keyword(s):  
Plasma Proteins ◽  
Rat Hepatocytes ◽  
Ultrastructural Localization ◽  
Carrier Proteins ◽  
Normal Cells ◽  
Adult Rat ◽  
Adult Rat Hepatocytes ◽  
Monospecific Antisera ◽  
Different Levels

Some authors using immunofluorescent techniques had already suggested that some hepatocytes are able to synthetize several plasma proteins. In vitro studies on normal cells or on cells issued of murine hepatomas raise the same conclusion. These works could be indications of an hepatocyte functionnal non-specialization, meanwhile the authors never give direct topographic proofs suitable with this hypothesis.The use of immunoenzymatic techniques after obtention of monospecific antisera had seemed to us useful to bring forward a better knowledge of this problem. We have studied three carrier proteins (transferrin = Tf, hemopexin = Hx, albumin = Alb) operating at different levels in iron metabolism by demonstrating and localizing the adult rat hepatocytes involved in their synthesis.Immunological, histological and ultrastructural methods have been described in a previous work.

Sign in / Sign up

Export Citation Format

Share Document