scholarly journals Simultaneous Semantic Segmentation and Depth Completion with Constraint of Boundary

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 635 ◽  
Author(s):  
Nan Zou ◽  
Zhiyu Xiang ◽  
Yiman Chen ◽  
Shuya Chen ◽  
Chengyu Qiao
Keyword(s):  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Vital Role ◽  
Learning Technologies ◽  
Learning Framework ◽  
Network Training ◽  
Real Scene ◽  
Relationship Of ◽  
Inner Constraints ◽  
Entire Network

As the core task of scene understanding, semantic segmentation and depth completion play a vital role in lots of applications such as robot navigation, AR/VR and autonomous driving. They are responsible for parsing scenes from the angle of semantics and geometry, respectively. While great progress has been made in both tasks through deep learning technologies, few works have been done on building a joint model by deeply exploring the inner relationship of the above tasks. In this paper, semantic segmentation and depth completion are jointly considered under a multi-task learning framework. By sharing a common encoder part and introducing boundary features as inner constraints in the decoder part, the two tasks can properly share the required information from each other. An extra boundary detection sub-task is responsible for providing the boundary features and constructing cross-task joint loss functions for network training. The entire network is implemented end-to-end and evaluated with both RGB and sparse depth input. Experiments conducted on synthesized and real scene datasets show that our proposed multi-task CNN model can effectively improve the performance of every single task.

scholarly journals Weakly-Supervised Recommended Traversable Area Segmentation Using Automatically Labeled Images for Autonomous Driving in Pedestrian Environment with No Edges

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 437
Author(s):  
Yuya Onozuka ◽  
Ryosuke Matsumi ◽  
Motoki Shino
Keyword(s):  
Visual Information ◽  
Data Augmentation ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Weighting Method ◽  
Personal Mobility ◽  
Human Understanding ◽  
Autonomous Mobility ◽  
Weakly Supervised ◽  
Traffic Rules

Detection of traversable areas is essential to navigation of autonomous personal mobility systems in unknown pedestrian environments. However, traffic rules may recommend or require driving in specified areas, such as sidewalks, in environments where roadways and sidewalks coexist. Therefore, it is necessary for such autonomous mobility systems to estimate the areas that are mechanically traversable and recommended by traffic rules and to navigate based on this estimation. In this paper, we propose a method for weakly-supervised recommended traversable area segmentation in environments with no edges using automatically labeled images based on paths selected by humans. This approach is based on the idea that a human-selected driving path more accurately reflects both mechanical traversability and human understanding of traffic rules and visual information. In addition, we propose a data augmentation method and a loss weighting method for detecting the appropriate recommended traversable area from a single human-selected path. Evaluation of the results showed that the proposed learning methods are effective for recommended traversable area detection and found that weakly-supervised semantic segmentation using human-selected path information is useful for recommended area detection in environments with no edges.

RSNet: Rail semantic segmentation network for extracting aerial railroad images

2021 ◽  
pp. 1-18
Author(s):  
R.S. Rampriya ◽  
Sabarinathan ◽  
R. Suganya
Keyword(s):  
Real Time ◽  
Visual Processing ◽  
Feature Fusion ◽  
Semantic Segmentation ◽  
Vital Role ◽  
Obstacle Detection ◽  
Aerial Images ◽  
Computationally Efficient ◽  
Fusion Algorithm ◽  
Uav Images

In the near future, combo of UAV (Unmanned Aerial Vehicle) and computer vision will play a vital role in monitoring the condition of the railroad periodically to ensure passenger safety. The most significant module involved in railroad visual processing is obstacle detection, in which caution is obstacle fallen near track gage inside or outside. This leads to the importance of detecting and segment the railroad as three key regions, such as gage inside, rails, and background. Traditional railroad segmentation methods depend on either manual feature selection or expensive dedicated devices such as Lidar, which is typically less reliable in railroad semantic segmentation. Also, cameras mounted on moving vehicles like a drone can produce high-resolution images, so segmenting precise pixel information from those aerial images has been challenging due to the railroad surroundings chaos. RSNet is a multi-level feature fusion algorithm for segmenting railroad aerial images captured by UAV and proposes an attention-based efficient convolutional encoder for feature extraction, which is robust and computationally efficient and modified residual decoder for segmentation which considers only essential features and produces less overhead with higher performance even in real-time railroad drone imagery. The network is trained and tested on a railroad scenic view segmentation dataset (RSSD), which we have built from real-time UAV images and achieves 0.973 dice coefficient and 0.94 jaccard on test data that exhibits better results compared to the existing approaches like a residual unit and residual squeeze net.

scholarly journals Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

2021 ◽  
Vol 13 (16) ◽  
pp. 3065
Author(s):  
Libo Wang ◽  
Rui Li ◽  
Dongzhi Wang ◽  
Chenxi Duan ◽  
Teng Wang ◽  
...  
Keyword(s):  
Large Scale ◽  
Texture Features ◽  
Semantic Segmentation ◽  
Autonomous Driving ◽  
Research Field ◽  
Learning Approaches ◽  
Fine Grained ◽  
Urban Scene ◽  
Fine Resolution ◽  
With Memory

Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, urban planning, etc. However, the tremendous details contained in the VFR image, especially the considerable variations in scale and appearance of objects, severely limit the potential of the existing deep learning approaches. Addressing such issues represents a promising research field in the remote sensing community, which paves the way for scene-level landscape pattern analysis and decision making. In this paper, we propose a Bilateral Awareness Network which contains a dependency path and a texture path to fully capture the long-range relationships and fine-grained details in VFR images. Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation. In addition, using the linear attention mechanism, a feature aggregation module is designed to effectively fuse the dependency features and texture features. Extensive experiments conducted on the three large-scale urban scene image segmentation datasets, i.e., ISPRS Vaihingen dataset, ISPRS Potsdam dataset, and UAVid dataset, demonstrate the effectiveness of our BANet. Specifically, a 64.6% mIoU is achieved on the UAVid dataset.

scholarly journals A Deep Learning Approach on Building Detection from Unmanned Aerial Vehicle-Based Images in Riverbank Monitoring

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3921 ◽  
Author(s):  
Wuttichai Boonpook ◽  
Yumin Tan ◽  
Yinghua Ye ◽  
Peerapong Torteeka ◽  
Kritanai Torsri ◽  
...  
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Semantic Segmentation ◽  
Water Levels ◽  
Building Detection ◽  
Network Training ◽  
Building Information ◽  
Open Standard ◽  
Uav Images ◽  
Uav Image

Buildings along riverbanks are likely to be affected by rising water levels, therefore the acquisition of accurate building information has great importance not only for riverbank environmental protection but also for dealing with emergency cases like flooding. UAV-based photographs are flexible and cloud-free compared to satellite images and can provide very high-resolution images up to centimeter level, while there exist great challenges in quickly and accurately detecting and extracting building from UAV images because there are usually too many details and distortions on UAV images. In this paper, a deep learning (DL)-based approach is proposed for more accurately extracting building information, in which the network architecture, SegNet, is used in the semantic segmentation after the network training on a completely labeled UAV image dataset covering multi-dimension urban settlement appearances along a riverbank area in Chongqing. The experiment results show that an excellent performance has been obtained in the detection of buildings from untrained locations with an average overall accuracy more than 90%. To verify the generality and advantage of the proposed method, the procedure is further evaluated by training and testing with another two open standard datasets which have a variety of building patterns and styles, and the final overall accuracies of building extraction are more than 93% and 95%, respectively.

Zebrafish embryos exposed to deltamethrin exhibit abnormalities despite induced expression of related genes (you, you-too, momo and u-boot)

2018 ◽  
Vol 35 (1) ◽  
pp. 11-19
Author(s):  
Kuder Reshma Shabnam ◽  
Dharmapuri Gangappa ◽  
Gundala Harold Philip
Keyword(s):  
Vital Role ◽  
Primary Objective ◽  
Chain Reaction ◽  
Environmental Persistence ◽  
Expression Of Genes ◽  
Pericardial Edema ◽  
Eye Pigmentation ◽  
Polymerase Chain ◽  
Relationship Of ◽  
The Relationship

Evaluation of the toxic effects of a widely used synthetic pyrethroid, deltamethrin (DM), was carried out in this study. This pesticide is preferred for pest control because of its low environmental persistence and toxicity. We investigated the expression pattern of four genes, namely, you ( you), yot ( you-too), momo ( mom) and ubo ( u-boot) during early development of zebrafish, that is, from 12 hpf to 48 hpf stages. These stages are selected as most of the important developmental aspects take place during this period. All four genes are known to play a vital role in development of notochord and somites. To understand the effect of DM on development, embryos of 4 hpf stage were exposed to two concentrations (100 and 200 µg/L) of DM, and observations were made at 12, 24 and 48 hpf stages. Our earlier studies have shown phenotypic abnormalities such as notochord bending, tail deformation, yolk sac and pericardial edema, lightening of body and eye pigmentation and interfered in somite patterning, during these stages of development. Understanding the relationship of phenotypic abnormalities with these four genes has been our primary objective. These four genes were analyzed by Reverse transcription (RT)-polymerase chain reaction and intensity of the bands has shown induction in their expression after exposure to the toxicant. In spite of the expression of genes, it was noticed that DM caused abnormalities. It can be said from the results that translational pathway could have been affected.

Deep Semantic Segmentation in Autonomous Driving

2020 ◽  
pp. 151-182
Author(s):  
Hazem Rashed ◽  
Senthil Yogamani ◽  
Ahmad El-Sallab ◽  
Mohamed Elhelw ◽  
Mahmoud Hassaballah
Keyword(s):  
Semantic Segmentation ◽  
Autonomous Driving

scholarly journals Russian Students’ Readiness for Distance Learning: Current Situation and Future Challenges

2021 ◽  
Vol 25 (2) ◽  
pp. 80-97
Author(s):  
V. N. Kiroy ◽  
D. N. Sherbina ◽  
A. A. Chernova ◽  
E. G. Denisova ◽  
D. M. Lazurenko
Keyword(s):  
Higher Education ◽  
Distance Learning ◽  
Digital Literacy ◽  
Online Courses ◽  
Learning Technologies ◽  
Internet Technologies ◽  
Future Challenges ◽  
Distance Learning Technologies ◽  
Relationship Of ◽  
The Relationship

In the context of the COVID pandemic, there has dramatically increased the significance of distance learning technologies. Higher education will most probably increase their usage even after overcoming the coronavirus. This paper aims at assessing Russian university students’ readiness to exercise distance learning technologies. The survey within Rostov-on-Don universities provided data on 428 students’ skills in using Internet technologies when studying. It is shown that in the pre-pandemic period, no more than a quarter of students had the necessary skills to participate in video conferences, and about 16 % of students took online courses autonomously. Only 6,5 % of the respondents could manage both technologies that comprise distance learning. The results obtained on the relationship between academic performance and self-participation in online courses, as well as on the relationship of these indicators with general digital literacy and immersion in social networks, should be taken into account within wide computerization of education during the pandemic.

scholarly journals Determination of Factors Effecting Medication Adherence in Depressed Patients Receiving Antidepressants in Pakistan

2020 ◽  
Vol 8 (1) ◽  
pp. 1-6 ◽  
Author(s):  
Muhammad Amir ◽  
Nathanial Rickles ◽  
Zeeshan Feroz ◽  
Anwer Ejaz Beg
Keyword(s):  
Medication Adherence ◽  
Significant Influence ◽  
Assessment Tool ◽  
Outpatient Setting ◽  
Vital Role ◽  
Limited Information ◽  
Self Assessment ◽  
Duration Of Therapy ◽  
Depressed Patients ◽  
Relationship Of

Background: The prevalence of depression in Pakistan is considered to be higher than other developing countries. Medication adherence is a major factor in the success and cost effectiveness of the treatment of depression. Limited information relating medication adherence and its factor are available for patients in Pakistan. Objective: The study aim to determine the factors associated with adherence of antidepressants in depressed patients. Methods: The study was conducted in outpatient setting of hospital. 200 participants were enrolled in the study. Self-assessment tool was used to determine the medication adherence. Results: The results showed that factors such as gender, education, employment and total number of medications have significant influence on adherence of antidepressants. The study also shows that the relationship of factors and adherence changes with the duration of therapy. Conclusion: Factors play a vital role in understanding the barriers in medication non-adherence. Factors effecting medication adherence change with respect to the duration of therapy. Gender, employment, morbidity and number of medications taken earlier have significant influence on medication adherence of antidepressants in depressed patients.

Sign in / Sign up

Export Citation Format

Share Document