scholarly journals An efficient encode-decode deep learning network for lane markings instant segmentation

2021 ◽  
Vol 11 (6) ◽  
pp. 4982
Author(s):  
A. Al Mamun ◽  
P. P. Em ◽  
J. Hossen
Keyword(s):  
Deep Learning ◽  
Environmental Conditions ◽  
False Negative ◽  
Distinct Type ◽  
Weather Conditions ◽  
Driver Assistance Systems ◽  
Traffic Condition ◽  
Computational Framework ◽  
Proposed Model ◽  
Deep Learning Network

<span lang="EN-US">Nowadays, advanced driver assistance systems (ADAS) has been incorporated with a distinct type of progressive and essential features. One of the most preliminary and significant features of the ADAS is lane marking detection, which permits the vehicle to keep in a particular road lane itself. It has been detected by utilizing high-specialized, handcrafted features and distinct post-processing approaches lead to less accurate, less efficient, and high computational framework under different environmental conditions. Hence, this research proposed a simple encode-decode deep learning approach under distinguishing environmental effects like different daytime, multiple lanes, different traffic condition, good and medium weather conditions for detecting the lane markings more accurately and efficiently. The proposed model is emphasized on the simple encode-decode Seg-Net framework incorporated with VGG16 architecture that has been trained by using the inequity and cross-entropy losses to obtain more accurate instant segmentation result of lane markings. The framework has been trained and tested on a vast public dataset named Tusimple, which includes around 3.6K training and 2.7 k testing image frames of different environmental conditions. The model has noted the highest accuracy, 96.61%, F1 score 96.34%, precision 98.91%, and recall 93.89%. Also, it has <span>also obtained the lowest 3.125% false positive and 1.259% false-negative value, which transcended some of the previous researches. It is expected to</span> assist significantly in the field of lane markings detection applying deep neural networks.</span>

scholarly journals Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1593 ◽  
Author(s):  
Yanlei Gu ◽  
Huiyang Zhang ◽  
Shunsuke Kamijo
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Body Orientation ◽  
Learning Approaches ◽  
The Public ◽  
Learning Network ◽  
Proposed Model ◽  
Body Boundary ◽  
Public Dataset ◽  
Deep Learning Network

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.

scholarly journals A Novel Feature Representation for Prediction of Global Horizontal Irradiance Using a Bidirectional Model

2021 ◽  
Vol 3 (4) ◽  
pp. 946-965
Author(s):  
Sourav Malakar ◽  
Saptarsi Goswami ◽  
Bhaswati Ganguli ◽  
Amlan Chakrabarti ◽  
Sugata Sen Roy ◽  
...  
Keyword(s):  
Deep Learning ◽  
Solar Energy ◽  
Weather Conditions ◽  
Feature Representation ◽  
Energy Prediction ◽  
Pv Systems ◽  
Proposed Model ◽  
Energy Domain ◽  
Learning Architectures ◽  
Gated Recurrent Unit

Complex weather conditions—in particular clouds—leads to uncertainty in photovoltaic (PV) systems, which makes solar energy prediction very difficult. Currently, in the renewable energy domain, deep-learning-based sequence models have reported better results compared to state-of-the-art machine-learning models. There are quite a few choices of deep-learning architectures, among which Bidirectional Gated Recurrent Unit (BGRU) has apparently not been used earlier in the solar energy domain. In this paper, BGRU was used with a new augmented and bidirectional feature representation. The used BGRU network is more generalized as it can handle unequal lengths of forward and backward context. The proposed model produced 59.21%, 37.47%, and 76.80% better prediction accuracy compared to traditional sequence-based, bidirectional models, and some of the established states-of-the-art models. The testbed considered for evaluation of the model is far more comprehensive and reliable considering the variability in the climatic zones and seasons, as compared to some of the recent studies in India.

scholarly journals Real-Time Color Image Classification Based On Deep Learning Network

2019 ◽  
Vol 54 (5) ◽  
Author(s):  
Mohammed Hamzah Abed ◽  
Atheer Hadi Issa Al-Rammahi ◽  
Mustafa Jawad Radif
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Real Time ◽  
Color Image ◽  
Input Image ◽  
Proposed Model ◽  
Real Time Image ◽  
Deep Learning Network ◽  
Fully Connected ◽  
Time Image

Real-time image classification is one of the most challenging issues in understanding images and computer vision domain. Deep learning methods, especially Convolutional Neural Network (CNN), has increased and improved the performance of image processing and understanding. The performance of real-time image classification based on deep learning achieves good results because the training style, and features that are used and extracted from the input image. This work proposes an interesting model for real-time image classification architecture based on deep learning with fully connected layers to extract proper features. The classification is based on the hybrid GoogleNet pre-trained model. The datasets that are used in this work are 15 scene and UC Merced Land-Use datasets, used to test the proposed model. The proposed model achieved 92.4 and 98.8 as a higher accuracy.

scholarly journals Review methods for breast cancer detection using artificial intelligence and deep learning methods

2021 ◽  
pp. 98-102
Author(s):  
Maryam Naderan
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Cancer Detection ◽  
High Performance ◽  
False Negative ◽  
Main Idea ◽  
New Approach ◽  
Training Time ◽  
Proposed Model ◽  
Convolutional Autoencoder

Nowadays, there are many related works and methods that use Neural Networks to detect the breast cancer. However, usually they do not take into account the training time and the result of False Negative (FN) while training the model. The main idea of this paper is to compare already existing methods for detecting the breast cancer using Deep Learning Algorithms. Moreover, since the breast cancer is one of the most common lethal cancers and early detection helps prevent complications, we propose a new approach and the use of the convolutional autoencoder. This proposed model has shown high performance with sensitivity, precision, and accuracy of 93,50%, 91,60% and 93% respectively.

scholarly journals Newly Built Construction Detection in SAR Images Using Deep Learning

2019 ◽  
Vol 11 (12) ◽  
pp. 1444 ◽  
Author(s):  
Raveerat Jaturapitpornchai ◽  
Masashi Matsuoka ◽  
Naruo Kanemoto ◽  
Shigeki Kuzuoka ◽  
Riho Ito ◽  
...  
Keyword(s):  
Deep Learning ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Weather Conditions ◽  
Google Earth ◽  
Sar Images ◽  
Convolutional Network ◽  
Optical Images ◽  
Sar Data ◽  
Deep Learning Network

Remote sensing data can be utilized to help developing countries monitor the use of land. However, the problem of constant cloud coverage prevents us from taking full advantage of satellite optical images. Therefore, we instead opt to use data from synthetic-aperture radar (SAR), which can capture images of the Earth’s surface regardless of the weather conditions. In this study, we use SAR data to identify newly built constructions. Most studies on change detection tend to detect all of the changes that have a similar temporal change characteristic occurring on two occasions, while we want to identify only the constructions and avoid detecting other changes such as the seasonal change of vegetation. To do so, we study various deep learning network techniques and have decided to propose the fully convolutional network with a skip connection. We train this network with pairs of SAR data acquired on two different occasions from Bangkok and the ground truth, which we manually create from optical images available from Google Earth for all of the SAR pairs. Experiments to assign the most suitable patch size, loss weighting, and epoch number to the network are discussed in this paper. The trained model can be used to generate a binary map that indicates the position of these newly built constructions precisely with the Bangkok dataset, as well as with the Hanoi and Xiamen datasets with acceptable results. The proposed model can even be used with SAR images of the same specific satellite from another orbit direction and still give promising results.

scholarly journals Lane marking detection using simple encode decode deep learning technique: SegNet

2021 ◽  
Vol 11 (4) ◽  
pp. 3032
Author(s):  
A. Al Mamun ◽  
P. P. Em ◽  
J. Hossen
Keyword(s):  
Deep Learning ◽  
Computational Complexity ◽  
False Negative ◽  
Road Accidents ◽  
Financial Loss ◽  
Driver Assistance ◽  
Driver Assistance Systems ◽  
Low Light ◽  
Lane Marking ◽  
Deep Learning Model

<span>In recent times, many innocent people are suffering from sudden death for the sake of unwanted road accidents, which also riveting a lot of financial properties. The researchers have deployed advanced driver assistance systems (ADAS) in which a large number of automated features have been incorporated in the modern vehicles to overcome human mortality as well as financial loss, and lane markings detection is one of them. Many computer vision techniques and intricate image processing approaches have been used for detecting the lane markings by utilizing the handcrafted with highly specialized features. However, the systems have become more challenging due to the computational complexity, overfitting, less accuracy, and incapability to cope up with the intricate environmental conditions. Therefore, this research paper proposed a simple encode-decode deep learning model to detect lane markings under the distinct environmental condition with lower computational complexity. The model is based on SegNet architecture for improving the performance of the existing researches, which is trained by the lane marking dataset containing different complex environment conditions like rain, cloud, low light, curve roads. The model has successfully achieved 96.38% accuracy, 0.0311 false positive, 0.0201 false negative, 0.960 F1 score with a loss of only 1.45%, less overfitting and 428 ms per step that outstripped some of the existing researches. It is expected that this research will bring a significant contribution to the field lane marking detection.</span>

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

Sign in / Sign up

Export Citation Format

Share Document