This paper presents a novel method to involve both spatial and temporal features for semantic segmentation of street scenes. Current work on convolutional neural networks (CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for the semantic segmentation task. We investigate how involving temporal features also has a good effect on segmenti...

Garbage is useless goods/materials used normally or specifically in production, goods damaged during production materials which mainly come from households. Moreover, inorganic waste very difficult and takes a longer time to be decomposed by the soil. The lack of public knowledge about classification types how process it causes serious problem Indonesia. Therefore, this research creates type re...

Although some believe it has been wiped out, the coronavirus is striking again. Controlling this epidemic necessitates early detection of disease. Computed tomography (CT) scan images allow fast and accurate screening for COVID-19. This study seeks to develop most precise model identifying classifying COVID-19 by developing an automated approach using transfer-learning CNN models as a base. Tra...

Deep learning approaches have shown to be useful in assisting physicians making decisions about cancer, heart disease, degenerative brain disorders, and eye disease. In this work, a deep model was proposed for the diagnosis of retinal diseases utilizing optical coherence tomography X-ray pictures (OCT) identify four states retina The consists three different convolutional neural network (CNN) m...

With the massive outbreak of coronavirus (COVID-19) disease, demand for automatic and quick detection COVID-19 has become a crucial challenge scientists around world. Many researchers are working on finding an automated effective system detecting COVID-19. They have found that computed tomography (CT-scan) X-ray images infected patients can provide more accurate faster results. In this paper, i...

Detecting insulators on a power transmission line is of great importance for the safe operation systems. Aiming at problem missed detection and misjudgment original feature extraction network VGG16 faster region-convolutional neural (R-CNN) in face different sizes, order to improve accuracy insulators’ lines, an improved R-CNN algorithm proposed. The replaces backbone with Resnet50 deeper layer...

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving many state-of-the-art (SOA) visual processing tasks. Even though Graphical Processing Units (GPUs) are most often used in training and deploying CNNs, their power consumption becomes a problem for real time mobile applications. We propose a flexible and efficient CNN accelerator architecture wh...

Autonomous driving has various visual perception tasks such as object detection, motion detection, depth estimation and flow estimation. Multi-task learning (MTL) has been successfully used for jointly estimating some of these tasks. Previous work was focused on utilizing appearance cues. In this paper, we address the gap of incorporating motion cues in a multi-task learning system. We propose ...

In the present scenario, Deep Learning (DL) is one of most popular research algorithms to increase accuracy data analysis. Due intra-class differences and inter-class variation, image classification difficult jobs in processing. Plant or spinach recognition deep learning applications through its leaf. Spinach more critical for human skin, bone, hair, etc. It provides vitamins, iron, minerals, p...

It is an inevitable trend to detect and recognize the states of different component on distribution cabinet panel more effectively accurately by using inspection robots instead manpower. Aiming at problems multiple recognition targets large size difference in image panel, improved Faster R-CNN multi-target detection method designed. Automatically required achieved this method. In paper, Resnet5...