scholarly journals A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1437
Author(s):  
Petar Durdevic ◽  
Daniel Ortiz-Arroyo
Keyword(s):  
Neural Networks ◽  
Wind Turbine ◽  
Stereo Vision ◽  
Visual Servoing ◽  
Deep Neural Networks ◽  
Feedback Signal ◽  
Vision Sensor ◽  
Deep Convolutional Neural Networks ◽  
Field Of Vision ◽  
Stereo Triangulation

This paper describes a novel stereo vision sensor based on deep neural networks, that can be used to produce a feedback signal for visual servoing in unmanned aerial vehicles such as drones. Two deep convolutional neural networks attached to the stereo camera in the drone are trained to detect wind turbines in images and stereo triangulation is used to calculate the distance from a wind turbine to the drone. Our experimental results show that the sensor produces data accurate enough to be used for servoing, even in the presence of noise generated when the drone is not being completely stable. Our results also show that appropriate filtering of the signals is needed and that to produce correct results, it is very important to keep the wind turbine within the field of vision of both cameras, so that both deep neural networks could detect it.

scholarly journals CircConv: A Structured Convolution with Low Complexity

2019 ◽  
Vol 33 ◽  
pp. 4287-4294
Author(s):  
Siyu Liao ◽  
Bo Yuan
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Low Complexity ◽  
Deep Convolutional Neural Networks ◽  
Significant Saving ◽  
Machine Learning Applications ◽  
Fast Multiplication ◽  
Large Model

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structureimposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.

Wind Turbine Gearbox Failure Identification With Deep Neural Networks

2017 ◽  
Vol 13 (3) ◽  
pp. 1360-1368 ◽  
Author(s):  
Long Wang ◽  
Zijun Zhang ◽  
Huan Long ◽  
Jia Xu ◽  
Ruihua Liu
Keyword(s):  
Neural Networks ◽  
Wind Turbine ◽  
Deep Neural Networks ◽  
Wind Turbine Gearbox ◽  
Failure Identification

scholarly journals Detection of Melanoma Skin Cancer with Deep Neural Networks

2019 ◽  
Vol 4 (4) ◽  
Keyword(s):  
Neural Networks ◽  
Skin Cancer ◽  
High Performance ◽  
Deep Neural Networks ◽  
Histopathological Examination ◽  
Skin Lesions ◽  
Image Features ◽  
Test Accuracy ◽  
Data Sets ◽  
Deep Convolutional Neural Networks

Detection of skin cancer involves several steps of examinations first being visual diagnosis that is followed by dermoscopic analysis, a biopsy, and histopathological examination. The classification of skin lesions in the first step is critical and challenging as classes vary by minute appearance in skin lesions. Deep convolutional neural networks (CNNs) have great potential in multicategory image-based classification by considering coarse-to-fine image features. This study aims to demonstrate how to classify skin lesions, in particular, melanoma, using CNN trained on data sets with disease labels. We developed and trained our own CNN model using a subset of the images from International Skin Imaging Collaboration (ISIC) Dermoscopic Archive. To test the performance of the proposed model, we used a different subset of images from the same archive as the test set. Our model is trained to classify images into two categories: malignant melanoma and nevus and is shown to achieve excellent classification results with high test accuracy (91.16%) and high performance as measured by various metrics. Our study demonstrated the potential of using deep neural networks to assist early detection of melanoma and thereby improve the patient survival rate from this aggressive skin cancer.

scholarly journals Exploring Perceptual Illusions in Deep Neural Networks

2019 ◽  
Author(s):  
Emily J. Ward
Keyword(s):  
Neural Networks ◽  
Object Recognition ◽  
Visual Processing ◽  
Visual Information ◽  
Deep Neural Networks ◽  
Perceptual System ◽  
Deep Convolutional Neural Networks ◽  
Perceptual Illusions ◽  
Trained Neural Network ◽  
Level Performance

AbstractPerceptual illusions—discrepancies between what exists externally and what we actually see—reveal a great deal about how the perceptual system functions. Rather than failures of perception, illusions expose automatic computations and biases in visual processing that help make better decisions from visual information to achieve our perceptual goals. Recognizing objects is one such perceptual goal that is shared between humans and certain Deep Convolutional Neural Networks, which can reach human-level performance. Do neural networks trained exclusively for object recognition “perceive” visual illusions, simply as a result of solving this one perceptual problem? Here, I showed four classic illusions to humans and a pre-trained neural network to see if the network exhibits similar perceptual biases. I found that deep neural networks trained exclusively for object recognition exhibit the Müller-Lyer illusion, but not other illusions. This result shows that some perceptual computations that are similar to humans’ may come “for free” in a system with perceptual goals similar to humans’.

scholarly journals Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks

2020 ◽  
Author(s):  
Tuan Hoang ◽  
Thanh-Toan Do ◽  
Tam V. Nguyen ◽  
Ngai-Man Cheung
Keyword(s):  
Neural Networks ◽  
Cost Function ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Gradient Descent ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Deep Convolutional Neural Networks ◽  
Novel Method ◽  
The Cost

This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. However, this approach would result in some mismatch: the gradient descent updates full-precision weights, but it does not update the quantized weights. To address this issue, we propose a novel method that enables direct updating of quantized weights with learnable quantization levels to minimize the cost function using gradient descent. Second, to obtain low bit-width activations, existing works consider all channels equally. However, the activation quantizers could be biased toward a few channels with high-variance. To address this issue, we propose a method to take into account the quantization errors of individual channels. With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the image classification task, using AlexNet, ResNet and MobileNetV2 architectures on CIFAR-100 and ImageNet datasets.

scholarly journals Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning

2018 ◽  
Vol 115 (25) ◽  
pp. E5716-E5725 ◽  
Author(s):  
Mohammad Sadegh Norouzzadeh ◽  
Anh Nguyen ◽  
Margaret Kosmala ◽  
Alexandra Swanson ◽  
Meredith S. Palmer ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Data Extraction ◽  
High Volume ◽  
Camera Trap ◽  
Camera Traps ◽  
Deep Convolutional Neural Networks ◽  
Manual Task ◽  
In The Wild

Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would improve our ability to study and conserve ecosystems. We investigate the ability to automatically, accurately, and inexpensively collect such data, which could help catalyze the transformation of many fields of ecology, wildlife biology, zoology, conservation biology, and animal behavior into “big data” sciences. Motion-sensor “camera traps” enable collecting wildlife pictures inexpensively, unobtrusively, and frequently. However, extracting information from these pictures remains an expensive, time-consuming, manual task. We demonstrate that such information can be automatically extracted by deep learning, a cutting-edge type of artificial intelligence. We train deep convolutional neural networks to identify, count, and describe the behaviors of 48 species in the 3.2 million-image Snapshot Serengeti dataset. Our deep neural networks automatically identify animals with >93.8% accuracy, and we expect that number to improve rapidly in years to come. More importantly, if our system classifies only images it is confident about, our system can automate animal identification for 99.3% of the data while still performing at the same 96.6% accuracy as that of crowdsourced teams of human volunteers, saving >8.4 y (i.e., >17,000 h at 40 h/wk) of human labeling effort on this 3.2 million-image dataset. Those efficiency gains highlight the importance of using deep neural networks to automate data extraction from camera-trap images, reducing a roadblock for this widely used technology. Our results suggest that deep learning could enable the inexpensive, unobtrusive, high-volume, and even real-time collection of a wealth of information about vast numbers of animals in the wild.

Sign in / Sign up

Export Citation Format

Share Document