scholarly journals A New Real-Time Detection and Tracking Method in Videos for Small Target Traffic Signs

2021 ◽  
Vol 11 (7) ◽  
pp. 3061
Author(s):  
Shaojian Song ◽  
Yuanchao Li ◽  
Qingbao Huang ◽  
Gang Li
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
Input Image ◽  
Small Sample ◽  
Traffic Signs ◽  
Feature Map ◽  
Detection And Tracking ◽  
Detailed Method ◽  
Tracking Ability ◽  
Small Targets

It is a challenging task for self-driving vehicles in Real-World traffic scenarios to find a trade-off between the real-time performance and the high accuracy of the detection, recognition, and tracking in videos. This issue is addressed in this paper with an improved YOLOv3 (You Only Look Once) and a multi-object tracking algorithm (Deep-Sort). First, data augmentation is employed for small sample traffic signs to address the problem of an extremely unbalanced distribution of different samples in the dataset. Second, a new architecture of YOLOv3 is proposed to make it more suitable for detecting small targets. The detailed method is (1) removing the output feature map corresponding to the 32-times subsampling of the input image in the original YOLOv3 structure to reduce its computational costs and improve its real-time performances; (2) adding an output feature map of 4-times subsampling to improve its detection capability for the small traffic signs; (3) Deep-Sort is integrated into the detection method to improve the precision and robustness of multi-object detection, and the tracking ability in videos. Finally, our method demonstrated better detection capabilities, with respect to state-of-the-art approaches, which precision, recall and mAP is 91%, 90%, and 84.76% respectively.

scholarly journals Improved YOLO Based Detection Algorithm for Floating Debris in Waterway

Entropy ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. 1111
Author(s):  
Feng Lin ◽  
Tian Hou ◽  
Qiannan Jin ◽  
Aiju You
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
Expansion Method ◽  
Detection Algorithm ◽  
Training Dataset ◽  
Visual Index ◽  
Water Plants ◽  
Small Targets ◽  
Data Expansion ◽  
Detection Effect

Various floating debris in the waterway can be used as one kind of visual index to measure the water quality. The traditional image processing method is difficult to meet the requirements of real-time monitoring of floating debris in the waterway due to the complexity of the environment, such as reflection of sunlight, obstacles of water plants, a large difference between the near and far target scale, and so on. To address these issues, an improved YOLOv5s (FMA-YOLOv5s) algorithm by adding a feature map attention (FMA) layer at the end of the backbone is proposed. The mosaic data augmentation is applied to enhance the detection effect of small targets in training. A data expansion method is introduced to expand the training dataset from 1920 to 4800, which fuses the labeled target objects extracted from the original training dataset and the background images of the clean river surface in the actual scene. The comparisons of accuracy and rapidity of six models of this algorithm are completed. The experiment proves that it meets the standards of real-time object detection.

scholarly journals Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yong He ◽  
Hong Zeng ◽  
Yangyang Fan ◽  
Shuaisheng Ji ◽  
Jianjian Wu
Keyword(s):  
Deep Learning ◽  
Integrated Pest Management ◽  
Pest Management ◽  
Real Time ◽  
Oilseed Rape ◽  
Data Augmentation ◽  
Low Cost ◽  
Response Speed ◽  
Original Model ◽  
Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

scholarly journals Universal Stokes’s nanomechanical viscometer

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Komal Chaudhary ◽  
Pooja Munjal ◽  
Kamal P. Singh
Keyword(s):  
Electric Field ◽  
Real Time ◽  
Sample Volume ◽  
Capillary Waves ◽  
Small Sample ◽  
Medical Applications ◽  
Rapid Measurement ◽  
Single Lens ◽  
Universal Applicability ◽  
Small Sample Volume

AbstractAlthough, many conventional approaches have been used to measure viscosity of fluids, most methods do not allow non-contact, rapid measurements on small sample volume and have universal applicability to all fluids. Here, we demonstrate a simple yet universal viscometer, as proposed by Stokes more than a century ago, exploiting damping of capillary waves generated electrically and probed optically with sub-nanoscale precision. Using a low electric field local actuation of fluids we generate quasi-monochromatic propagating capillary waves and employ a pair of single-lens based compact interferometers to measure attenuation of capillary waves in real-time. Our setup allows rapid measurement of viscosity of a wide variety of polar, non-polar, transparent, opaque, thin or thick fluids having viscosity values varying over four orders of magnitude from $$10^{0}{-}10^{4}~\text{mPa} \, \text{s}$$ 10 0 - 10 4 mPa s . Furthermore, we discuss two additional damping mechanisms for nanomechanical capillary waves caused by bottom friction and top nano-layer appearing in micro-litre droplets. Such self-stabilized droplets when coupled with precision interferometers form interesting microscopic platform for picomechanical optofluidics for fundamental, industrial and medical applications.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals PDANet: Self-Supervised Monocular Depth Estimation Using Perceptual and Data Augmentation Consistency

2021 ◽  
Vol 11 (12) ◽  
pp. 5383
Author(s):  
Huachen Gao ◽  
Xiaoyu Liu ◽  
Meixia Qu ◽  
Shijie Huang
Keyword(s):  
Data Augmentation ◽  
State Of The Art ◽  
Depth Estimation ◽  
Input Image ◽  
Depth Information ◽  
Disparity Map ◽  
Estimation Model ◽  
Absolute Relative Error ◽  
Texture Region ◽  
Monocular Depth

In recent studies, self-supervised learning methods have been explored for monocular depth estimation. They minimize the reconstruction loss of images instead of depth information as a supervised signal. However, existing methods usually assume that the corresponding points in different views should have the same color, which leads to unreliable unsupervised signals and ultimately damages the reconstruction loss during the training. Meanwhile, in the low texture region, it is unable to predict the disparity value of pixels correctly because of the small number of extracted features. To solve the above issues, we propose a network—PDANet—that integrates perceptual consistency and data augmentation consistency, which are more reliable unsupervised signals, into a regular unsupervised depth estimation model. Specifically, we apply a reliable data augmentation mechanism to minimize the loss of the disparity map generated by the original image and the augmented image, respectively, which will enhance the robustness of the image in the prediction of color fluctuation. At the same time, we aggregate the features of different layers extracted by a pre-trained VGG16 network to explore the higher-level perceptual differences between the input image and the generated one. Ablation studies demonstrate the effectiveness of each components, and PDANet shows high-quality depth estimation results on the KITTI benchmark, which optimizes the state-of-the-art method from 0.114 to 0.084, measured by absolute relative error for depth estimation.

scholarly journals Caffeine may disrupt the impact of real-time drowsiness on cognitive performance: a double-blind, placebo-controlled small-sample study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
E. Aidman ◽  
M. Balin ◽  
K. Johnson ◽  
S. Jackson ◽  
G. M. Paech ◽  
...  
Keyword(s):  
Real Time ◽  
Cognitive Performance ◽  
Small Sample ◽  
Night Time ◽  
Double Blind ◽  
Infra Red ◽  
Procedural Decisions ◽  
Performance Gains ◽  
The Impact ◽  
Modest Reduction

AbstractCaffeine is widely used to promote alertness and cognitive performance under challenging conditions, such as sleep loss. Non-digestive modes of delivery typically reduce variability of its effect. In a placebo-controlled, 50-h total sleep deprivation (TSD) protocol we administered four 200 mg doses of caffeine-infused chewing-gum during night-time circadian trough and monitored participants' drowsiness during task performance with infra-red oculography. In addition to the expected reduction of sleepiness, caffeine was found to disrupt its degrading impact on performance errors in tasks ranging from standard cognitive tests to simulated driving. Real-time drowsiness data showed that caffeine produced only a modest reduction in sleepiness (compared to our placebo group) but substantial performance gains in vigilance and procedural decisions, that were largely independent of the actual alertness dynamics achieved. The magnitude of this disrupting effect was greater for more complex cognitive tasks.

Sign in / Sign up

Export Citation Format

Share Document