scholarly journals JRL-YOLO: A Novel Jump-Join Repetitious Learning Structure for Real-Time Dangerous Object Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Yiliang Zeng ◽  
Lihao Zhang ◽  
Jiahong Zhao ◽  
Jinhui Lan ◽  
Biao Li
Keyword(s):  
Target Detection ◽  
Rapid Development ◽  
Experimental Tests ◽  
Detection Accuracy ◽  
The Public ◽  
Percent Increase ◽  
Spatial Pyramid Pooling ◽  
Model Size ◽  
Intelligent Security ◽  
Security Incidents

Campus security incidents occur from time to time, which seriously affect the public security. In recent years, the rapid development of artificial intelligence has brought technical support for campus intelligent security. In order to quickly recognize and locate dangerous targets on campus, an improved YOLOv3-Tiny model is proposed for dangerous target detection. Since the biggest advantage of this model is that it can achieve higher precision with very fewer parameters than YOLOv3-Tiny, it is one of the Tinier-YOLO models. In this paper, the dangerous targets include dangerous objects and dangerous actions. The main contributions of this work include the following: firstly, the detection of dangerous objects and dangerous actions is integrated into one model, and the model can achieve higher accuracy with fewer parameters. Secondly, to solve the problem of insufficient YOLOv3-Tiny target detection, a jump-join repetitious learning (JRL) structure is proposed, combined with the spatial pyramid pooling (SPP), which serves as the new backbone network of YOLOv3-Tiny and can accelerate the speed of feature extraction while integrating features of different scales. Finally, the soft-NMS and DIoU-NMS algorithm are combined to effectively reduce the missing detection when two targets are too close. Experimental tests on self-made datasets of dangerous targets show that the average MAP value of the JRL-YOLO algorithm is 85.03%, which increases by 3.22 percent compared with YOLOv3-Tiny. On the VOC2007 dataset, the proposed method has a 9.29 percent increase in detection accuracy compared to that using YOLOv3-Tiny and a 2.38 percent increase compared to that employing YOLOv4-Tiny, respectively. These results all evidence the great improvement in detection accuracy brought by the proposed method. Moreover, when testing the dataset of dangerous targets, the model size of JRL-YOLO is 5.84 M, which is about one-fifth of the size of YOLOv3-Tiny (33.1 M) and one-third of the size of YOLOv4-Tiny (22.4 M), separately.

scholarly journals AMCD: an accurate deep learning-based metallic corrosion detector for MAV-based real-time visual inspection

2021 ◽  
Author(s):  
Leijian Yu ◽  
Erfu Yang ◽  
Cai Luo ◽  
Peng Ren
Keyword(s):  
Deep Learning ◽  
Visual Inspection ◽  
Safety Issue ◽  
Detection Accuracy ◽  
Corrosion Detection ◽  
Detection Algorithms ◽  
Spatial Pyramid Pooling ◽  
Model Size ◽  
Inspection Tasks ◽  
Metallic Corrosion

AbstractCorrosion has been concerned as a serious safety issue for metallic facilities. Visual inspection carried out by an engineer is expensive, subjective and time-consuming. Micro Aerial Vehicles (MAVs) equipped with detection algorithms have the potential to perform safer and much more efficient visual inspection tasks than engineers. Towards corrosion detection algorithms, convolution neural networks (CNNs) have enabled the power for high accuracy metallic corrosion detection. However, these detectors are restricted by MAVs on-board capabilities. In this study, based on You Only Look Once v3-tiny (Yolov3-tiny), an accurate deep learning-based metallic corrosion detector (AMCD) is proposed for MAVs on-board metallic corrosion detection. Specifically, a backbone with depthwise separable convolution (DSConv) layers is designed to realise efficient corrosion detection. The convolutional block attention module (CBAM), three-scale object detection and focal loss are incorporated to improve the detection accuracy. Moreover, the spatial pyramid pooling (SPP) module is improved to fuse local features for further improvement of detection accuracy. A field inspection image dataset labelled with four types of corrosions (the nubby corrosion, bar corrosion, exfoliation and fastener corrosion) is utilised for training and testing the AMCD. Test results show that the AMCD achieves 84.96% mean average precision (mAP), which outperforms other state-of-the-art detectors. Meanwhile, 20.18 frames per second (FPS) is achieved leveraging NVIDIA Jetson TX2, the most popular MAVs on-board computer, and the model size is only 6.1 MB.

The public and the private: reconfiguring the interrelationship during a civil act

2019 ◽  
pp. 53-69
Author(s):  
Natalia Kostenko
Keyword(s):  
Public Sphere ◽  
Public Space ◽  
Rapid Development ◽  
Online Communication ◽  
Decisive Role ◽  
Physical Interaction ◽  
Bare Life ◽  
Public And Private ◽  
The Public ◽  
The Public Sphere

The subject matter of research interest here is the movement of sociological reflection concerning the interplay of public and private realms in social, political and individual life. The focus is on the boundary constructs embodying publicity, which are, first of all, classical models of the space of appearance for free citizens of the polis (H. Arendt) and the public sphere organised by communicative rationality (Ju. Habermas). Alternative patterns are present in modern ideas pertaining to the significance of biological component in public space in the context of biopolitics (M. Foucault), “inclusive exclusion of bare life” (G. Agamben), as well as performativity of corporeal and linguistic experience related to the right to participate in civil acts such as popular assembly (J. Butler), where the established distinctions between the public and the private are levelled, and the interrelationship of these two realms becomes reconfigured. Once the new media have come into play, both the structure and nature of the public sphere becomes modified. What assumes a decisive role is people’s physical interaction with online communication gadgets, which instantly connect information networks along various trajectories. However, the rapid development of information technology produces particular risks related to the control of communications industry, leaving both public and private realms unprotected and deforming them. This also urges us to rethink the issue of congruence of the two ideas such as transparency of societies and security.

scholarly journals Implementation of a Modified Faster R-CNN for Target Detection Technology of Coastal Defense Radar

2021 ◽  
Vol 13 (9) ◽  
pp. 1703
Author(s):  
He Yan ◽  
Chao Chen ◽  
Guodong Jin ◽  
Jindong Zhang ◽  
Xudong Wang ◽  
...  
Keyword(s):  
False Alarm ◽  
False Alarm Rate ◽  
Target Detection ◽  
Real Data ◽  
Detection Performance ◽  
Detection Accuracy ◽  
Constant False Alarm Rate ◽  
Data Set ◽  
Detection Technology ◽  
Coastal Defense

The traditional method of constant false-alarm rate detection is based on the assumption of an echo statistical model. The target recognition accuracy rate and the high false-alarm rate under the background of sea clutter and other interferences are very low. Therefore, computer vision technology is widely discussed to improve the detection performance. However, the majority of studies have focused on the synthetic aperture radar because of its high resolution. For the defense radar, the detection performance is not satisfactory because of its low resolution. To this end, we herein propose a novel target detection method for the coastal defense radar based on faster region-based convolutional neural network (Faster R-CNN). The main processing steps are as follows: (1) the Faster R-CNN is selected as the sea-surface target detector because of its high target detection accuracy; (2) a modified Faster R-CNN based on the characteristics of sparsity and small target size in the data set is employed; and (3) soft non-maximum suppression is exploited to eliminate the possible overlapped detection boxes. Furthermore, detailed comparative experiments based on a real data set of coastal defense radar are performed. The mean average precision of the proposed method is improved by 10.86% compared with that of the original Faster R-CNN.

scholarly journals Multi-Feature Fusion for Weak Target Detection on Sea-Surface Based on FAR Controllable Deep Forest Model

2021 ◽  
Vol 13 (4) ◽  
pp. 812
Author(s):  
Jiahuan Zhang ◽  
Hongjun Song
Keyword(s):  
Target Detection ◽  
Feature Fusion ◽  
Feature Space ◽  
Sea Surface ◽  
Detection Accuracy ◽  
Forest Model ◽  
High Profile ◽  
Deep Forest ◽  
Positive Effect ◽  
Weak Target

Target detection on the sea-surface has always been a high-profile problem, and the detection of weak targets is one of the most difficult problems and the key issue under this problem. Traditional techniques, such as imaging, cannot effectively detect these types of targets, so researchers choose to start by mining the characteristics of the received echoes and other aspects for target detection. This paper proposes a false alarm rate (FAR) controllable deep forest model based on six-dimensional feature space for efficient and accurate detection of weak targets on the sea-surface. This is the first attempt at the deep forest model in this field. The validity of the model was verified on IPIX data, and the detection probability was compared with other proposed methods. Under the same FAR condition, the average detection accuracy rate of the proposed method could reach over 99.19%, which is 9.96% better than the results of the current most advanced method (K-NN FAR-controlled Detector). Experimental results show that multi-feature fusion and the use of a suitable detection framework have a positive effect on the detection of weak targets on the sea-surface.

scholarly journals Improved YOLO Network for Free-Angle Remote Sensing Target Detection

2021 ◽  
Vol 13 (11) ◽  
pp. 2171
Author(s):  
Yuhao Qing ◽  
Wenyi Liu ◽  
Liuyan Feng ◽  
Wanjia Gao
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Target Detection ◽  
Multiple Scales ◽  
Classification Problem ◽  
Input Image ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Regression Problem ◽  
Public Datasets

Despite significant progress in object detection tasks, remote sensing image target detection is still challenging owing to complex backgrounds, large differences in target sizes, and uneven distribution of rotating objects. In this study, we consider model accuracy, inference speed, and detection of objects at any angle. We also propose a RepVGG-YOLO network using an improved RepVGG model as the backbone feature extraction network, which performs the initial feature extraction from the input image and considers network training accuracy and inference speed. We use an improved feature pyramid network (FPN) and path aggregation network (PANet) to reprocess feature output by the backbone network. The FPN and PANet module integrates feature maps of different layers, combines context information on multiple scales, accumulates multiple features, and strengthens feature information extraction. Finally, to maximize the detection accuracy of objects of all sizes, we use four target detection scales at the network output to enhance feature extraction from small remote sensing target pixels. To solve the angle problem of any object, we improved the loss function for classification using circular smooth label technology, turning the angle regression problem into a classification problem, and increasing the detection accuracy of objects at any angle. We conducted experiments on two public datasets, DOTA and HRSC2016. Our results show the proposed method performs better than previous methods.

scholarly journals Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1820
Author(s):  
Xiaotao Shao ◽  
Qing Wang ◽  
Wei Yang ◽  
Yun Chen ◽  
Yi Xie ◽  
...  
Keyword(s):  
Semantic Information ◽  
Detection System ◽  
Pedestrian Detection ◽  
Detection Accuracy ◽  
The Public ◽  
Scale Feature ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Art Works ◽  
Feature Pyramid

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

scholarly journals Research on Lightweight Infrared Pedestrian Detection Model Algorithm for Embedded Platform

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Zhaoli Wu ◽  
Xin Wang ◽  
Chao Chen
Keyword(s):  
Real Time ◽  
Target Detection ◽  
Pedestrian Detection ◽  
Infrared Image ◽  
Far Infrared ◽  
Detection Algorithm ◽  
Model Parameters ◽  
Detection Accuracy ◽  
Detection Model ◽  
Embedded Platform

Due to the limitation of energy consumption and power consumption, the embedded platform cannot meet the real-time requirements of the far-infrared image pedestrian detection algorithm. To solve this problem, this paper proposes a new real-time infrared pedestrian detection algorithm (RepVGG-YOLOv4, Rep-YOLO), which uses RepVGG to reconstruct the YOLOv4 backbone network, reduces the amount of model parameters and calculations, and improves the speed of target detection; using space spatial pyramid pooling (SPP) obtains different receptive field information to improve the accuracy of model detection; using the channel pruning compression method reduces redundant parameters, model size, and computational complexity. The experimental results show that compared with the YOLOv4 target detection algorithm, the Rep-YOLO algorithm reduces the model volume by 90%, the floating-point calculation is reduced by 93.4%, the reasoning speed is increased by 4 times, and the model detection accuracy after compression reaches 93.25%.

scholarly journals Analyzing the Marketing Instruments in the Sphere of Innovative Entrepreneurship and Creative Industries in the City of Kharkiv

2020 ◽  
Vol 10 (513) ◽  
pp. 420-434
Author(s):  
M. S. Pasmor ◽  
◽  
S. V. Demchenko ◽  
D. V. Zaitseva ◽  
◽  
...  
Keyword(s):  
Rapid Development ◽  
Business Environment ◽  
Modern Human ◽  
Creative Industries ◽  
The Internet ◽  
Public Organization ◽  
The Public ◽  
Modern Business ◽  
On Line ◽  
The City

The topic of development and involvement of marketing instruments in business is relevant nowadays. In the era of the Internet, social networks and open information space, it is extremely important for companies and organizations to learn and implement new marketing instruments in order to utilize and fill the communication channels used by modern human in everyday life. Most marketing instruments, applied by the business environment before 2014–2016, are already becoming irrelevant due to the lack of feedback from the younger generation. From the off-line format, the interaction of business – buyer is increasingly moving to the on-line format. Thanks to the rapid development of digitalization in recent years, enterprises have received new channels of communication with their target audience, and, accordingly, new channels of communication and marketing instruments, which are covered in the publication. The article is aimed at theoretical studying the latest marketing instruments and analyzing their introduction into the creative industries of the city of Kharkiv. The latest marketing instruments are analyzed, examples of their use in the modern business environment of Ukraine are provided. Their adaptability is considered and recommendations for their use in commercial structures are made. Systematized and allocated are purely new marketing instruments used by business in the 21st century. The efficiency of their introduction into the activities of companies and organizations is substantiated and proved on specific examples. In addition, special attention is paid to the extended presentation of their use and disclosure of the essence on the example of the public organization «Kharkiv IT Cluster».

scholarly journals The importance of public health in radiology and radiation protection

2021 ◽  
Author(s):  
Zuzana Bárdyová ◽  
Martina Horváthová ◽  
Katarína Pinčáková ◽  
Darina Budošová
Keyword(s):  
Public Health ◽  
Ionizing Radiation ◽  
Radiation Safety ◽  
Biological Effects ◽  
Rapid Development ◽  
Physical Factors ◽  
Constant Attention ◽  
The Public ◽  
Many Sources ◽  
Safety Knowledge

The ionizing radiation belongs to the basic physical factors that can be measured. We forget often about its risks and the possible damage to our health. The imaging methods which use the ionizing radiation increase the diagnostics quality and they have become a certainty for many medical workers. Therefore, they are being used without rational thinking many times. With this is related to increasing the cumulative dose of patients. Next problem can be radiation safety knowledge of medical workers. The enormous increase in the use of sources ionizing radiation in medicine and rapid development, there may be a disproportionate acquisition of radiation safety knowledge of healthcare workers. At the same time, constant attention must be paid to the biological effects of radiation and realize epidemiology studies. In all the areas mentioned the public health has space. However, it is sad that presently, the radiation safety is not considered important enough in Public Health.  Based on many sources, it is safe to say that this is a major problem, because the public health itself can play an important role in radiation safety. It is important to point out, that safety and effectivity of using the source of ionizing radiation is one of the main components of Good Medical Practice.

scholarly journals Modern Russian Cinema: Expert Characteristics

2020 ◽  
Vol 19 (4) ◽  
pp. 111-118
Author(s):  
A.O. Glotova ◽  
◽  
Keyword(s):  
Film Industry ◽  
Rapid Development ◽  
Research Focus ◽  
Focus Group Discussions ◽  
Group Discussions ◽  
Personal Lives ◽  
The Public ◽  
Living Space ◽  
Russian Cinema ◽  
Modern Russian

the rapid development of the film industry and its ever-increasing integration into the public and personal lives of people can expand the perspective of the living space of a modern person. In this article, the author considers modern Russian cinema as one of the most popular types of contemporary art and analyzes the products of its activities. The article is written on the basis of qualitative research – focus group discussions with experts in the field of cinematographic art and who have at least 3 years of experience in it. Based on the obtained data analysis, the author describe the products of Russian cinematographic art as a whole and consider its features, trends and development vectors. The author of the work classified the images of modern film characters based on the most discussed trends of modern Russian films and identified the properties characteristic of each type of hero.

Sign in / Sign up

Export Citation Format

Share Document