scholarly journals Efficient Shot Detector: Lightweight Network Based on Deep Learning Using Feature Pyramid

2021 ◽  
Vol 11 (18) ◽  
pp. 8692
Author(s):  
Chansoo Park ◽  
Sanghun Lee ◽  
Hyunho Han
Keyword(s):  
Deep Learning ◽  
Detection Efficiency ◽  
Rapid Development ◽  
Extraction Process ◽  
General Purpose ◽  
Learning Technologies ◽  
Detection Accuracy ◽  
Data Set ◽  
Small Parameters ◽  
Feature Pyramid

Convolutional-neural-network (CNN)-based methods are continuously used in various industries with the rapid development of deep learning technologies. However, an inference efficiency problem was reported in applications that require real-time performance, such as a mobile device. It is important to design a lightweight network that can be used in general-purpose environments such as mobile environments and GPU environments. In this study, we propose a lightweight network efficient shot detector (ESDet) based on deep training with small parameters. The feature extraction process was performed using depthwise and pointwise convolution to minimize the computational complexity of the proposed network. The subsequent layer was formed in a feature pyramid structure to ensure that the extracted features were robust to multiscale objects. The network was trained by defining a prior box optimized for the data set of each feature scale. We defined an ESDet-baseline with optimal parameters through experiments and expanded it by gradually increasing the input resolution for detection accuracy. ESDet training and evaluation was performed using the PASCAL VOC and MS COCO2017 Dataset. Moreover, the average precision (AP) evaluation index was used for quantitative evaluation of detection performance. Finally, superior detection efficiency was demonstrated through the experiment compared to the conventional detection method.

scholarly journals Research on Network Security Application Based on Deep Learning

CONVERTER ◽  
2021 ◽  
pp. 598-605
Author(s):  
Zhao Jianchao
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Rapid Development ◽  
Internet Security ◽  
Detection Accuracy ◽  
Data Sets ◽  
Learning Technology ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Internet Industry

Behind the rapid development of the Internet industry, Internet security has become a hidden danger. In recent years, the outstanding performance of deep learning in classification and behavior prediction based on massive data makes people begin to study how to use deep learning technology. Therefore, this paper attempts to apply deep learning to intrusion detection to learn and classify network attacks. Aiming at the nsl-kdd data set, this paper first uses the traditional classification methods and several different deep learning algorithms for learning classification. This paper deeply analyzes the correlation among data sets, algorithm characteristics and experimental classification results, and finds out the deep learning algorithm which is relatively good at. Then, a normalized coding algorithm is proposed. The experimental results show that the algorithm can improve the detection accuracy and reduce the false alarm rate.

scholarly journals A Target Detection Algorithm for Remote Sensing Images Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-6
Author(s):  
Yi Lv ◽  
Zhengbo Yin ◽  
Zhezhou Yu
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Target Detection ◽  
Detection Efficiency ◽  
False Positive Rate ◽  
Remote Sensing Image ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Data Set ◽  
Detection Effect

In order to improve the accuracy of remote sensing image target detection, this paper proposes a remote sensing image target detection algorithm DFS based on deep learning. Firstly, dimension clustering module, loss function, and sliding window segmentation detection are designed. The data set used in the experiment comes from GoogleEarth, and there are 6 types of objects: airplanes, boats, warehouses, large ships, bridges, and ports. Training set, verification set, and test set contain 73490 images, 22722 images, and 2138 images, respectively. It is assumed that the number of detected positive samples and negative samples is A and B, respectively, and the number of undetected positive samples and negative samples is C and D, respectively. The experimental results show that the precision-recall curve of DFS for six types of targets shows that DFS has the best detection effect for bridges and the worst detection effect for boats. The main reason is that the size of the bridge is relatively large, and it is clearly distinguished from the background in the image, so the detection difficulty is low. However, the target of the boat is very small, and it is easy to be mixed with the background, so it is difficult to detect. The MAP of DFS is improved by 12.82%, the detection accuracy is improved by 13%, and the recall rate is slightly decreased by 1% compared with YOLOv2. According to the number of detection targets, the number of false positives (FPs) of DFS is much less than that of YOLOv2. The false positive rate is greatly reduced. In addition, the average IOU of DFS is 11.84% higher than that of YOLOv2. For small target detection efficiency and large remote sensing image detection, the DFS algorithm has obvious advantages.

scholarly journals Real-Time Detection of Railway Track Component via One-Stage Deep Learning Networks

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4325
Author(s):  
Tiange Wang ◽  
Fangfang Yang ◽  
Kwok-Leung Tsui
Keyword(s):  
Deep Learning ◽  
Learning Technologies ◽  
Railway Track ◽  
Detection Accuracy ◽  
Learning Approaches ◽  
Learning Networks ◽  
Railway Transportation ◽  
One Stage ◽  
Input Size ◽  
Feature Pyramid

Railway inspection has always been a critical task to guarantee the safety of the railway transportation. The development of deep learning technologies brings new breakthroughs in the accuracy and speed of image-based railway inspection application. In this work, a series of one-stage deep learning approaches, which are fast and accurate at the same time, are proposed to inspect the key components of railway track including rail, bolt, and clip. The inspection results show that the enhanced model, the second version of you only look once (YOLOv2), presents the best component detection performance with 93% mean average precision (mAP) at 35 image per second (IPS), whereas the feature pyramid network (FPN) based model provides a smaller mAP and much longer inference time. Besides, the detection performances of more deep learning approaches are evaluated under varying input sizes, where larger input size usually improves the detection accuracy but results in a longer inference time. Overall, the YOLO series models could achieve faster speed under the same detection accuracy.

Semi supervised inspection algorithm of automatic packaging curve based on deep learning

2021 ◽  
pp. 1-10
Author(s):  
Yong He
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Optimization Algorithm ◽  
Posterior Probability ◽  
Detection Method ◽  
Detection System ◽  
Experimental Results ◽  
Detection Accuracy ◽  
Data Set ◽  
Packaging Process

The current automatic packaging process is complex, requires high professional knowledge, poor universality, and difficult to apply in multi-objective and complex background. In view of this problem, automatic packaging optimization algorithm has been widely paid attention to. However, the traditional automatic packaging detection accuracy is low, the practicability is poor. Therefore, a semi-supervised detection method of automatic packaging curve based on deep learning and semi-supervised learning is proposed. Deep learning is used to extract features and posterior probability to classify unlabeled data. KDD CUP99 data set was used to verify the accuracy of the algorithm. Experimental results show that this method can effectively improve the performance of automatic packaging curve semi-supervised detection system.

scholarly journals A Review of Intelligent Driving Pedestrian Detection Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Di Tian ◽  
Yi Han ◽  
Biyao Wang ◽  
Tian Guan ◽  
Wei Wei
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Rapid Development ◽  
Pedestrian Detection ◽  
Evaluation Criteria ◽  
Human Perception ◽  
Detection Accuracy ◽  
Learning Stage ◽  
Detection Technology ◽  
General Object

Pedestrian detection is a specific application of object detection. Compared with general object detection, it shows similarities and unique characteristics. In addition, it has important application value in the fields of intelligent driving and security monitoring. In recent years, with the rapid development of deep learning, pedestrian detection technology has also made great progress. However, there still exists a huge gap between it and human perception. Meanwhile, there are still a lot of problems, and there remains a lot of room for research. Regarding the application of pedestrian detection in intelligent driving technology, it is of necessity to ensure its real-time performance. Additionally, it is necessary to lighten the model while ensuring detection accuracy. This paper first briefly describes the development process of pedestrian detection and then concentrates on summarizing the research results of pedestrian detection technology in the deep learning stage. Subsequently, by summarizing the pedestrian detection dataset and evaluation criteria, the core issues of the current development of pedestrian detection are analyzed. Finally, the next possible development direction of pedestrian detection technology is explained at the end of the paper.

scholarly journals Robust Self-Adaptation Fall-Detection System Based on Camera Height

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3768 ◽  
Author(s):  
Kong ◽  
Chen ◽  
Wang ◽  
Chen ◽  
Meng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Detection System ◽  
Fall Detection ◽  
Daily Activities ◽  
Detection Methods ◽  
Depth Camera ◽  
Detection Accuracy ◽  
Data Set ◽  
Human Segmentation ◽  
Self Adaptation

Vision-based fall-detection methods have been previously studied but many have limitations in terms of practicality. Due to differences in rooms, users do not set the camera or sensors at the same height. However, few studies have taken this into consideration. Moreover, some fall-detection methods are lacking in terms of practicality because only standing, sitting and falling are taken into account. Hence, this study constructs a data set consisting of various daily activities and fall events and studies the effect of camera/sensor height on fall-detection accuracy. Each activity in the data set is carried out by eight participants in eight directions and taken with the depth camera at five different heights. Many related studies heavily depended on human segmentation by using Kinect SDK but this is not reliable enough. To address this issue, this study proposes Enhanced Tracking and Denoising Alex-Net (ETDA-Net) to improve tracking and denoising performance and classify fall and non-fall events. Experimental results indicate that fall-detection accuracy is affected by camera height, against which ETDA-Net is robust, outperforming traditional deep learning based fall-detection methods.

scholarly journals Chinese Character Boxes: Single Shot Detector Network for Chinese Character Detection

2019 ◽  
Vol 9 (2) ◽  
pp. 315 ◽  
Author(s):  
Junhwan Ryu ◽  
Sungho Kim
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Chinese Character ◽  
Layer Structure ◽  
Single Step ◽  
Single Shot ◽  
Data Set ◽  
Pyramid Structure ◽  
Feature Pyramid ◽  
Translation Systems

This paper proposes a deep learning-based Chinese character detection network which is important for character recognition and translation. Detecting the correct character area is an important part of recognition and translation. Previous studies have focused on methods using projection through image pre-processing and recognition methods based on segmentation and methods using hand-crafted features such as analyzing and using features. Unfortunately, the results are vulnerable to noise. Recently, recognition or translation systems based on deep learning were dealt with as a single step from detection to translation but they failed to consider the inaccurate localization problem that arises in detectors. This paper proposes a Chinese character boxes (CCB) network that deals with a method to detect the character area more accurately using the single-shot multibox detector (SSD) as the baseline and called CCB-SSD. The proposed CCB-SSD network has a single prediction layer structure in which unnecessary layers are removed from the feature-pyramid structure. The augmentation method for training is introduced and the problem caused by the use of default boxes is solved by using the proposed non-maximum suppression (NMS). The experimental results revealed a 96.1% detection rate and 0.89 performance against the false positives per character (FPPC) which is the proposed false positive index for the character data-set and caoshu data-set used in this paper. This method showed better performance than the conventional SSD with 69.4% and 6.57 FPPC.

scholarly journals A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method

Scanning ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Lun Zhao ◽  
Yunlong Pan ◽  
Sen Wang ◽  
Liang Zhang ◽  
Md Shafiqul Islam
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Crack Detection ◽  
Rapid Development ◽  
Detection Accuracy ◽  
Learning Method ◽  
Sem Images ◽  
Bounding Boxes ◽  
Scanning Electron

The scanning electron microscope (SEM) is widely used in the analysis and research of materials, including fracture analysis, microstructure morphology, and nanomaterial analysis. With the rapid development of materials science and computer vision technology, the level of detection technology is constantly improving. In this paper, the deep learning method is used to intelligently identify microcracks in the microscopic morphology of SEM image. A deep learning model based on image level is selected to reduce the interference of other complex microscopic topography, and a detection method with dense continuous bounding boxes suitable for SEM images is proposed. The dense and continuous bounding boxes were used to obtain the local features of the cracks and rotating the bounding boxes to reduce the feature differences between the bounding boxes. Finally, the bounding boxes with filled regression were used to highlight the microcrack detection effect. The results show that the detection accuracy of our approach reached 71.12%, and the highest mIOU reached 64.13%. Also, microcracks in different magnifications and in different backgrounds were detected successfully.

scholarly journals NSD-SSD: A Novel Real-Time Ship Detector Based on Convolutional Neural Network in Surveillance Video

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Jiuwu Sun ◽  
Zhijing Xu ◽  
Shanshan Liang
Keyword(s):  
Real Time ◽  
Clustering Algorithm ◽  
Detection Efficiency ◽  
Rapid Development ◽  
Outdoor Environment ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Single Shot ◽  
Ship Detection ◽  
Real Time Detection

With the rapid development of the marine industry, intelligent ship detection plays a very important role in the marine traffic safety and the port management. Current detection methods mainly focus on synthetic aperture radar (SAR) images, which is of great significance to the field of ship detection. However, these methods sometimes cannot meet the real-time requirement. To solve the problems, a novel ship detection network based on SSD (Single Shot Detector), named NSD-SSD, is proposed in this paper. Nowadays, the surveillance system is widely used in the indoor and outdoor environment, and its combination with deep learning greatly promotes the development of intelligent object detection and recognition. The NSD-SSD uses visual images captured by surveillance cameras to achieve real-time detection and further improves detection performance. First, dilated convolution and multiscale feature fusion are combined to improve the small objects’ performance and detection accuracy. Second, an improved prediction module is introduced to enhance deeper feature extraction ability of the model, and the mean Average Precision (mAP) and recall are significant improved. Finally, the prior boxes are reconstructed by using the K-means clustering algorithm, the Intersection-over-Union (IoU) is higher, and the visual effect is better. The experimental results based on ship images show that the mAP and recall can reach 89.3% and 93.6%, respectively, which outperforms the representative model (Faster R-CNN, SSD, and YOLOv3). Moreover, our model’s FPS is 45, which can meet real-time detection acquirement well. Hence, the proposed method has the better overall performance and achieves higher detection efficiency and better robustness.

scholarly journals Ablation studies on YOLOFruit detection algorithm for fruit harvesting robot using deep learning

2021 ◽  
Vol 922 (1) ◽  
pp. 012001
Author(s):  
O M Lawal ◽  
Z Huamin ◽  
Z Fan
Keyword(s):  
Detection Efficiency ◽  
Activation Function ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Detection Time ◽  
Detection Algorithms ◽  
Spatial Pyramid Pooling ◽  
Feature Pyramid ◽  
Harvesting Robot ◽  
Spatial Pyramid

Abstract Fruit detection algorithm as an integral part of harvesting robot is expected to be robust, accurate, and fast against environmental factors such as occlusion by stem and leaves, uneven illumination, overlapping fruit and many more. For this reason, this paper explored and compared ablation studies on proposed YOLOFruit, YOLOv4, and YOLOv5 detection algorithms. The final selected YOLOFruit algorithm used ResNet43 backbone with Combined activation function for feature extraction, Spatial Pyramid Pooling Network (SPPNet) for detection accuracies, Feature Pyramid Network (FPN) for feature pyramids, Distance Intersection Over Union-Non Maximum Suppression (DIoU-NMS) for detection efficiency and accuracy, and Complete Intersection Over Union (CIoU) loss for faster and better performance. The obtained results showed that the average detection accuracy of YOLOFruit at 86.2% is 1% greater than YOLOv4 at 85.2% and 4.3% higher than YOLOv5 at 81.9%, while the detection time of YOLOFruit at 11.9ms is faster than YOLOv4 at 16.6ms, but not with YOLOv5 at 2.7ms. Hence, the YOLOFruit detection algorithm is highly prospective for better generalization and real-time fruit detection.

Sign in / Sign up

Export Citation Format

Share Document