scholarly journals Gastric polyp detection in gastroscopic images using deep neural network

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0250632
Author(s):  
Chanting Cao ◽  
Ruilin Wang ◽  
Yao Yu ◽  
Hui zhang ◽  
Ying Yu ◽  
...  
Keyword(s):  
Semantic Information ◽  
Detection Method ◽  
Recall Rate ◽  
Feature Maps ◽  
Polyp Detection ◽  
Training Images ◽  
Gastric Polyps ◽  
High Level ◽  
High Level Feature ◽  
Better Than

This paper presents the research results of detecting gastric polyps with deep learning object detection method in gastroscopic images. Gastric polyps have various sizes. The difficulty of polyp detection is that small polyps are difficult to detect from the background. We propose a feature extraction and fusion module and combine it with the YOLOv3 network to form our network. This method performs better than other methods in the detection of small polyps because it can fuse the semantic information of high-level feature maps with low-level feature maps to help small polyps detection. In this work, we use a dataset of gastric polyps created by ourselves, containing 1433 training images and 508 validation images. We train and validate our network on our dataset. In comparison with other methods of polyps detection, our method has a significant improvement in precision, recall rate, F1, and F2 score. The precision, recall rate, F1 score, and F2 score of our method can achieve 91.6%, 86.2%, 88.8%, and 87.2%.

A Saliency Detection Method Based on Wavelet Transform and Simple Priors

2014 ◽  
Vol 602-605 ◽  
pp. 2238-2241
Author(s):  
Jian Kun Chen ◽  
Zhi Wei Kang
Keyword(s):  
Wavelet Transform ◽  
Detection Method ◽  
Saliency Detection ◽  
Visual Saliency ◽  
Feature Maps ◽  
Multi Scale ◽  
Saliency Model ◽  
Proposed Model ◽  
Visual Saliency Model ◽  
Better Than

In this paper, we present a new visual saliency model, which based on Wavelet Transform and simple Priors. Firstly, we create multi-scale feature maps to represent different features from edge to texture in wavelet transform. Then we modulate local saliency at a location and its global saliency, combine the local saliency and global saliency to generate a new saliency .Finally, the final saliency is generated by combining the new saliency and two simple priors (color prior an location prior). Experimental evaluation shows the proposed model can achieve state-of-the-art results and better than the other models on a public available benchmark dataset.

scholarly journals A Multibranch Object Detection Method for Traffic Scenes

2019 ◽  
Vol 2019 ◽  
pp. 1-16
Author(s):  
Jiangfan Feng ◽  
Fanjie Wang ◽  
Siqin Feng ◽  
Yongrong Peng
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Detection Method ◽  
State Of The Art ◽  
Recall Rate ◽  
Small Scale ◽  
Feature Maps ◽  
Time Requirements ◽  
Speed Up

The performance of convolutional neural network- (CNN-) based object detection has achieved incredible success. Howbeit, existing CNN-based algorithms suffer from a problem that small-scale objects are difficult to detect because it may have lost its response when the feature map has reached a certain depth, and it is common that the scale of objects (such as cars, buses, and pedestrians) contained in traffic images and videos varies greatly. In this paper, we present a 32-layer multibranch convolutional neural network named MBNet for fast detecting objects in traffic scenes. Our model utilizes three detection branches, in which feature maps with a size of 16 × 16, 32 × 32, and 64 × 64 are used, respectively, to optimize the detection for large-, medium-, and small-scale objects. By means of a multitask loss function, our model can be trained end-to-end. The experimental results show that our model achieves state-of-the-art performance in terms of precision and recall rate, and the detection speed (up to 33 fps) is fast, which can meet the real-time requirements of industry.

scholarly journals R-CNN-Based Satellite Components Detection in Optical Images

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Yulang Chen ◽  
Jingmin Gao ◽  
Kebei Zhang
Keyword(s):  
Neural Network ◽  
Detection Method ◽  
Recall Rate ◽  
Feature Maps ◽  
Test Set ◽  
Detection Model ◽  
Accurate Detection ◽  
Optical Images ◽  
Imaging Characteristics ◽  
New Feature

The accurate detection of satellite components based on optical images can provide data support for aerospace missions such as pointing and tracking between satellites. However, the traditional target detection method is inefficient when performing calculations and has a low detection precision, especially when the attitude of the satellite and illumination conditions change considerably. To enable the precise detection of satellite components, we analyse the imaging characteristics of a satellite in space and propose a method to detect the satellite components. This approach is based on a regional-based convolutional neural network (R-CNN), and it can enable the accurate detection of various satellite components by using optical images. First, on the basis of the Mask R-CNN, we combine the DenseNet, ResNet, and FPN to construct a new feature extraction structure and obtain the R-CNN based satellite-component-detection model (RSD). The feature maps are extracted and concatenated at a deeper multiscale level, and the feature propagation between each layer is enhanced by providing a dense connection. Next, an information-rich satellite dataset is constructed, which is composed of images of various kinds of satellites from various perspectives and orbital positions. The detection model is trained and optimized on the constructed dataset to obtain the satellite component detection model. Finally, the proposed RSD model and original Mask R-CNN are tested on the same established test set. The experimental results show that the proposed detection model has higher precision, recall rate, and F1 score. Therefore, the proposed approach can effectively detect satellite components, based on optical images.

The “How” of Animacy Effects in Episodic Memory

2015 ◽  
Vol 62 (6) ◽  
pp. 371-384 ◽  
Author(s):  
Patrick Bonin ◽  
Margaux Gelin ◽  
Betty Laroche ◽  
Alain Méot ◽  
Aurélia Bugaiska
Keyword(s):  
Memory Load ◽  
Recall Performance ◽  
Memory Task ◽  
Human Memory ◽  
Recall Rate ◽  
Interactive Imagery ◽  
Ultimate Explanation ◽  
Better Than ◽  
Observation Results

Abstract. Animates are better remembered than inanimates. According to the adaptive view of human memory ( Nairne, 2010 ; Nairne & Pandeirada, 2010a , 2010b ), this observation results from the fact that animates are more important for survival than inanimates. This ultimate explanation of animacy effects has to be complemented by proximate explanations. Moreover, animacy currently represents an uncontrolled word characteristic in most cognitive research ( VanArsdall, Nairne, Pandeirada, & Cogdill, 2015 ). In four studies, we therefore investigated the “how” of animacy effects. Study 1 revealed that words denoting animates were recalled better than those referring to inanimates in an intentional memory task. Study 2 revealed that adding a concurrent memory load when processing words for the animacy dimension did not impede the animacy effect on recall rates. Study 3A was an exact replication of Study 2 and Study 3B used a higher concurrent memory load. In these two follow-up studies, animacy effects on recall performance were again not altered by a concurrent memory load. Finally, Study 4 showed that using interactive imagery to encode animate and inanimate words did not alter the recall rate of animate words but did increase the recall of inanimate words. Taken together, the findings suggest that imagery processes contribute to these effects.

Visible Laser Probing (VLP) with GaP Solid Immersion Lens Demonstrating 110 nm Resolution in Common Laser Probing Applications

2016 ◽  
Author(s):  
Travis Eiles ◽  
Patrick Pardy
Keyword(s):  
Gallium Phosphide ◽  
Fault Isolation ◽  
Solid Immersion Lens ◽  
Laser Probing ◽  
Isolation Methods ◽  
Visible Laser ◽  
High Level ◽  
Industry Needs ◽  
Diameter Reduction ◽  
Better Than

Abstract This paper demonstrates a breakthrough method of visible laser probing (VLP), including an optimized 577 nm laser microscope, visible-sensitive detector, and an ultimate-resolution gallium phosphide-based solid immersion lens on the 10 nm node, showing a 110 nm resolution. This is 2x better than what is achieved with the standard suite of probing systems using typical infrared (IR) wavelengths today. Since VLP provides a spot diameter reduction of 0.5x over IR methods, it is reasonable, based simply on geometry, to project that VLP using the 577 nm laser will meet the industry needs for laser probing for both the 10 nm and 7 nm process nodes. Based on its high level of optimization, including high resolution and specialized solid immersion lens, it is highly likely that this VLP technology will be one of the last optically-based fault isolation methods successfully used.

scholarly journals Person Re-Identification Based on Attention Mechanism and Context Information Fusion

2021 ◽  
Vol 13 (3) ◽  
pp. 72
Author(s):  
Shengbo Chen ◽  
Hongchang Zhang ◽  
Zhou Lei
Keyword(s):  
Information Fusion ◽  
Irrelevant Information ◽  
Features Extraction ◽  
Attention Mechanism ◽  
Cross Entropy ◽  
Context Information ◽  
Feature Map ◽  
High Level ◽  
Surveillance Analysis ◽  
High Level Feature

Person re-identification (ReID) plays a significant role in video surveillance analysis. In the real world, due to illumination, occlusion, and deformation, pedestrian features extraction is the key to person ReID. Considering the shortcomings of existing methods in pedestrian features extraction, a method based on attention mechanism and context information fusion is proposed. A lightweight attention module is introduced into ResNet50 backbone network equipped with a small number of network parameters, which enhance the significant characteristics of person and suppress irrelevant information. Aiming at the problem of person context information loss due to the over depth of the network, a context information fusion module is designed to sample the shallow feature map of pedestrians and cascade with the high-level feature map. In order to improve the robustness, the model is trained by combining the loss of margin sample mining with the loss function of cross entropy. Experiments are carried out on datasets Market1501 and DukeMTMC-reID, our method achieves rank-1 accuracy of 95.9% on the Market1501 dataset, and 90.1% on the DukeMTMC-reID dataset, outperforming the current mainstream method in case of only using global feature.

scholarly journals A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5

2021 ◽  
Vol 13 (9) ◽  
pp. 1619
Author(s):  
Bin Yan ◽  
Pan Fan ◽  
Xiaoyan Lei ◽  
Zhijie Liu ◽  
Fuzeng Yang
Keyword(s):  
Real Time ◽  
Apple Tree ◽  
Detection Method ◽  
Recognition Algorithm ◽  
Medium Size ◽  
Feature Maps ◽  
Detection Algorithms ◽  
Fusion Mode ◽  
Visual Attention Mechanism ◽  
Tree Image

The apple target recognition algorithm is one of the core technologies of the apple picking robot. However, most of the existing apple detection algorithms cannot distinguish between the apples that are occluded by tree branches and occluded by other apples. The apples, grasping end-effector and mechanical picking arm of the robot are very likely to be damaged if the algorithm is directly applied to the picking robot. Based on this practical problem, in order to automatically recognize the graspable and ungraspable apples in an apple tree image, a light-weight apple targets detection method was proposed for picking robot using improved YOLOv5s. Firstly, BottleneckCSP module was improved designed to BottleneckCSP-2 module which was used to replace the BottleneckCSP module in backbone architecture of original YOLOv5s network. Secondly, SE module, which belonged to the visual attention mechanism network, was inserted to the proposed improved backbone network. Thirdly, the bonding fusion mode of feature maps, which were inputs to the target detection layer of medium size in the original YOLOv5s network, were improved. Finally, the initial anchor box size of the original network was improved. The experimental results indicated that the graspable apples, which were unoccluded or only occluded by tree leaves, and the ungraspable apples, which were occluded by tree branches or occluded by other fruits, could be identified effectively using the proposed improved network model in this study. Specifically, the recognition recall, precision, mAP and F1 were 91.48%, 83.83%, 86.75% and 87.49%, respectively. The average recognition time was 0.015 s per image. Contrasted with original YOLOv5s, YOLOv3, YOLOv4 and EfficientDet-D0 model, the mAP of the proposed improved YOLOv5s model increased by 5.05%, 14.95%, 4.74% and 6.75% respectively, the size of the model compressed by 9.29%, 94.6%, 94.8% and 15.3% respectively. The average recognition speeds per image of the proposed improved YOLOv5s model were 2.53, 1.13 and 3.53 times of EfficientDet-D0, YOLOv4 and YOLOv3 and model, respectively. The proposed method can provide technical support for the real-time accurate detection of multiple fruit targets for the apple picking robot.

Deep AI Enabled Ubiquitous Wireless Sensing

2021 ◽  
Vol 54 (2) ◽  
pp. 1-35
Author(s):  
Chenning Li ◽  
Zhichao Cao ◽  
Yunhao Liu
Keyword(s):  
Great Success ◽  
Wireless Sensing ◽  
Ubiquitous Sensing ◽  
Sensing Systems ◽  
The Status ◽  
Sensing Model ◽  
High Level ◽  
Traditional Approaches ◽  
The Internet Of Things ◽  
High Level Feature

With the development of the Internet of Things (IoT), many kinds of wireless signals (e.g., Wi-Fi, LoRa, RFID) are filling our living and working spaces nowadays. Beyond communication, wireless signals can sense the status of surrounding objects, known as wireless sensing , with their reflection, scattering, and refraction while propagating in space. In the last decade, many sophisticated wireless sensing techniques and systems were widely studied for various applications (e.g., gesture recognition, localization, and object imaging). Recently, deep Artificial Intelligence (AI), also known as Deep Learning (DL), has shown great success in computer vision. And some works have initially proved that deep AI can benefit wireless sensing as well, leading to a brand-new step toward ubiquitous sensing. In this survey, we focus on the evolution of wireless sensing enhanced by deep AI techniques. We first present a general workflow of Wireless Sensing Systems (WSSs) which consists of signal pre-processing, high-level feature, and sensing model formulation. For each module, existing deep AI-based techniques are summarized, further compared with traditional approaches. Then, we provide a view of issues and challenges induced by combining deep AI and wireless sensing together. Finally, we discuss the future trends of deep AI to enable ubiquitous wireless sensing.

scholarly journals An Anchor-Free Siamese Network with Multi-Template Update for Object Tracking

Electronics ◽  
2021 ◽  
Vol 10 (9) ◽  
pp. 1067
Author(s):  
Tongtong Yuan ◽  
Wenzhu Yang ◽  
Qian Li ◽  
Yuxia Wang
Keyword(s):  
Object Tracking ◽  
Correlation Energy ◽  
Feature Maps ◽  
Siamese Network ◽  
Template Update ◽  
Free Network ◽  
Multiple Prediction ◽  
Bounding Boxes ◽  
High Level ◽  
Speed And Accuracy

Siamese trackers are widely used in various fields for their advantages of balancing speed and accuracy. Compared with the anchor-based method, the anchor-free-based approach can reach faster speeds without any drop in precision. Inspired by the Siamese network and anchor-free idea, an anchor-free Siamese network (AFSN) with multi-template updates for object tracking is proposed. To improve tracking performance, a dual-fusion method is adopted in which the multi-layer features and multiple prediction results are combined respectively. The low-level feature maps are concatenated with the high-level feature maps to make full use of both spatial and semantic information. To make the results as stable as possible, the final results are obtained by combining multiple prediction results. Aiming at the template update, a high-confidence multi-template update mechanism is used. The average peak to correlation energy is used to determine whether the template should be updated. We use the anchor-free network to implement object tracking in a per-pixel manner, which computes the object category and bounding boxes directly. Experimental results indicate that the average overlap and success rate of the proposed algorithm increase by about 5% and 10%, respectively, compared to the SiamRPN++ algorithm when running on the dataset of GOT-10k (Generic Object Tracking Benchmark).

scholarly journals Spectral Convolution Feature-Based SPD Matrix Representation for Signal Detection Using a Deep Neural Network

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 949
Author(s):  
Jiangyi Wang ◽  
Min Liu ◽  
Xinwu Zeng ◽  
Xiaoqiang Hua
Keyword(s):  
Neural Network ◽  
Signal Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Detection Method ◽  
Learning Algorithm ◽  
Simulated Data ◽  
Data Sets ◽  
Feature Maps ◽  
Simulated Data Sets

Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish samples with different information. In this paper, a deep neural network signal detection method based on spectral convolution features is proposed. In this method, local features extracted from convolutional neural network are used to construct the SPD matrix, and a deep learning algorithm for the SPD matrix is used to detect target signals. Feature maps extracted by two kinds of convolutional neural network models are applied in this study. Based on this method, signal detection has become a binary classification problem of signals in samples. In order to prove the availability and superiority of this method, simulated and semi-physical simulated data sets are used. The results show that, under low SCR (signal-to-clutter ratio), compared with the spectral signal detection method based on the deep neural network, this method can obtain a gain of 0.5–2 dB on simulated data sets and semi-physical simulated data sets.

Sign in / Sign up

Export Citation Format

Share Document