scholarly journals Detecting Small Chinese Traffic Signs via Improved YOLOv3 Method

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Baojun Zhang ◽  
Guili Wang ◽  
Huilan Wang ◽  
Chenchen Xu ◽  
Yu Li ◽  
...  
Keyword(s):  
Recognition Accuracy ◽  
Recognition Rate ◽  
Network Computing ◽  
Long Distance ◽  
Effective Technique ◽  
Traffic Signs ◽  
Speed Up ◽  
Small Targets ◽  
Scale Detection ◽  
Better Than

Long-distance detection of traffic signs provides drivers with more reaction time, which is an effective technique to reduce the probability of sudden accidents. It is recognized that the imaging size of far traffic signs is decreasing with distance. Such a fact imposes much challenge on long-distance detection. Aiming to enhance the recognition rate of long-distance small targets, we design a four-scale detection structure based on the three-scale detection structure of YOLOv3 network. In order to reduce the occlusion effects of similar objects, NMS is replaced by soft-NMS. In addition, the datasets are trained and the K-Means method is used to generate the appropriate anchor boxes, so as to speed up the network computing. By using these methods, better experimental results for the recognition of long-distance traffic signs have been obtained. The recognition rate is 43.8 frames per second (FPS), and the recognition accuracy is improved to 98.8%, which is much better than the original YOLOv3.

scholarly journals Strawberry Maturity Recognition Algorithm Combining Dark Channel Enhancement and YOLOv5

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 419
Author(s):  
Youchen Fan ◽  
Shuya Zhang ◽  
Kai Feng ◽  
Kechang Qian ◽  
Yitong Wang ◽  
...  
Keyword(s):  
Recognition Accuracy ◽  
Recognition Rate ◽  
Histogram Equalization ◽  
Recognition Algorithm ◽  
Complex Environments ◽  
Dark Channel ◽  
Testing Accuracy ◽  
Logarithmic Variation ◽  
Enhancement Algorithm ◽  
Better Than

Aiming at the problems of low accuracy of strawberry fruit picking and large rate of mispicking or missed picking, YOLOv5 combined with dark channel enhancement is proposed. In “Fengxiang” strawberry, the criterion of “bad fruit” is added to the conventional three criteria of ripeness, near-ripeness, and immaturity, because some of the bad fruits are close to the color of ripe fruits, but the fruits are small and dry. The training accuracy of the four kinds of strawberries with different ripeness is above 85%, and the testing accuracy is above 90%. Then, to meet the demand of all-day picking and address the problem of low illumination of images collected at night, an enhancement algorithm is proposed to enhance the images, which are recognized. We compare the actual detection results of the five enhancement algorithms, i.e., histogram equalization, Laplace transform, gamma transform, logarithmic variation, and dark channel enhancement processing under the different numbers of fruits, periods, and video tests. The results show that combined with dark channel enhancement, YOLOv5 has the highest recognition rate. Finally, the experimental results demonstrate that YOLOv5 is better than SSD, DSSD, and EfficientDet in terms of recognition accuracy, and the correct rate can reach more than 90%. Meanwhile, the method has good robustness in complex environments such as partial occlusion and multiple fruits.

scholarly journals An Open-Source Cloud-FPGA Gene Regulatory Accelerator

2021 ◽  
Author(s):  
Lucas Bragança ◽  
Jeronimo Penha ◽  
Michael Canesche ◽  
Dener Ribeiro ◽  
José Augusto M. Nacif ◽  
...  
Keyword(s):  
Open Source ◽  
Gene Regulatory Networks ◽  
High Performance ◽  
Regulatory Networks ◽  
Cloud Services ◽  
On Demand ◽  
Speed Up ◽  
Gene Regulatory ◽  
High Level ◽  
Better Than

FPGAs are suitable to speed up gene regulatory network (GRN) algorithms with high throughput and energy efficiency. In addition, virtualizing FPGA using hardware generators and cloud resources increases the computing ability to achieve on-demand accelerations across multiple users. Recently, Amazon AWS provides high-performance Cloud's FPGAs. This work proposes an open source accelerator generator for Boolean gene regulatory networks. The generator automatically creates all hardware and software pieces from a high-level GRN description. We evaluate the accelerator performance and cost for CPU, GPU, and Cloud FPGA implementations by considering six GRN models proposed in the literature. As a result, the FPGA accelerator is at least 12x faster than the best GPU accelerator. Furthermore, the FPGA reaches the best performance per dollar in cloud services, at least 5x better than the best GPU accelerator.

scholarly journals Parameters Optimization and Application of SVM Based on PCA-Particle Swarm Algorithm

2019 ◽  
pp. 325-330 ◽  
Author(s):  
Qingmi Yang
Keyword(s):  
Parameter Optimization ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Particle Swarm ◽  
Optimal Solution ◽  
Principal Component ◽  
Pso Algorithm ◽  
Parameters Optimization ◽  
Support Vector ◽  
Particle Swarm Algorithm

The parameter optimization of Support Vector Machine (SVM) has been a hot research direction. To improve the optimization rate and classification performance of SVM, the Principal Component Analysis (PCA) - Particle Swarm Optimization (PSO) algorithm was used to optimize the penalty parameters and kernel parameters of SVM. PSO which is to find the optimal solution through continuous iteration combined with PCA that eliminates linear redundancy between data, effectively enhance the generalization ability of the model, reduce the optimization time of parameters, and improve the recognition accuracy. The simulation comparison experiments on 6 UCI datasets illustrate that the excellent performance of the PCA-PSO-SVM model. The results show that the proposed algorithm has higher recognition accuracy and better recognition rate than simple PSO algorithm in the parameter optimization of SVM. It is an effective parameter optimization method.

scholarly journals An Improved High-Intelligence Method of Gas and Oil Pipeline Prewarning System in Real Soil Environment

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Fang Wang ◽  
Jichuan Xing ◽  
Jinxin Li ◽  
Feng Zhao ◽  
Shufeng Zhang
Keyword(s):  
Optical Fiber ◽  
Real Time ◽  
Recognition Accuracy ◽  
Signal Acquisition ◽  
Soil Environment ◽  
Long Distance ◽  
Vibration Signals ◽  
Oil Pipeline ◽  
Time Performance ◽  
High Intelligence

With the development of technology, the total extent of global pipeline transportation is also increased. However, the traditional long-distance optical fiber prewarning system has poor real-time performance and high false alarm rate when recognizing events threatening pipeline safety. The same vibration signal would vary greatly when collected in different soil environments and this problem would reduce the signal recognition accuracy of the prewarning system. In this paper, we studied this effect theoretically and analyzed soil vibration signals under different soil conditions. Then we studied the signal acquisition problem of long-distance gas and oil pipeline prewarning system in real soil environment. Ultimately, an improved high-intelligence method was proposed for optimization. This method is based on the real application environment, which is more suitable for the recognition of optical fiber vibration signals. Through experiments, the method yielded high recognition accuracy of above 95%. The results indicate that the method can significantly improve signal acquisition and recognition and has good adaptability and real-time performance in the real soil environment.

Research on Adaptive Face Gender Recognition Based on Compressive Sensing

2014 ◽  
Vol 989-994 ◽  
pp. 4187-4190 ◽  
Author(s):  
Lin Zhang
Keyword(s):  
Feature Extraction ◽  
Compressive Sensing ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Low Frequency ◽  
Face Image ◽  
Gender Recognition ◽  
Recognition Method ◽  
Frequency Information ◽  
Learning Machine

An adaptive gender recognition method is proposed in this paper. At first, do multiwavlet transform to face image and get its low frequency information, then do feature extraction to the low frequency information using compressive sensing (CS), use extreme learning machine (ELM) to achieve gender recognition finally. In the process of feature extraction, we use genetic algorithm (GA) to get the number of measurements of CS in order to gain the highest recognition rate, so the method can adaptive access optimal performance. Experimental results show that compared with PDA and LDA, the new method improved the recognition accuracy substantially.

Computer Control by Gaze

2012 ◽  
pp. 78-102 ◽  
Author(s):  
Henrik Skovsgaard ◽  
Kari-Jouko Räihä ◽  
Martin Tall
Keyword(s):  
Eye Gaze ◽  
Computer Control ◽  
Target Selection ◽  
Specific Area ◽  
Head Movements ◽  
Interaction Techniques ◽  
Information Spaces ◽  
Speed Up ◽  
Small Targets ◽  
Selection Of

This chapter provides an overview of gaze-based interaction techniques. We will first explore specific techniques intended to make target selection easier and to avoid the Midas touch problem. We will then take a look at techniques that do not require the use of special widgets in the interface but instead manipulate the rendering on the basis of eye gaze to facilitate the selection of small targets. Dwell-based interaction makes use of fixations; recent research has looked into the other option, using saccades as the basis for eye gestures. We will also discuss examples of how eye gaze has been used with other input modalities (blinks and winks, keyboard and mouse, facial gestures, head movements, and speech) to speed up interaction. Finally, we will discuss examples of interaction techniques in the context of a specific area of application: navigating information spaces.

scholarly journals Optical Flow Filtering-Based Micro-Expression Recognition Method

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2056
Author(s):  
Junjie Wu ◽  
Jianfeng Xu ◽  
Deyu Lin ◽  
Min Tu
Keyword(s):  
Optical Flow ◽  
Recognition Accuracy ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Expression Recognition ◽  
Recognition Method ◽  
Video Clips ◽  
Low Degree ◽  
Micro Expression

The recognition accuracy of micro-expressions in the field of facial expressions is still understudied, as current research methods mainly focus on feature extraction and classification. Based on optical flow and decision thinking theory, we propose a novel micro-expression recognition method, which can filter low-quality micro-expression video clips. Determined by preset thresholds, we develop two optical flow filtering mechanisms: one based on two-branch decisions (OFF2BD) and the other based on three-way decisions (OFF3WD). In OFF2BD, which use the classical binary logic to classify images, and divide the images into positive or negative domain for further filtering. Differ from the OFF2BD, OFF3WD added boundary domain to delay to judge the motion quality of the images. In this way, the video clips with low degree of morphological change can be eliminated, so as to directly improve the quality of micro-expression features and recognition rate. From the experimental results, we verify the recognition accuracy of 61.57%, and 65.41% for CASMEII, and SMIC datasets, respectively. Through the comparative analysis, it shows that the scheme can effectively improve the recognition performance.

Low-Resolution Face Recognition of Multi-Scale Blocking CS-LBP and Weighted PCA

2016 ◽  
Vol 30 (08) ◽  
pp. 1656005 ◽  
Author(s):  
Jiadi Li ◽  
Zhenxue Chen ◽  
Chengyun Liu
Keyword(s):  
Face Recognition ◽  
Local Binary Pattern ◽  
Recognition Accuracy ◽  
Recognition Rate ◽  
Principal Component ◽  
Low Resolution ◽  
Multi Scale ◽  
Face Features ◽  
Weighted Principal Component ◽  
Pca Algorithm

A novel method is proposed in this paper to improve the recognition accuracy of Local Binary Pattern (LBP) on low-resolution face recognition. More precise descriptors and effectively face features can be extracted by combining multi-scale blocking center symmetric local binary pattern (CS-LBP) based on Gaussian pyramids and weighted principal component analysis (PCA) on low-resolution condition. Firstly, the features statistical histograms of face images are calculated by multi-scale blocking CS-LBP operator. Secondly, the stronger classification and lower dimension features can be got by applying weighted PCA algorithm. Finally, the different classifiers are used to select the optimal classification categories of low-resolution face set and calculate the recognition rate. The results in the ORL human face databases show that recognition rate can get 89.38% when the resolution of face image drops to 12[Formula: see text]10 pixel and basically satisfy the practical requirements of recognition. The further comparison of other descriptors and experiments from videos proved that the novel algorithm can improve recognition accuracy.

MOCUM Code Verification and Sensibility Study Using C5G7 Benchmark

2016 ◽  
Author(s):  
Xue Yang ◽  
Rajan Borse ◽  
Nader Satvat
Keyword(s):  
Method Of Characteristics ◽  
Polar Angle ◽  
Mesh Size ◽  
Sensitivity Study ◽  
High Accuracy ◽  
Benchmark Problem ◽  
Code Verification ◽  
Heterogeneous Effects ◽  
Speed Up ◽  
Better Than

This work uses the 2-D C5G7 benchmark to verify the accuracy of the MOCUM code, a parallel neutronics program based on the method of characteristics (MOC) for solving arbitrary core geometry. Compared to the MCNP results, MOCUM k-eff, maximum assembly and pin power percentage errors are 0.02%, −0.06%, and 0.64%, respectively. The results demonstrate the high accuracy of the MOCUM code. The calculation uses a total of 56 threads, and the runtime on dual Intel Xeon E5-2699 v3 CPUs is 26 minutes, with speed up higher than 50 times. The sensitivity study of various MOC parameters using the calculation of the C5G7 benchmark problem is also performed. The study reveals that C5G7 requires the usage of 48 or more azimuthal angles. The strong flux gradient and the heterogeneous effects need fine unstructured meshes to resolve. The simulation uses 258 million zones with an average mesh size of 0.016 cm2. The investigation of the polar angle quadrature indicates that Leonard polar angle performs slightly better than Gauss-Legendre and Tabuchi polar angles and more than three polar angles are not necessary. In addition, parameter sensitivity study shows that coarse parameters are prone to introduce error to the neutron flux but not k-eff.

Sign in / Sign up

Export Citation Format

Share Document