当前位置:网站首页>Object detection based on impulse neural network
Object detection based on impulse neural network
2022-07-05 23:11:00 【biyezuopinvip】
Resource download address :https://download.csdn.net/download/sheziqiong/85909649
Resource download address :https://download.csdn.net/download/sheziqiong/85909649
1 introduction
1.1 Research background
Target detection is a technology that applies a specific computer algorithm to find the desired target in the image . In recent years , With The continuous development of computer hardware , Various algorithms of target detection have also ushered in a huge breakthrough , More and more used in Traffic detection 、 Smart payment 、 Medical imaging and other aspects . In computer vision , Target detection is better than image Class is a more complex problem , It not only needs to know the type of goal , We also need to achieve the positioning of the goal . therefore , Physical examination The test is more difficult , More challenging , The corresponding deep learning model will also be more complex .
There are many algorithms for target detection , Convolutional neural networks (Convolutional Neural Networks, CNN) Is its generation One of the table algorithms . It's a feedforward neural network , With convolution calculation and depth structure . at present , Based on convolutional neural network The target detection algorithm of network can be roughly divided into two modes , namely twostage Patterns and onestage Pattern ,twostage model The detection process of formula is divided into two steps : First, several candidate boxes are generated by the algorithm , Re pass CNN Check the candidate box classification ;onestage Mode is end-to-end learning , Directly regress the confidence probability and position of the target , phase There is a loss of accuracy for , But the speed is slow twostage The algorithm of pattern is faster .[1]
be based on twostage The algorithm of :
• RCNN: By selective search (selective search) To determine the candidate box , Then uniformly compress the candidate boxes To size ; Then use CNN Feature extraction of candidate boxes ; Finally, use multiple support vector machines (SVM) The classifier classifies the output vector , Use boundary regression to generate the target region [2].
• Fast RCNN: Still use selective search to identify candidate boxes , But input the whole picture into CNN, In volume Use the region of interest on the feature layer (Region of interest pooling,ROI pooling) operation , And from special Extract a feature vector with a specific length from the eigengraph ; Then input the eigenvector into the full connection layer , use softmax Classify them ; Finally, the candidate boxes belonging to the same feature are classified and their positions are regressed [3].
•Faster RCNN: Use RPN (Region Proposal Network) Not selective search , Greatly reduce The time for extracting candidate boxes . take RPN and Fast RCNN Combination , First, extract the features of the whole picture ; Then input the feature results into RPN; And then use ROI The pool layer fixes the size of the candidate box ; Finally, it belongs to Candidate box regression and adjustment of a feature [4].
be based on onestage The algorithm of :
• YOLO v1 And many subsequent improved algorithms :YOLO Series algorithm is an advanced target detection algorithm Law . Because the whole detection framework is a whole , Therefore, the performance of the algorithm can be optimized end-to-end .
• SSD Series algorithm : Multi scale feature map is used to detect ., Set a priori box , Use convolution to detect .
Impulse neural network (Spiking Neural Network, SNN), Originated from brain science , Because of its rich space-time Neurodynamic properties of the field 、 Diverse coding mechanisms and ultra-low power consumption are known as the third generation Neural Networks . Here is front , Neural networks have gone through several stages of development : The first stage is the perceptron stage , It can simulate human perception Force and by American neuroscientists Frank Rosenblatt stay BM704 The simulation is completed on the machine . The second stage is based on connection The multi-layer artificial neural network of knot theory (Artificial Neural Network, ANN), It originated in the 20th century 80 years Mid - .20 century 80 End of the decade , Distributed expression and back propagation algorithm are proposed . stay 2006 Years later , Deep volume Product network plays an important role , It has led the development of artificial intelligence in recent ten years [5].
ANN All areas of deep learning ( Such as computer vision and natural language processing ) Great success , but ANN Is biologically imprecise , It cannot accurately imitate the working mechanism of biological brain neurons , Lack of certain Biological interpretability of . In order to make the neural network closer to the human brain ,SNN And then came . But with ANN On all sides The wide application of face is different ,SNN There are still many problems to be solved in the field , Its research is still in the early stage of rapid development Stage .
1.2 Research significance
SNN As the third generation artificial neural network , Event driven mechanism based on neurodynamics , Make it good at efficiency Deal with complexity 、 Sparse spatiotemporal information . also SNN In the hardware circuit, it has the advantage of ultra-low energy consumption .2019 year Developed by Tsinghua University ANN/SNN Heterogeneous fusion tianjixin board Nature cover , Point out the depth of computer science orientation The cross fusion of degree learning and neuroscience oriented impulse neural network will be the development direction of artificial general intelligence [6].
The significance of this design paper is to explore the application of impulse neural network in target detection , The current mainstream pulse The training algorithm of impulse neural network has direct BP Training 、STDP Unsupervised training and well trained ANN The transformation of , although There are many training algorithms , however SNN There is still no mature training algorithm . For example, in larger and deeper network training , Facing the problem of pulse signal coding 、 Problems such as high training costs [5]. And in the realization of target detection , Need more Complex network structure , At present, only Kim et al. (2020) Waiting for someone in the classic YOLO Model On spikingyolo. So , Based on different network structures SNN, To facilitate implementation in hardware Low power consumption of , And compared with the existing results , It has a certain significance .
1.3 Paper organization and structure
The research content of this paper is : In the summary and analysis of domestic and foreign ANN To transform SNN On the theoretical basis of , benefit Use the existing ANN Target detection model , Analyze the losses in the transformation process , And the realization of various transformation means The way ; At the same time, the transformation model is compared with the work done by predecessors , Analyze different model pairs SNN The impact of transformation , And in pytorch Design and implement the model under the framework .
This paper extends the problem to theoretical support , And then to algorithm research and specific solution design organization , It is divided into the following six chapters :
The first chapter is this chapter : Firstly, the background and significance of pulse neural network and target detection are described , And then put forward The main content of this paper is to design a transformation model and compare it with previous work to analyze the effects of different models on SNN The conversion influence , Finally, the structure and framework of the paper are given .
In Chapter 2, pulse neural network is introduced systematically : Development trend 、 Advantages and disadvantages 、 Learning methods, etc . Focus on ANN
To SNN The method of transformation is described
The third chapter gives the commonly used artificial neural network model in target detection (Artificial Neural Network,ANN), With onestage Representative algorithm SSD For example , The structure of the model 、 Loss function and other aspects .
The fourth chapter introduces the design ideas and methods of the model
Chapter five combines experiments , separately ssd,spikingssd Comparison of ;yolo,spikingyolo Comparison of . Give real Test results , Analyze .
Chapter six summarizes and analyzes , Analyze the existing results of the transformation model from multiple perspectives , And it is given that this kind of knot Possible causes of fruit .
Catalog
1 introduction 2
1.1 Research background 2
1.2 Research significance 3
1.3 Paper organization and structure 3
2 Impulse neural network 5
2.1 Learning algorithms 5
2.2 ANN Transformed SNN 6
2.3 ANN Pulse implementation of operation 8
Deviation normalization 8
Normalize except for outliers 8
3 ANN Model structure 10
3.1 SSD 10
3.2 YOLO 13
4 SNN Model structure 16
4.1 spikingssd 16
4.2 spikingyolo 18
5 experimental result 22
5.1 Data set introduction 22
5.2 Introduction to experimental indicators 22
5.3 Comparison of experimental results 22
6 Summarize and discuss 25
6.1 The impact of data on results 25
6.2 Several factors that affect the results of the model 25
reference 26
Resource download address :https://download.csdn.net/download/sheziqiong/85909649
Resource download address :https://download.csdn.net/download/sheziqiong/85909649
边栏推荐
- Composition of interface
- Spectrum analysis of ADC sampling sequence based on stm32
- Hainan Nuanshen tea recruits warmhearted people: recruitment of the product experience recommender of Nuanshen multi bubble honey orchid single cluster
- 2022 registration examination for safety management personnel of hazardous chemical business units and simulated reexamination examination for safety management personnel of hazardous chemical busines
- Krypton Factor-紫书第七章暴力求解
- Non rigid / flexible point cloud ICP registration
- [untitled]
- 2:第一章:认识JVM规范1:JVM简介;
- Three. Js-01 getting started
- 基于脉冲神经网络的物体检测
猜你喜欢
【Note17】PECI(Platform Environment Control Interface)
Element operation and element waiting in Web Automation
openresty ngx_ Lua request response
Vcomp110.dll download -vcomp110 What if DLL is lost
Ultrasonic sensor flash | LEGO eV3 Teaching
数据库基础知识(面试)
[digital signal denoising] improved wavelet modulus maxima digital signal denoising based on MATLAB [including Matlab source code 1710]
Using LNMP to build WordPress sites
Douban scoring applet Part-2
Use of metadata in golang grpc
随机推荐
February 13, 2022 -5- maximum depth of binary tree
实现反向代理客户端IP透传
Metasploit(msf)利用ms17_010(永恒之蓝)出现Encoding::UndefinedConversionError问题
The maximum happiness of the party
Hcip day 11 (BGP agreement)
Practice of concurrent search
Calculating the number of daffodils in C language
Global and Chinese markets of industrial pH meters 2022-2028: Research Report on technology, participants, trends, market size and share
Hainan Nuanshen tea recruits warmhearted people: recruitment of the product experience recommender of Nuanshen multi bubble honey orchid single cluster
Douban scoring applet Part-2
LabVIEW打开PNG 图像正常而 Photoshop打开得到全黑的图像
Selenium+Pytest自动化测试框架实战
Multi view 3D reconstruction
audiopolicy
Week 17 homework
Vision Transformer (ViT)
2022 G3 boiler water treatment simulation examination and G3 boiler water treatment simulation examination question bank
一文搞定class的微觀結構和指令
Hcip day 12 (BGP black hole, anti ring, configuration)
Finally understand what dynamic planning is