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
- Element positioning of Web Automation
- Common model making instructions
- Vision Transformer (ViT)
- 使用rewrite规则实现将所有到a域名的访问rewrite到b域名
- 两数之和、三数之和(排序+双指针)
- 一文搞定class的微觀結構和指令
- Use the rewrite rule to rewrite all accesses to the a domain name to the B domain name
- Use of metadata in golang grpc
- openresty ngx_lua正则表达式
- 3:第一章:认识JVM规范2:JVM规范,简介;
猜你喜欢
Fix the memory structure of JVM in one article
Getting started stm32--gpio (running lantern) (nanny level)
数学公式截图识别神器Mathpix无限使用教程
The difference between MVVM and MVC
Simple and beautiful method of PPT color matching
Un article traite de la microstructure et des instructions de la classe
Masked Autoencoders Are Scalable Vision Learners (MAE)
Element operation and element waiting in Web Automation
终于搞懂什么是动态规划的
Use of metadata in golang grpc
随机推荐
Getting started stm32--gpio (running lantern) (nanny level)
[speech processing] speech signal denoising and denoising based on Matlab GUI low-pass filter [including Matlab source code 1708]
d3dx9_ How to repair 31.dll_ d3dx9_ 31. Solution to missing DLL
Ultrasonic sensor flash | LEGO eV3 Teaching
基于STM32的ADC采样序列频谱分析
Global and Chinese markets of industrial pH meters 2022-2028: Research Report on technology, participants, trends, market size and share
Practice of concurrent search
查看网页最后修改时间方法以及原理简介
利用LNMP实现wordpress站点搭建
Codeforces Global Round 19
Methods modified by static
终于搞懂什么是动态规划的
[speech processing] speech signal denoising based on Matlab GUI Hanning window fir notch filter [including Matlab source code 1711]
秒杀系统的设计与实现思路
fibonacci search
数据库基础知识(面试)
Judge whether the binary tree is a complete binary tree
leecode-学习笔记
Commonly used probability distributions: Bernoulli distribution, binomial distribution, polynomial distribution, Gaussian distribution, exponential distribution, Laplace distribution and Dirac delta d
LeetCode102. Sequence traversal of binary tree (output by layer and unified output)