QA Official

2016 Visual Target Tracking Summary 2019-04-16
Recently I learned the visual target tracking algorithm. I have mainly learned several mainstream tracking algorithms, kcf, stc, dsst, and many principles of the algorithm are available online. I will not repeat them here, but only make test records of the tracking effect. Kcf full name Kernelized Correlation Filters Fhog (Felzenszwalb 'shog, an improved hog proposed by the authors of DPM) is used for HOG features effect is better, the title is kcf-DSST, actually KCF, download address:

C++ Development Overview 2019-04-16
C++ is an object-oriented High-level programming language developed on the basis of C. It has been more than 30 years since it was founded in 1983 by Professor Bjarne Stroustrup in Bell Labs.From the original C with class, C++ has undergone many standardized transformations from C++98, C++ 03, C++ 11, C++ 14 to C++17. Its functions have been greatly enriched. It has evolved into a complex programming language with many

K Nearest Neighbor-Iris Classification 2019-04-16
The following uses KNN algorithm to classify biological species, and uses the most famous Iris data set.This data has been used by Fisher in classical papers, and is currently pre-stored in S Kearne's toolkit as textbook data samples. Python source code: #coding=utf-8 from sklearn.datasets import load_iris #------------- from sklearn.cross_validation import train_test_split #------------- from sklearn.preprocessing import StandardScaler from sklearn.neighbors import KNeighborsClassifier #------------- from sklearn.metrics import classification_report #-------------load data iris=load_iris() print 'data shape',iris.

R Language-Data Preprocessing (2) 2019-04-16
1, r data set related operationsThe output tells us that 104 samples are complete, 34 samples miss only the Ozone measurement, 4 samples miss only the Solar.R value and so on. tempData <- mice(data,m=5,maxit=50,meth='pmm',seed=500) summary(tempData) 其中m=5 代表输入数据集的个数,meth='pmm' 代表填充的方法,在

alv Multi-layer Display and Classification Summary 2019-04-16
*&---------------------------------------------------------------------* *& Report ZFI_JXC_PRINT *& *&---------------------------------------------------------------------* REPORT ZFI_JXC_PRINT. tables: sscrfields,bseg,bkpf,mara. type-pools: slis,kkblo. data: w_vari type disvariant, w_layo type slis_layout_alv, i_fcat type slis_t_fieldcat_alv, w_fcat type slis_fieldcat_alv, i_evts type slis_t_event, i_evts_exit type slis_t_event_exit, w_keyinfo type slis_keyinfo_alv. constants: cns_x type c value 'X'. field-symbols:type table. field-symbols: type table. data:str_name1(30) type c, str_name2(30) type c. data: l_total type i value 0. data: x_total type i value 0. data: g_belnr like range of bkpf-belnr, g_belnr_line

Analysis of Common Database Scenarios 2019-04-16
Common Database Scenarios Analysis 2 a relational database 2 1. Introduction to Relational Data 2 2. Common Concepts 2 4. Feature 3 5. Common Relational Databases 3 2 Common Hibari (NoSQL) Scenario Analysis 3 1, NoSQL feature 3 2, according to the needs of classification 4 2.1 Kye-Value Database Meeting Extremely High Read and Write Performance Requirements: Redis, Tokyo Cabinet, Flare 4

Building Convolutional Neural Network for Simple Picture Classification (3)-Testing and Application of Model 2019-04-16
Both functions are in the same file 1. create a new file import tensorflow as tf from PIL import Image import os import numpy as np import matplotlib.pyplot as plt from GetCnnData import get_files import CNN classes = [] n_classes = 0 #获取一张图片 def get_one_image(train): n = len(train) ind = np.random.randint(0, n) img_dir = train[ind] # 随机选择测试的

Change the Development Trend of IT Industry in the Future (Transfer) 2019-04-16
[color=green]原帖地址: [url][/url][/color][

Classical Paper Sorting in Image Processing and Computer Vision 2019-04-16
Before 1990 Peter Burt, Edward Adelson The Laplacian Pyramid as ACompact Image Code 虽说这个Laplacian Pyramid是有冗余的,但使用起来非常简单方便,对理解小波变换也非常有帮助。这位Ade

Definition of Target Detection 2019-04-16
Target detection and identification refers to finding targets from a scene (picture), including two processes of detection (where) and identification (what).The difficulty of the task lies in the extraction and identification of candidate regions to be detected. Therefore, the broad framework of the task is as follows: Firstly, a model for extracting candidate regions from the scene is established and then identify the classification model of the candidate region Finally fine-tune the parameters of the classification model and the location of valid candidate boxes Target detection and recognition has a wide range of applications in many fields of life.