Processing

Please wait...

Settings

Settings

Goto Application

1. CN107423760 - Depth learning target detection method based on pre-segmentation and regression

Office China
Application Number 201710598875.X
Application Date 21.07.2017
Publication Number 107423760
Publication Date 01.12.2017
Publication Kind A
IPC
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
G06K 9/32
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
32Aligning or centering of the image pick-up or image-field
G06K 9/34
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
34Segmentation of touching or overlapping patterns in the image field
G06K 9/46
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
G06K 9/3233
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
32Aligning or centering of the image pick-up or image-field
3233Determination of region of interest
G06K 9/342
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
20Image acquisition
34Segmentation of touching or overlapping patterns in the image field
342Cutting or merging image elements, e.g. region growing, watershed, clustering-based techniques
G06K 9/4604
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4604Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6261
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6261partitioning the feature space
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
Applicants XIDIAN UNIVERSITY
Inventors SUN WEI
PAN RONG
BIAN LEI
WANG PENG
Title
(EN) Depth learning target detection method based on pre-segmentation and regression
(ZH) 基于预分割和回归的深度学习目标检测方法
Abstract
(EN)
The invention discloses a depth learning target detection method based on pre-segmentation and regression, mainly to solve the problems that the existing target detection method is poor in small target detection precision and long in detection time. The method comprises steps: 1) a quadtree segmentation algorithm is used to extract a region of interest in a to-be-detected image; 2) a basic convolution layer and an auxiliary convolution layer are used to carry out feature extraction on the region of interest, and feature graphs of multiple scales are obtained; 3) the position information of a default border is calculated on the feature graphs of multiple scales, a convolution filter is used for detection on the feature graphs of multiple scales, and multiple predicted borders and multiple category scores are obtained; and 4) non-maximum suppression is used for the multiple predicted borders and the multiple category scores, and the final target border position and the category information are obtained. A small target in the image can be quickly and accurately detected, and the method can be used for target real-time detection in unmanned aerial vehicle aerial photographing.

(ZH)
本发明公开了一种基于预分割和回归的深度学习的目标检测方法,主要解决现有目标检测方法对小目标检测精度差和检测时间长的问题。其实现方案是:1)利用四叉树分割算法提取待检测图像的感兴趣区域;2)使用基础卷积层和辅助卷积层对感兴趣区域进行特征提取,得到多个尺度的特征图;3)在多个尺度的特征图上计算默认边框的位置信息,使用卷积滤波器在多个尺度的特征图上进行检测,得到多个预测边框和多个类别得分;4)使用非极大值抑制对多个预测边框和多个类别得分,得到最终的目标的边框位置和类别信息。本发明能对图像中的小目标进行快速准确的检测,可用于无人机航拍中的目标实时检测。