CN115335872A - 目标检测网络的训练方法、目标检测方法及装置 - Google Patents

目标检测网络的训练方法、目标检测方法及装置 Download PDF

Info

Publication number
CN115335872A
CN115335872A CN202180000352.5A CN202180000352A CN115335872A CN 115335872 A CN115335872 A CN 115335872A CN 202180000352 A CN202180000352 A CN 202180000352A CN 115335872 A CN115335872 A CN 115335872A
Authority
CN
China
Prior art keywords
detection
frame
target
target object
network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202180000352.5A
Other languages
English (en)
Inventor
王镜茹
胡风硕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BOE Technology Group Co Ltd
Original Assignee
BOE Technology Group Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by BOE Technology Group Co Ltd filed Critical BOE Technology Group Co Ltd
Publication of CN115335872A publication Critical patent/CN115335872A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Image Analysis (AREA)

Abstract

本公开提供一种目标检测网络的训练方法、目标检测方法及装置，该训练方法包括：将训练图像输入至待训练目标检测网络中得到目标对象的检测信息，检测信息包括目标对象的检测分类、目标对象的检测框的检测位置和目标对象的特征点的检测位置；计算待训练目标检测网络的总损失函数，总损失函数根据目标对象的检测分类的损失函数，目标对象的检测框的检测位置的损失函数，和，目标对象的特征点的检测位置的损失函数计算得到；根据总损失函数，对待训练目标检测网络的参数进行调整。本公开中，在训练目标检测网络时，额外考虑了目标对象的特征点的检测位置损失，有助于提高检测到的目标对象的质量，降低复杂应用场景下干扰物体对检测结果的影响。

Description

PCT国内申请，说明书已公开。

Claims (22)

  1. PCT国内申请，权利要求书已公开。
CN202180000352.5A 2021-02-26 2021-02-26 目标检测网络的训练方法、目标检测方法及装置 Pending CN115335872A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/078156 WO2022178833A1 (zh) 2021-02-26 2021-02-26 目标检测网络的训练方法、目标检测方法及装置

Publications (1)

Publication Number Publication Date
CN115335872A true CN115335872A (zh) 2022-11-11

Family

ID=83006504

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180000352.5A Pending CN115335872A (zh) 2021-02-26 2021-02-26 目标检测网络的训练方法、目标检测方法及装置

Country Status (3)

Country Link
US (1) US12002254B2 (zh)
CN (1) CN115335872A (zh)
WO (1) WO2022178833A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116580210A (zh) * 2023-07-05 2023-08-11 四川弘和数智集团有限公司 一种线性目标检测方法、装置、设备及介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116704017B (zh) * 2023-08-09 2023-11-14 烟台大学 一种基于视觉混合的机械臂位姿检测方法
CN116824549B (zh) * 2023-08-29 2023-12-08 所托(山东)大数据服务有限责任公司 基于多检测网络融合的目标检测方法、装置及车辆
CN117079196B (zh) * 2023-10-16 2023-12-29 长沙北斗产业安全技术研究院股份有限公司 基于深度学习以及目标运动轨迹的无人机识别方法

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8639625B1 (en) * 1995-02-13 2014-01-28 Intertrust Technologies Corporation Systems and methods for secure transaction management and electronic rights protection
US6355336B1 (en) * 1998-12-15 2002-03-12 Mitsubishi, Engineering-Plastics Corporation Multi-layer packaging film
CN101115211A (zh) 2007-08-30 2008-01-30 四川长虹电器股份有限公司 色彩独立增强处理方法
CN103593834B (zh) 2013-12-03 2017-06-13 厦门美图网科技有限公司 一种智能添加景深的图像增强方法
US10078791B2 (en) 2014-01-09 2018-09-18 Irvine Sensors Corporation Methods and devices for cognitive-based image data analytics in real time
US10223344B2 (en) * 2015-01-26 2019-03-05 Adobe Inc. Recognition and population of form fields in an electronic document
US9805296B2 (en) * 2016-02-23 2017-10-31 The Chinese University Of Hong Kong Method and apparatus for decoding or generating multi-layer color QR code, method for recommending setting parameters in generation of multi-layer QR code, and product comprising multi-layer color QR code
CN109978918A (zh) 2019-03-21 2019-07-05 腾讯科技（深圳）有限公司 一种轨迹追踪方法、装置和存储介质
CN110503097A (zh) 2019-08-27 2019-11-26 腾讯科技（深圳）有限公司 图像处理模型的训练方法、装置及存储介质
KR20210044073A (ko) * 2019-10-14 2021-04-22 엘지전자 주식회사 영상의 상품 인식에 기반하여 매장 내 위치를 추정하기 위한 방법 및 장치
CN111161277B (zh) * 2019-12-12 2023-04-18 中山大学 一种基于深度学习的自然图像抠图方法
CN111199230B (zh) 2020-01-03 2023-07-07 腾讯科技（深圳）有限公司 目标检测的方法、装置、电子设备及计算机可读存储介质
CN111508002B (zh) * 2020-04-20 2020-12-25 北京理工大学 一种小型低飞目标视觉检测跟踪系统及其方法
CN111709295A (zh) 2020-05-18 2020-09-25 武汉工程大学 一种基于SSD-MobileNet的实时手势检测和识别方法及系统
CN111738077A (zh) 2020-05-19 2020-10-02 云知声智能科技股份有限公司 一种人脸检测和对齐方法及装置
CN111898406B (zh) 2020-06-05 2022-04-29 东南大学 基于焦点损失和多任务级联的人脸检测方法
CN112183435A (zh) 2020-10-12 2021-01-05 河南威虎智能科技有限公司 一种两阶段的手部目标检测方法
CN112288726B (zh) 2020-10-30 2023-12-29 西安智财全技术转移中心有限公司 一种井下带式输送机带面异物检测方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116580210A (zh) * 2023-07-05 2023-08-11 四川弘和数智集团有限公司 一种线性目标检测方法、装置、设备及介质
CN116580210B (zh) * 2023-07-05 2023-09-15 四川弘和数智集团有限公司 一种线性目标检测方法、装置、设备及介质

Also Published As

Publication number Publication date
US12002254B2 (en) 2024-06-04
WO2022178833A1 (zh) 2022-09-01
US20220277541A1 (en) 2022-09-01

Similar Documents

Publication Publication Date Title
CN110458095B (zh) 一种有效手势的识别方法、控制方法、装置和电子设备
CN110738101B (zh) 行为识别方法、装置及计算机可读存储介质
CN115335872A (zh) 目标检测网络的训练方法、目标检测方法及装置
CN108304820B (zh) 一种人脸检测方法、装置及终端设备
CN110246181B (zh) 基于锚点的姿态估计模型训练方法、姿态估计方法和系统
CN113158862B (zh) 一种基于多任务的轻量级实时人脸检测方法
CN106845430A (zh) 基于加速区域卷积神经网络的行人检测与跟踪方法
CN111062263B (zh) 手部姿态估计的方法、设备、计算机设备和存储介质
CN112381061B (zh) 一种面部表情识别方法及系统
KR100862349B1 (ko) 제스처 인식 기능을 이용한 반투과 거울 기반 사용자인터페이스 시스템
CN111444764A (zh) 一种基于深度残差网络的手势识别方法
CN112506340A (zh) 设备控制方法、装置、电子设备及存储介质
US20230237777A1 (en) Information processing apparatus, learning apparatus, image recognition apparatus, information processing method, learning method, image recognition method, and non-transitory-computer-readable storage medium
CN111709268A (zh) 一种深度图像中的基于人手结构指导的人手姿态估计方法和装置
CN113591763A (zh) 人脸脸型的分类识别方法、装置、存储介质及计算机设备
CN115861715A (zh) 基于知识表示增强的图像目标关系识别算法
Feng Mask RCNN-based single shot multibox detector for gesture recognition in physical education
CN108053425B (zh) 一种基于多通道特征的高速相关滤波目标跟踪方法
CN113327269A (zh) 一种无标记颈椎运动检测方法
WO2024021321A1 (zh) 模型生成的方法、装置、电子设备和存储介质
CN115527083A (zh) 图像标注方法、装置和电子设备
CN111914751B (zh) 一种图像人群密度识别检测方法及系统
CN115205806A (zh) 生成目标检测模型的方法、装置和自动驾驶车辆
Mesbahi et al. Hand gesture recognition based on various deep learning YOLO models
Tyagi et al. Hand Anatomy and Neural Network-Based Recognition for Sign Language

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination