CN112861988A - 一种基于注意力图神经网络的特征匹配方法 - Google Patents
一种基于注意力图神经网络的特征匹配方法 Download PDFInfo
- Publication number
- CN112861988A CN112861988A CN202110237853.7A CN202110237853A CN112861988A CN 112861988 A CN112861988 A CN 112861988A CN 202110237853 A CN202110237853 A CN 202110237853A CN 112861988 A CN112861988 A CN 112861988A
- Authority
- CN
- China
- Prior art keywords
- feature
- training
- neural network
- matching
- 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.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 43
- 239000013598 vector Substances 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- IJJWOSAXNHWBPR-HUBLWGQQSA-N 5-[(3as,4s,6ar)-2-oxo-1,3,3a,4,6,6a-hexahydrothieno[3,4-d]imidazol-4-yl]-n-(6-hydrazinyl-6-oxohexyl)pentanamide Chemical compound N1C(=O)N[C@@H]2[C@H](CCCCC(=O)NCCCCCC(=O)NN)SC[C@@H]21 IJJWOSAXNHWBPR-HUBLWGQQSA-N 0.000 claims description 2
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000011056 performance test Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims 1
- 230000000007 visual effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (5)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110237853.7A CN112861988B (zh) | 2021-03-04 | 2021-03-04 | 一种基于注意力图神经网络的特征匹配方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110237853.7A CN112861988B (zh) | 2021-03-04 | 2021-03-04 | 一种基于注意力图神经网络的特征匹配方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112861988A true CN112861988A (zh) | 2021-05-28 |
CN112861988B CN112861988B (zh) | 2022-03-11 |
Family
ID=75991526
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110237853.7A Active CN112861988B (zh) | 2021-03-04 | 2021-03-04 | 一种基于注意力图神经网络的特征匹配方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112861988B (zh) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221153A (zh) * | 2021-05-31 | 2021-08-06 | 平安科技(深圳)有限公司 | 图神经网络训练方法、装置、计算设备及存储介质 |
CN114398972A (zh) * | 2022-01-07 | 2022-04-26 | 福建农林大学 | 一种基于联合表示注意力机制的深度学习图像匹配方法 |
CN114707611A (zh) * | 2022-04-21 | 2022-07-05 | 安徽工程大学 | 基于图神经网络特征提取与匹配的移动机器人地图构建方法、存储介质及设备 |
CN114937153A (zh) * | 2022-06-07 | 2022-08-23 | 北京理工大学 | 弱纹理环境下基于神经网络的视觉特征处理系统及方法 |
CN115620150A (zh) * | 2022-12-05 | 2023-01-17 | 海豚乐智科技(成都)有限责任公司 | 基于孪生Transformer的多模态图像地面建筑识别方法及装置 |
CN117635967A (zh) * | 2023-11-30 | 2024-03-01 | 中科南京智能技术研究院 | 一种自监督学习里程计量方法、装置、系统及存储介质 |
CN117789253A (zh) * | 2024-02-23 | 2024-03-29 | 东北大学 | 一种基于双网络的视频行人重识别方法 |
CN118628991A (zh) * | 2024-08-13 | 2024-09-10 | 合肥讯图信息科技有限公司 | 一种基于人脸识别和车牌识别的监测方法及系统 |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100267927A1 (en) * | 2006-06-22 | 2010-10-21 | Garrett Thomas P J | Structure of the Insulin Receptor Ectodomain |
CN102789594A (zh) * | 2012-06-28 | 2012-11-21 | 南京邮电大学 | 一种基于diva神经网络模型的语音生成方法 |
CN107045715A (zh) * | 2017-02-22 | 2017-08-15 | 西南科技大学 | 一种单幅低动态范围图像生成高动态范围图像的方法 |
CN107563308A (zh) * | 2017-08-11 | 2018-01-09 | 西安电子科技大学 | 基于粒子群优化算法的slam闭环检测方法 |
US20190370577A1 (en) * | 2018-06-04 | 2019-12-05 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving Management Methods and Systems, Vehicle-Mounted Intelligent Systems, Electronic Devices, and Medium |
CN110929748A (zh) * | 2019-10-12 | 2020-03-27 | 杭州电子科技大学 | 一种基于深度学习的运动模糊图像特征匹配方法 |
CN111428586A (zh) * | 2020-03-09 | 2020-07-17 | 同济大学 | 基于特征融合与样本增强的三维人体姿态估计方法 |
CN111507210A (zh) * | 2020-03-31 | 2020-08-07 | 华为技术有限公司 | 交通信号灯的识别方法、系统、计算设备和智能车 |
CN111681067A (zh) * | 2020-04-17 | 2020-09-18 | 清华大学 | 基于图注意力网络的长尾商品推荐方法及系统 |
CN111737511A (zh) * | 2020-06-17 | 2020-10-02 | 南强智视(厦门)科技有限公司 | 基于自适应局部概念嵌入的图像描述方法 |
CN111738090A (zh) * | 2020-05-27 | 2020-10-02 | 北京三快在线科技有限公司 | 行人重识别模型训练方法、装置及行人重识别方法、装置 |
CN112084952A (zh) * | 2020-09-10 | 2020-12-15 | 湖南大学 | 一种基于自监督训练的视频点位跟踪方法 |
CN112288011A (zh) * | 2020-10-30 | 2021-01-29 | 闽江学院 | 一种基于自注意力深度神经网络的图像匹配方法 |
CN112417756A (zh) * | 2020-11-13 | 2021-02-26 | 清华大学苏州汽车研究院(吴江) | 一种自动驾驶算法的交互式仿真测试系统 |
-
2021
- 2021-03-04 CN CN202110237853.7A patent/CN112861988B/zh active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100267927A1 (en) * | 2006-06-22 | 2010-10-21 | Garrett Thomas P J | Structure of the Insulin Receptor Ectodomain |
CN102789594A (zh) * | 2012-06-28 | 2012-11-21 | 南京邮电大学 | 一种基于diva神经网络模型的语音生成方法 |
CN107045715A (zh) * | 2017-02-22 | 2017-08-15 | 西南科技大学 | 一种单幅低动态范围图像生成高动态范围图像的方法 |
CN107563308A (zh) * | 2017-08-11 | 2018-01-09 | 西安电子科技大学 | 基于粒子群优化算法的slam闭环检测方法 |
US20190370577A1 (en) * | 2018-06-04 | 2019-12-05 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving Management Methods and Systems, Vehicle-Mounted Intelligent Systems, Electronic Devices, and Medium |
CN110929748A (zh) * | 2019-10-12 | 2020-03-27 | 杭州电子科技大学 | 一种基于深度学习的运动模糊图像特征匹配方法 |
CN111428586A (zh) * | 2020-03-09 | 2020-07-17 | 同济大学 | 基于特征融合与样本增强的三维人体姿态估计方法 |
CN111507210A (zh) * | 2020-03-31 | 2020-08-07 | 华为技术有限公司 | 交通信号灯的识别方法、系统、计算设备和智能车 |
CN111681067A (zh) * | 2020-04-17 | 2020-09-18 | 清华大学 | 基于图注意力网络的长尾商品推荐方法及系统 |
CN111738090A (zh) * | 2020-05-27 | 2020-10-02 | 北京三快在线科技有限公司 | 行人重识别模型训练方法、装置及行人重识别方法、装置 |
CN111737511A (zh) * | 2020-06-17 | 2020-10-02 | 南强智视(厦门)科技有限公司 | 基于自适应局部概念嵌入的图像描述方法 |
CN112084952A (zh) * | 2020-09-10 | 2020-12-15 | 湖南大学 | 一种基于自监督训练的视频点位跟踪方法 |
CN112288011A (zh) * | 2020-10-30 | 2021-01-29 | 闽江学院 | 一种基于自注意力深度神经网络的图像匹配方法 |
CN112417756A (zh) * | 2020-11-13 | 2021-02-26 | 清华大学苏州汽车研究院(吴江) | 一种自动驾驶算法的交互式仿真测试系统 |
Non-Patent Citations (6)
Title |
---|
M.E.ELALAMI等: "A new matching strategy for content based image retrieval system", 《APPLIED SOFT COMPUTING》 * |
VASSILEIOS BALNTAS ET AL: "H-Patches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors", 《2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
张红英等: "基于不变矩相似度的快速图像拼接", 《微型机与应用》 * |
徐守坤等: "一种结合空间特征的图像注意力标注算法改进研究", 《计算机应用研究》 * |
杨燕: "复杂场景图像特征分析与匹配方法研究", 《中国博士学位论文全文数据库 (信息科技辑)》 * |
程鸣洋等: "基于注意力机制的立体匹配网络研究", 《光学学报》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113221153A (zh) * | 2021-05-31 | 2021-08-06 | 平安科技(深圳)有限公司 | 图神经网络训练方法、装置、计算设备及存储介质 |
CN113221153B (zh) * | 2021-05-31 | 2022-12-27 | 平安科技(深圳)有限公司 | 图神经网络训练方法、装置、计算设备及存储介质 |
CN114398972A (zh) * | 2022-01-07 | 2022-04-26 | 福建农林大学 | 一种基于联合表示注意力机制的深度学习图像匹配方法 |
CN114707611A (zh) * | 2022-04-21 | 2022-07-05 | 安徽工程大学 | 基于图神经网络特征提取与匹配的移动机器人地图构建方法、存储介质及设备 |
CN114937153A (zh) * | 2022-06-07 | 2022-08-23 | 北京理工大学 | 弱纹理环境下基于神经网络的视觉特征处理系统及方法 |
CN114937153B (zh) * | 2022-06-07 | 2023-06-30 | 北京理工大学 | 弱纹理环境下基于神经网络的视觉特征处理系统及方法 |
CN115620150A (zh) * | 2022-12-05 | 2023-01-17 | 海豚乐智科技(成都)有限责任公司 | 基于孪生Transformer的多模态图像地面建筑识别方法及装置 |
CN115620150B (zh) * | 2022-12-05 | 2023-08-04 | 海豚乐智科技(成都)有限责任公司 | 基于孪生Transformer的多模态图像地面建筑识别方法及装置 |
CN117635967A (zh) * | 2023-11-30 | 2024-03-01 | 中科南京智能技术研究院 | 一种自监督学习里程计量方法、装置、系统及存储介质 |
CN117789253A (zh) * | 2024-02-23 | 2024-03-29 | 东北大学 | 一种基于双网络的视频行人重识别方法 |
CN117789253B (zh) * | 2024-02-23 | 2024-05-03 | 东北大学 | 一种基于双网络的视频行人重识别方法 |
CN118628991A (zh) * | 2024-08-13 | 2024-09-10 | 合肥讯图信息科技有限公司 | 一种基于人脸识别和车牌识别的监测方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
CN112861988B (zh) | 2022-03-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112861988B (zh) | 一种基于注意力图神经网络的特征匹配方法 | |
CN110135366B (zh) | 基于多尺度生成对抗网络的遮挡行人重识别方法 | |
Liu et al. | Learning human pose models from synthesized data for robust RGB-D action recognition | |
Xu et al. | Dktnet: dual-key transformer network for small object detection | |
Gehlot et al. | Analysis of different CNN architectures for tomato leaf disease classification | |
Wang et al. | Pm-gans: Discriminative representation learning for action recognition using partial-modalities | |
Ding et al. | Skeleton-based square grid for human action recognition with 3D convolutional neural network | |
Hu et al. | A spatio-temporal integrated model based on local and global features for video expression recognition | |
Xiao et al. | Adaptivepose: Human parts as adaptive points | |
Marcon et al. | Unsupervised learning of local equivariant descriptors for point clouds | |
Tomas et al. | Human activity recognition using combined deep architectures | |
Salem et al. | Semantic image inpainting using self-learning encoder-decoder and adversarial loss | |
Alzu'Bi et al. | Compact root bilinear cnns for content-based image retrieval | |
Liu et al. | Student behavior recognition from heterogeneous view perception in class based on 3-D multiscale residual dense network for the analysis of case teaching | |
Özbay et al. | 3D Human Activity Classification with 3D Zernike Moment Based Convolutional, LSTM-Deep Neural Networks. | |
Ahmad et al. | Embedded deep vision in smart cameras for multi-view objects representation and retrieval | |
Gowada et al. | Unethical human action recognition using deep learning based hybrid model for video forensics | |
Yu | Deep learning methods for human action recognition | |
Li et al. | Action recognition with spatio-temporal augmented descriptor and fusion method | |
Sharafi et al. | Low altitude aerial scene synthesis using generative adversarial networks for autonomous natural resource management | |
Zou et al. | An intelligent image feature recognition algorithm with hierarchical attribute constraints based on weak supervision and label correlation | |
Al-Barazanchi et al. | Performance evaluation of hybrid CNN for SIPPER plankton image calssification | |
Xia et al. | GCENet: Global contextual exploration network for RGB-D salient object detection | |
Zhao et al. | Lightweight anchor-free one-level feature indoor personnel detection method based on transformer | |
CN117036658A (zh) | 一种图像处理方法及相关设备 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230523 Address after: Floor 14 and 15, Building 1, Block 2, East Tianfu Haichuangyuan, Zizhou Avenue Road, Chengdu City, Sichuan Province, 610000 Patentee after: Southwest University of Science and Technology Sichuan Tianfu New Area Innovation Research Institute Address before: 621010, No. 59, Qinglong Avenue, Fucheng District, Sichuan, Mianyang Patentee before: Southwest University of Science and Technology |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20231108 Address after: 11th Floor, Building 1, No. 118 Jitai Fifth Road, High tech Zone, Chengdu, Sichuan, 610000 Patentee after: CHENGDU HORSENT WISELINK TECHNOLOGY Co.,Ltd. Patentee after: Southwest University of Science and Technology Sichuan Tianfu New Area Innovation Research Institute Address before: Floor 14 and 15, Building 1, Block 2, East Tianfu Haichuangyuan, Zizhou Avenue Road, Chengdu City, Sichuan Province, 610000 Patentee before: Southwest University of Science and Technology Sichuan Tianfu New Area Innovation Research Institute |