CN115223117A - 三维目标检测模型的训练和使用方法、装置、介质及设备 - Google Patents
三维目标检测模型的训练和使用方法、装置、介质及设备 Download PDFInfo
- Publication number
- CN115223117A CN115223117A CN202210602131.1A CN202210602131A CN115223117A CN 115223117 A CN115223117 A CN 115223117A CN 202210602131 A CN202210602131 A CN 202210602131A CN 115223117 A CN115223117 A CN 115223117A
- Authority
- CN
- China
- Prior art keywords
- loss function
- dimensional
- feature map
- detection model
- distillation
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 252
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000006870 function Effects 0.000 claims abstract description 228
- 238000004821 distillation Methods 0.000 claims abstract description 140
- 230000004044 response Effects 0.000 claims abstract description 44
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000010586 diagram Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 8
- 239000000523 sample Substances 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 230000001629 suppression Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims 2
- 238000013140 knowledge distillation Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (13)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210602131.1A CN115223117B (zh) | 2022-05-30 | 2022-05-30 | 三维目标检测模型的训练和使用方法、装置、介质及设备 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210602131.1A CN115223117B (zh) | 2022-05-30 | 2022-05-30 | 三维目标检测模型的训练和使用方法、装置、介质及设备 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115223117A true CN115223117A (zh) | 2022-10-21 |
CN115223117B CN115223117B (zh) | 2023-05-30 |
Family
ID=83608056
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210602131.1A Active CN115223117B (zh) | 2022-05-30 | 2022-05-30 | 三维目标检测模型的训练和使用方法、装置、介质及设备 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115223117B (zh) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116229209A (zh) * | 2023-02-14 | 2023-06-06 | 北京百度网讯科技有限公司 | 目标模型的训练方法、目标检测方法及装置 |
CN116524329A (zh) * | 2023-07-04 | 2023-08-01 | 吉咖智能机器人有限公司 | 用于低算力平台的网络模型构建方法、装置、设备和介质 |
CN117315402A (zh) * | 2023-11-02 | 2023-12-29 | 北京百度网讯科技有限公司 | 三维对象检测模型的训练方法及三维对象检测方法 |
CN117351450A (zh) * | 2023-12-06 | 2024-01-05 | 吉咖智能机器人有限公司 | 一种单目3d检测方法、装置、电子设备及存储介质 |
CN117711609A (zh) * | 2024-02-04 | 2024-03-15 | 广州中大医疗器械有限公司 | 一种基于大数据的神经移植方案推荐方法及系统 |
CN118799665A (zh) * | 2024-09-12 | 2024-10-18 | 烟台大学 | 一种基于跨模态解耦知识转移的三维目标检测方法及系统 |
CN118918418A (zh) * | 2024-10-09 | 2024-11-08 | 杭州海康威视数字技术股份有限公司 | 一种目标检测模型的训练方法、装置及电子设备 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180268292A1 (en) * | 2017-03-17 | 2018-09-20 | Nec Laboratories America, Inc. | Learning efficient object detection models with knowledge distillation |
CN111462137A (zh) * | 2020-04-02 | 2020-07-28 | 中科人工智能创新技术研究院(青岛)有限公司 | 一种基于知识蒸馏和语义融合的点云场景分割方法 |
US20200293904A1 (en) * | 2019-03-13 | 2020-09-17 | Cortica Ltd. | Method for object detection using knowledge distillation |
CN112560631A (zh) * | 2020-12-09 | 2021-03-26 | 昆明理工大学 | 一种基于知识蒸馏的行人重识别方法 |
CN112906502A (zh) * | 2021-01-29 | 2021-06-04 | 北京百度网讯科技有限公司 | 目标检测模型的训练方法、装置、设备以及存储介质 |
CN113569882A (zh) * | 2020-04-28 | 2021-10-29 | 上海舜瞳科技有限公司 | 一种基于知识蒸馏的快速行人检测方法 |
CN113705432A (zh) * | 2021-08-26 | 2021-11-26 | 京东鲲鹏(江苏)科技有限公司 | 一种模型训练、三维目标检测方法、装置、设备及介质 |
CN114037046A (zh) * | 2021-09-27 | 2022-02-11 | 北京旷视科技有限公司 | 神经网络模型的蒸馏方法、装置及电子系统 |
-
2022
- 2022-05-30 CN CN202210602131.1A patent/CN115223117B/zh active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180268292A1 (en) * | 2017-03-17 | 2018-09-20 | Nec Laboratories America, Inc. | Learning efficient object detection models with knowledge distillation |
US20200293904A1 (en) * | 2019-03-13 | 2020-09-17 | Cortica Ltd. | Method for object detection using knowledge distillation |
CN111462137A (zh) * | 2020-04-02 | 2020-07-28 | 中科人工智能创新技术研究院(青岛)有限公司 | 一种基于知识蒸馏和语义融合的点云场景分割方法 |
CN113569882A (zh) * | 2020-04-28 | 2021-10-29 | 上海舜瞳科技有限公司 | 一种基于知识蒸馏的快速行人检测方法 |
CN112560631A (zh) * | 2020-12-09 | 2021-03-26 | 昆明理工大学 | 一种基于知识蒸馏的行人重识别方法 |
CN112906502A (zh) * | 2021-01-29 | 2021-06-04 | 北京百度网讯科技有限公司 | 目标检测模型的训练方法、装置、设备以及存储介质 |
CN113705432A (zh) * | 2021-08-26 | 2021-11-26 | 京东鲲鹏(江苏)科技有限公司 | 一种模型训练、三维目标检测方法、装置、设备及介质 |
CN114037046A (zh) * | 2021-09-27 | 2022-02-11 | 北京旷视科技有限公司 | 神经网络模型的蒸馏方法、装置及电子系统 |
Non-Patent Citations (3)
Title |
---|
WANG T等: "Distilling object detection with fine-grained feature imitation", 《CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
张彤彤;董军宇;赵浩然;李琼;孙鑫;: "基于知识蒸馏的轻量型浮游植物检测网络", 应用科学学报 * |
赖叶静;郝珊锋;黄定江;: "深度神经网络模型压缩方法与进展", 华东师范大学学报(自然科学版) * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116229209A (zh) * | 2023-02-14 | 2023-06-06 | 北京百度网讯科技有限公司 | 目标模型的训练方法、目标检测方法及装置 |
CN116229209B (zh) * | 2023-02-14 | 2023-11-07 | 北京百度网讯科技有限公司 | 目标模型的训练方法、目标检测方法及装置 |
CN116524329A (zh) * | 2023-07-04 | 2023-08-01 | 吉咖智能机器人有限公司 | 用于低算力平台的网络模型构建方法、装置、设备和介质 |
CN116524329B (zh) * | 2023-07-04 | 2023-08-29 | 吉咖智能机器人有限公司 | 用于低算力平台的网络模型构建方法、装置、设备和介质 |
CN117315402A (zh) * | 2023-11-02 | 2023-12-29 | 北京百度网讯科技有限公司 | 三维对象检测模型的训练方法及三维对象检测方法 |
CN117351450A (zh) * | 2023-12-06 | 2024-01-05 | 吉咖智能机器人有限公司 | 一种单目3d检测方法、装置、电子设备及存储介质 |
CN117351450B (zh) * | 2023-12-06 | 2024-02-27 | 吉咖智能机器人有限公司 | 一种单目3d检测方法、装置、电子设备及存储介质 |
CN117711609A (zh) * | 2024-02-04 | 2024-03-15 | 广州中大医疗器械有限公司 | 一种基于大数据的神经移植方案推荐方法及系统 |
CN117711609B (zh) * | 2024-02-04 | 2024-05-03 | 广州中大医疗器械有限公司 | 一种基于大数据的神经移植方案推荐方法及系统 |
CN118799665A (zh) * | 2024-09-12 | 2024-10-18 | 烟台大学 | 一种基于跨模态解耦知识转移的三维目标检测方法及系统 |
CN118918418A (zh) * | 2024-10-09 | 2024-11-08 | 杭州海康威视数字技术股份有限公司 | 一种目标检测模型的训练方法、装置及电子设备 |
Also Published As
Publication number | Publication date |
---|---|
CN115223117B (zh) | 2023-05-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115223117B (zh) | 三维目标检测模型的训练和使用方法、装置、介质及设备 | |
CN109118564B (zh) | 一种基于融合体素的三维点云标记方法和装置 | |
US10817752B2 (en) | Virtually boosted training | |
CN114724120B (zh) | 基于雷视语义分割自适应融合的车辆目标检测方法及系统 | |
CN113378686B (zh) | 一种基于目标中心点估计的两阶段遥感目标检测方法 | |
CN112233097A (zh) | 基于空时域多维融合的道路场景他车检测系统和方法 | |
CN109029363A (zh) | 一种基于深度学习的目标测距方法 | |
CN115631344B (zh) | 一种基于特征自适应聚合的目标检测方法 | |
CN115797736B (zh) | 目标检测模型的训练和目标检测方法、装置、设备和介质 | |
Xiong et al. | Contrastive learning for automotive mmWave radar detection points based instance segmentation | |
Kapoor et al. | An intelligent railway surveillance framework based on recognition of object and railway track using deep learning | |
CN111126278A (zh) | 针对少类别场景的目标检测模型优化与加速的方法 | |
CN116703996A (zh) | 基于实例级自适应深度估计的单目三维目标检测算法 | |
CN113160117A (zh) | 一种自动驾驶场景下的三维点云目标检测方法 | |
CN114973031A (zh) | 一种无人机视角下的可见光-热红外图像目标检测方法 | |
CN116206275B (zh) | 基于知识蒸馏的识别模型训练方法及装置 | |
CN114639021A (zh) | 一种目标检测模型的训练方法及目标划分方法 | |
Zhang et al. | CE-RetinaNet: A channel enhancement method for infrared wildlife detection in UAV images | |
CN111126327B (zh) | 车道线检测方法、系统、车载系统及车辆 | |
CN116863426A (zh) | 基于扩散模型的三维点云目标检测方法与装置 | |
CN115937520A (zh) | 基于语义信息引导的点云运动目标分割方法 | |
Zhang et al. | Depth monocular estimation with attention-based encoder-decoder network from single image | |
CN117475142A (zh) | 面向自动驾驶基于ViT的毫米波雷达点云分割方法 | |
CN114842313B (zh) | 基于伪点云的目标检测方法、装置、电子设备和存储介质 | |
CN115719485A (zh) | 一种基于类别引导的路侧交通目标检测方法 |
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 | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: 100 meters west of Changhou Road, Changxingzhuang Village, Xiaotangshan Town, Changping District, Beijing 102211, 2nd Floor, Silk Road Style (Beijing) Hotel Management Service Co., Ltd. 821645 Patentee after: Beijing Feichi Era Technology Co.,Ltd. Country or region after: China Patentee after: Jiuzhi (Suzhou) Intelligent Technology Co.,Ltd. Address before: 100 meters west of Changhou Road, Changxingzhuang Village, Xiaotangshan Town, Changping District, Beijing 102211, 2nd Floor, Silk Road Style (Beijing) Hotel Management Service Co., Ltd. 821645 Patentee before: Jiuzhizhixing (Beijing) Technology Co.,Ltd. Country or region before: China Patentee before: Jiuzhi (Suzhou) Intelligent Technology Co.,Ltd. |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20241107 Address after: Room A-T1064, Building 3, No. 20 Yong'an Road, Shilong Economic Development Zone, Mentougou District, Beijing, 102300 Patentee after: Jiushi Intelligence (Beijing) Technology Co.,Ltd. Country or region after: China Patentee after: Jiuzhi (Suzhou) Intelligent Technology Co.,Ltd. Address before: 100 meters west of Changhou Road, Changxingzhuang Village, Xiaotangshan Town, Changping District, Beijing 102211, 2nd Floor, Silk Road Style (Beijing) Hotel Management Service Co., Ltd. 821645 Patentee before: Beijing Feichi Era Technology Co.,Ltd. Country or region before: China Patentee before: Jiuzhi (Suzhou) Intelligent Technology Co.,Ltd. |