CN117726791A - 从机器学习模型输出推断出的实例分割 - Google Patents

从机器学习模型输出推断出的实例分割 Download PDF

Info

Publication number
CN117726791A
CN117726791A CN202311642181.3A CN202311642181A CN117726791A CN 117726791 A CN117726791 A CN 117726791A CN 202311642181 A CN202311642181 A CN 202311642181A CN 117726791 A CN117726791 A CN 117726791A
Authority
CN
China
Prior art keywords
model
image
roi
rois
size range
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
CN202311642181.3A
Other languages
English (en)
Chinese (zh)
Inventor
S·塔里克
J·W·V·菲尔宾
K·戈埃尔
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.)
Zoox Inc
Original Assignee
Zoox Inc
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
Priority claimed from US16/013,729 external-priority patent/US10936922B2/en
Priority claimed from US16/013,748 external-priority patent/US11592818B2/en
Priority claimed from US16/013,764 external-priority patent/US10817740B2/en
Application filed by Zoox Inc filed Critical Zoox Inc
Publication of CN117726791A publication Critical patent/CN117726791A/zh
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Image Analysis (AREA)
CN202311642181.3A 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割 Pending CN117726791A (zh)

Applications Claiming Priority (8)

Application Number Priority Date Filing Date Title
US16/013,729 2018-06-20
US16/013,729 US10936922B2 (en) 2018-06-20 2018-06-20 Machine learning techniques
US16/013,748 US11592818B2 (en) 2018-06-20 2018-06-20 Restricted multi-scale inference for machine learning
US16/013,748 2018-06-20
US16/013,764 US10817740B2 (en) 2018-06-20 2018-06-20 Instance segmentation inferred from machine learning model output
US16/013,764 2018-06-20
CN201980041346.7A CN112334906B (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割
PCT/US2019/037967 WO2019246250A1 (en) 2018-06-20 2019-06-19 Instance segmentation inferred from machine-learning model output

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201980041346.7A Division CN112334906B (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割

Publications (1)

Publication Number Publication Date
CN117726791A true CN117726791A (zh) 2024-03-19

Family

ID=67138215

Family Applications (3)

Application Number Title Priority Date Filing Date
CN202311642181.3A Pending CN117726791A (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割
CN202311626614.6A Pending CN117710647A (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割
CN201980041346.7A Active CN112334906B (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割

Family Applications After (2)

Application Number Title Priority Date Filing Date
CN202311626614.6A Pending CN117710647A (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割
CN201980041346.7A Active CN112334906B (zh) 2018-06-20 2019-06-19 从机器学习模型输出推断出的实例分割

Country Status (4)

Country Link
EP (1) EP3811285B1 (https=)
JP (2) JP7469237B2 (https=)
CN (3) CN117726791A (https=)
WO (1) WO2019246250A1 (https=)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117726791A (zh) 2018-06-20 2024-03-19 祖克斯有限公司 从机器学习模型输出推断出的实例分割
US11308634B2 (en) * 2020-02-05 2022-04-19 Datalogic Ip Tech S.R.L. Unsupervised anchor handling for machine vision system
CN111401359A (zh) * 2020-02-25 2020-07-10 北京三快在线科技有限公司 目标识别方法、装置、电子设备和存储介质
US11436842B2 (en) 2020-03-13 2022-09-06 Argo AI, LLC Bulb mask representation for traffic light classification
JP7723479B2 (ja) * 2021-02-01 2025-08-14 株式会社デンソーテン 学習用データセット生成装置及び学習用データセット生成方法
JP7672694B2 (ja) * 2021-08-31 2025-05-08 ＤｅｅｐＥｙｅＶｉｓｉｏｎ株式会社 情報処理装置、情報処理方法及びプログラム
US11893084B2 (en) * 2021-09-07 2024-02-06 Johnson Controls Tyco IP Holdings LLP Object detection systems and methods including an object detection model using a tailored training dataset
US20230078218A1 (en) * 2021-09-16 2023-03-16 Nvidia Corporation Training object detection models using transfer learning
US12080074B2 (en) * 2021-11-30 2024-09-03 Zoox, Inc. Center-based detection and tracking
TWI808019B (zh) * 2022-10-03 2023-07-01 漢通科技股份有限公司 基於人工神經網路的物件表面型態的篩選方法與系統
CN116704178B (zh) * 2023-04-04 2025-12-16 支付宝(杭州)数字服务技术有限公司 一种图像的实例分割方法、装置、存储介质及电子设备
WO2025176546A1 (en) * 2024-02-21 2025-08-28 Signify Holding B.V. Determining object boundaries

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106688011B (zh) * 2014-09-10 2018-12-28 北京市商汤科技开发有限公司 用于多类别物体检测的方法和系统
US20180096191A1 (en) * 2015-03-27 2018-04-05 Siemens Aktiengesellschaft Method and system for automated brain tumor diagnosis using image classification
EP3325938B1 (en) * 2015-05-25 2022-05-11 Natarajan, Adarsh Sample stainer
US10192323B2 (en) * 2016-04-08 2019-01-29 Orbital Insight, Inc. Remote determination of containers in geographical region
JP6629678B2 (ja) * 2016-06-16 2020-01-15 株式会社日立製作所 機械学習装置
US10424064B2 (en) * 2016-10-18 2019-09-24 Adobe Inc. Instance-level semantic segmentation system
US10380741B2 (en) * 2016-12-07 2019-08-13 Samsung Electronics Co., Ltd System and method for a deep learning machine for object detection
CN106780536A (zh) * 2017-01-13 2017-05-31 深圳市唯特视科技有限公司 一种基于对象掩码网络的形状感知实例分割方法
JP2018180945A (ja) * 2017-04-13 2018-11-15 株式会社豊田中央研究所 物体検出装置及びプログラム
US10558864B2 (en) * 2017-05-18 2020-02-11 TuSimple System and method for image localization based on semantic segmentation
CN107818313B (zh) * 2017-11-20 2019-05-14 腾讯科技（深圳）有限公司 活体识别方法、装置和存储介质
CN108154196B (zh) * 2018-01-19 2019-10-22 百度在线网络技术（北京）有限公司 用于输出图像的方法和装置
CN117726791A (zh) 2018-06-20 2024-03-19 祖克斯有限公司 从机器学习模型输出推断出的实例分割

Also Published As

Publication number Publication date
EP3811285A1 (en) 2021-04-28
JP2024086791A (ja) 2024-06-28
CN112334906A (zh) 2021-02-05
JP7560692B2 (ja) 2024-10-02
EP3811285B1 (en) 2026-01-28
CN117710647A (zh) 2024-03-15
CN112334906B (zh) 2024-05-17
WO2019246250A1 (en) 2019-12-26
JP2021528757A (ja) 2021-10-21
JP7469237B2 (ja) 2024-04-16

Similar Documents

Publication Publication Date Title
US20230266771A1 (en) Restricted multi-scale inference for machine learning
CN112334906B (zh) 从机器学习模型输出推断出的实例分割
US10936922B2 (en) Machine learning techniques
US10817740B2 (en) Instance segmentation inferred from machine learning model output
US11379998B2 (en) Detector-tracker architecture
JP7682190B2 (ja) オブジェクト速度および／またはヨーレート検出およびトラッキング
CN112292711B (zh) 关联lidar数据和图像数据
US12189718B1 (en) Learned state covariances
US12352597B2 (en) Methods and systems for predicting properties of a plurality of objects in a vicinity of a vehicle
CN102693432B (zh) 使用可靠局部模型更新来调节畅通路径检测
JP2022552138A (ja) 衝突回避知覚システム
US12217431B2 (en) Systems and methods for panoptic segmentation of images for autonomous driving
EP3767543B1 (en) Device and method for operating a neural network
EP4145398A1 (en) Systems and methods for vehicle camera obstruction detection
US12423987B2 (en) System and method for determining object characteristics in real-time
CN112084835A (zh) 基于航拍数据和遥测数据生成地图特征
JP7226368B2 (ja) 物体状態識別装置
Al Khafaji et al. Traffic signs detection and recognition using a combination of YOLO and CNN
CN113139984B (zh) 检测与跟踪融合的长时间无人机目标跟踪方法及系统
Fasina An Improved Traffic Light Colour Detection and Recognition System for Autonomous Vehicles
Fu A novel road traffic accidents recognition model for intersections in mixed-traffic environment using deep learning-based scene and feature understanding
Taegener et al. Automated Data Labeling of Driving Recordings for the Use in supervised-learning Applications for Sensor Fu-sion

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