CN115004259A - 对象识别方法、装置、计算机设备和存储介质 - Google Patents

对象识别方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
CN115004259A
CN115004259A CN202080092994.8A CN202080092994A CN115004259A CN 115004259 A CN115004259 A CN 115004259A CN 202080092994 A CN202080092994 A CN 202080092994A CN 115004259 A CN115004259 A CN 115004259A
Authority
CN
China
Prior art keywords
point cloud
image
target
features
feature
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
Application number
CN202080092994.8A
Other languages
English (en)
Other versions
CN115004259B (zh
Inventor
张磊杰
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.)
DeepRoute AI Ltd
Original Assignee
DeepRoute AI 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 DeepRoute AI Ltd filed Critical DeepRoute AI Ltd
Publication of CN115004259A publication Critical patent/CN115004259A/zh
Application granted granted Critical
Publication of CN115004259B publication Critical patent/CN115004259B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Abstract

一种对象识别方法，包括：获取目标运动对象对应的当前场景图像以及当前场景点云(S202)；对所述当前场景图进行图像特征提取，得到初始图像特征，对所述当前场景点云进行点云特征提取，得到初始点云特征(S204)；获取所述当前场景图像对应的目标图像位置，基于所述初始点云特征中，所述目标图像位置对应的点云特征，对所述初始图像特征进行融合处理，得到目标图像特征(S206)；获取当前场景点云对应的目标点云位置，基于所述初始图像特征中，所述目标点云位置对应的图像特征，对所述初始点云特征进行融合处理，得到目标点云特征(S208)；基于所述目标图像特征以及所述目标点云特征，确定场景对象对应的对象位置(S210)；基于所述场景对象对应的位置控制所述目标运动对象进行运动(S212)。

Description

PCT国内申请，说明书已公开。

Claims (10)

  1. PCT国内申请，权利要求书已公开。
CN202080092994.8A 2020-11-11 2020-11-11 对象识别方法、装置、计算机设备和存储介质 Active CN115004259B (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/128125 WO2022099510A1 (zh) 2020-11-11 2020-11-11 对象识别方法、装置、计算机设备和存储介质

Publications (2)

Publication Number Publication Date
CN115004259A true CN115004259A (zh) 2022-09-02
CN115004259B CN115004259B (zh) 2023-08-15

Family

ID=81601893

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080092994.8A Active CN115004259B (zh) 2020-11-11 2020-11-11 对象识别方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN115004259B (zh)
WO (1) WO2022099510A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116740669A (zh) * 2023-08-16 2023-09-12 之江实验室 多目图像检测方法、装置、计算机设备和存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116246287B (zh) * 2023-03-15 2024-03-22 北京百度网讯科技有限公司 目标对象识别方法、训练方法、装置以及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110045729A (zh) * 2019-03-12 2019-07-23 广州小马智行科技有限公司 一种车辆自动驾驶方法及装置
US10634793B1 (en) * 2018-12-24 2020-04-28 Automotive Research & Testing Center Lidar detection device of detecting close-distance obstacle and method thereof
CN111191600A (zh) * 2019-12-30 2020-05-22 深圳元戎启行科技有限公司 障碍物检测方法、装置、计算机设备和存储介质
CN111563923A (zh) * 2020-07-15 2020-08-21 浙江大华技术股份有限公司 获得稠密深度图的方法及相关装置
CN111797734A (zh) * 2020-06-22 2020-10-20 广州视源电子科技股份有限公司 车辆点云数据处理方法、装置、设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10634793B1 (en) * 2018-12-24 2020-04-28 Automotive Research & Testing Center Lidar detection device of detecting close-distance obstacle and method thereof
CN110045729A (zh) * 2019-03-12 2019-07-23 广州小马智行科技有限公司 一种车辆自动驾驶方法及装置
CN111191600A (zh) * 2019-12-30 2020-05-22 深圳元戎启行科技有限公司 障碍物检测方法、装置、计算机设备和存储介质
CN111797734A (zh) * 2020-06-22 2020-10-20 广州视源电子科技股份有限公司 车辆点云数据处理方法、装置、设备和存储介质
CN111563923A (zh) * 2020-07-15 2020-08-21 浙江大华技术股份有限公司 获得稠密深度图的方法及相关装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116740669A (zh) * 2023-08-16 2023-09-12 之江实验室 多目图像检测方法、装置、计算机设备和存储介质
CN116740669B (zh) * 2023-08-16 2023-11-14 之江实验室 多目图像检测方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
WO2022099510A1 (zh) 2022-05-19
CN115004259B (zh) 2023-08-15

Similar Documents

Publication Publication Date Title
CN110163904B (zh) 对象标注方法、移动控制方法、装置、设备及存储介质
CN111223135B (zh) 通过使用雷达和运动数据的单目相机来增强距离估计的系统和方法
US11442464B2 (en) Bird's eye view map based recognition and motion prediction for autonomous systems
US11074438B2 (en) Disentangling human dynamics for pedestrian locomotion forecasting with noisy supervision
CN113424079A (zh) 障碍物检测方法、装置、计算机设备和存储介质
CN113228043A (zh) 移动平台基于神经网络的障碍物检测及关联的系统和方法
CN113678136A (zh) 基于无人驾驶技术的障碍物检测方法、装置和计算机设备
KR20200132468A (ko) 첨단 운전자 지원 장치 및 이의 객체를 검출하는 방법
JP7135665B2 (ja) 車両制御システム、車両の制御方法及びコンピュータプログラム
US20210397855A1 (en) Monocular depth supervision from 3d bounding boxes
WO2022099510A1 (zh) 对象识别方法、装置、计算机设备和存储介质
US11727588B2 (en) Depth estimation based on ego-motion estimation and residual flow estimation
KR20230070253A (ko) 포인트 클라우드들로부터의 효율적인 3차원 객체 검출
CN110262487B (zh) 一种障碍物检测方法、终端及计算机可读存储介质
US20210064913A1 (en) Driving assistant system, electronic device, and operation method thereof
EP4246437A1 (en) Method and apparatus for detecting motion information of target, and device and medium
US11321859B2 (en) Pixel-wise residual pose estimation for monocular depth estimation
CN114998856B (zh) 一种多相机图像的3d目标检测方法、装置、设备及介质
CN116469079A (zh) 一种自动驾驶bev任务学习方法及相关装置
US11625905B2 (en) System and method for tracking occluded objects
US11531842B2 (en) Invertible depth network for image reconstruction and domain transfers
US11551363B2 (en) Systems and methods for self-supervised residual flow estimation
CN116681739A (zh) 目标运动轨迹生成方法、装置及电子设备
US20220300768A1 (en) Evaluation process for a multi-task network
CN114092899A (zh) 从输入数据中识别对象的方法和设备

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