CNIPA.AI
返回搜索
档案

Target detection method, vehicle and storage medium

其他/未提供未知

数据来源:EPO OPS

正文暂时无法获取,您仍可查看已取得的基本信息。

92763658专利族
§ Ⅰ

卷宗概要

申请人

BYD CO LTD

申请号

CN202310326277

发明人

ZHANG KAIYAN; YANG DONGSHENG; WANG HUAN; XU CHI

申请日

Mar 22, 2023

公开日

Sep 24, 2024

专利族 ID

92763658

IPC 分类

G06N3/045G06N3/0464G06N3/0475G06N3/088G06N3/09G06N3/094G06V10/774G06V10/82G06V20/58

CPC 分类

G06N3/045G06N3/0464G06N3/0475G06N3/088G06N3/09G06N3/094G06V10/774G06V10/82G06V20/58G06V2201/07G06V2201/08

The invention relates to a target detection method, a vehicle and a storage medium, and the method comprises the steps: carrying out the processing of a target image through a target detection model, obtaining a target detection result, and enabling the target detection model to be obtained based on a sample detection image training basic network, the sample detection image is obtained by performing image transformation on a first sample image and a second sample image, the first sample image comprises at least one target object in a plurality of preset target objects, and the second sample image does not comprise the preset target object. Therefore, the first sample image containing the unusual obstacles and the second sample image not containing the unusual obstacles can be processed through a plurality of image transformation methods, and the sample detection image containing more unusual obstacles is obtained. Therefore, the target detection model obtained through sample detection image training can have a good recognition capability on uncommon obstacles, and the recognition accuracy of the uncommon obstacles is improved.

EPO 研究资料

选择栏目后,按需获取当前文献的官方资料。

选择上方栏目查看对应资料。

专利研究工具