Unlock instant, AI-driven research and patent intelligence for your innovation.

On-vehicle object identification system, automobile, vehicle lamp, classifier learning method, and arithmetic operation device

A computing processing device and object recognition technology, applied in the field of object recognition systems, can solve problems such as increased computing processing costs and the like

Pending Publication Date: 2020-06-09
KOITO MFG CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the higher the resolution of the point cloud data, the more accurate the object recognition based on the point cloud data generated by LiDAR is, but the cost of computing processing increases

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • On-vehicle object identification system, automobile, vehicle lamp, classifier learning method, and arithmetic operation device
  • On-vehicle object identification system, automobile, vehicle lamp, classifier learning method, and arithmetic operation device
  • On-vehicle object identification system, automobile, vehicle lamp, classifier learning method, and arithmetic operation device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0057] Hereinafter, the present invention will be described based on preferred embodiments with reference to the drawings. The same or equivalent constituent elements, members, and processes shown in the drawings are given the same reference numerals, and overlapping descriptions are appropriately omitted. In addition, the embodiment is not to limit the invention but to illustrate, and all the features described in the embodiment or combinations thereof are not necessarily the essence of the invention.

[0058] figure 1 It is a block diagram of the object recognition system 10 of embodiment. This object recognition system 10 is mounted on a vehicle such as an automobile or a motorcycle, and determines the type (category) of an object OBJ existing around the vehicle.

[0059] The object recognition system 10 mainly includes a distance measuring sensor 20 and an arithmetic processing device 40 . The distance measuring sensor 20 scans a light beam in the horizontal direction t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Systems, devices, and methods are provided that enable identification of objects with a small number of horizontal lines. An on-vehicle object identification system 10 is provided with; a ranging sensor 20; and an arithmetic operation device 40. The ranging sensor 20 horizontally scans one beam, and measures the distance to a point P on the surface of an object OBJ. The arithmetic operation device40 includes a classifier 42 that can identify the type of the object OBJ on the basis of point collection data PCD corresponding to one scan line SL acquired by the ranging sensor 20. The classifier42 is mounted on the basis of a learned model acquired through machine learning. The machine learning is carried out by using a plurality of point collection data corresponding to a plurality of scanlines acquired through measurement of a prescribed object by a LiDAR having the scan lines in the vertical direction.

Description

technical field [0001] The present invention relates to object recognition systems. Background technique [0002] Candidates for automotive sensors include LiDAR (Light Detection and Ranging, Laser Imaging Detection and Ranging), cameras, millimeter-wave radar, and ultrasonic sonar. Among them, compared with other sensors, LiDAR has (i) the ability to recognize objects based on point cloud data, (ii) although it is an active sensor, it can perform high-precision detection even in bad weather in the past, iii ) can perform a wide range of measurements, etc., and is expected to become the mainstream of automotive sensing systems in the future. [0003] Patent Document 1: Japanese Patent Laid-Open No. 2017-56935 [0004] Patent Document 2: Japanese Patent Laid-Open No. 2009-98023 [0005] Although the higher the resolution of the point cloud data, the more accurate the object recognition based on the point cloud data generated by LiDAR is, but the cost of computing processin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06V20/58
CPCG06V20/56G06F18/24G06F18/214G01S17/89G01S17/931G01S7/4817G01S7/4802G08G1/015G06N3/08G06V20/58G06N3/02
Inventor 永岛彻
Owner KOITO MFG CO LTD