Object detection method, device, apparatus, storage medium and vehicle

An object detection and object technology, applied in the field of sensors, can solve the problems of long process, high delay, inability to integrate system optimization, etc., to achieve the effect of simplifying the detection process

Inactive Publication Date: 2019-02-15
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing post-fusion multi-sensor detection scheme requires rules and probabilities as the basis for data association. On the

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
  • Object detection method, device, apparatus, storage medium and vehicle
  • Object detection method, device, apparatus, storage medium and vehicle
  • Object detection method, device, apparatus, storage medium and vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Figure 2A It is a flow chart of an object detection method provided in Embodiment 1 of the present invention, Figure 2B It is a schematic diagram of an object detection process applicable to the embodiment of the present invention. This embodiment is applicable to the situation of how to simplify the detection process while being able to detect the objects contained in the scene. The method can be executed by the object detection device in the embodiment of the present invention, the device can be implemented in the form of software and / or hardware, the device can be an independent physical device, and can also be configured in a terminal (such as the control of an autonomous driving mobile carrier frame). Such as Figure 2A and 2B As shown, the method specifically includes the following steps:

[0032] S210. Input the scene point cloud data into the pre-trained point cloud feature extraction model to obtain the point cloud description features of the scene, and i...

Embodiment 2

[0047] image 3 It is a flow chart of an object detection method in Embodiment 2 of the present invention. This embodiment is based on the above embodiment, and further inputs the point cloud description features and image description features of each target area in the scene into the pre-trained Explained in Object Recognition Model. Such as image 3 As shown, the method of this embodiment specifically includes the following steps:

[0048] S310. Input the scene point cloud data into the pre-trained point cloud feature extraction model to obtain the point cloud description features of the scene, and input the scene image data into the pre-trained image feature extraction model to obtain the scene image description features.

[0049] S320. Identify the point cloud description features or image description features of each area in the scene to obtain each candidate object included in the scene, and use the area where the candidate object is located as a target area.

[0050]...

Embodiment 3

[0063] Figure 4 It is a schematic structural diagram of an object detection device provided by Embodiment 3 of the present invention. The device can execute the object detection method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. Such as Figure 4 As shown, the device specifically includes: a description feature acquisition module 410 , a three-dimensional field object detection input module 420 and a detection result acquisition module 430 .

[0064] Wherein, the descriptive feature acquisition module 410 is used to input the scene point cloud data into the pre-trained point cloud feature extraction model to obtain the point cloud description features of the scene, and input the scene image data into the pre-trained image feature extraction model to obtain the image of the scene Descriptive features;

[0065] The object detection input module 420 is used to input the point cl...

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

The embodiment of the invention discloses an object detection method, a device, a storage medium and a vehicle. The method comprises the following steps: inputting scene point cloud data into a pre-trained point cloud feature extraction model to obtain scene point cloud description features; inputting scene image data into a pre-trained image feature extraction model to obtain scene image description features; The point cloud descriptive features and image descriptive features of each target region in the scene are input into a pre-trained object recognition model, and the detection results ofthe objects located at each target region are obtained. Compared with the existing post-fusion multi-sensor detection scheme, the technical scheme of the invention corresponds to the pre-fusion multi-sensor detection scheme of features, does not need to use rules and probabilities as the basis of fusion to carry out data association, and simplifies the detection process while detecting an object.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of sensors, and in particular to an object detection method, device, equipment, storage medium and vehicle. Background technique [0002] With the development of sensor technology, multiple sensors are used to detect the same object or environment at the same time, and the detection results obtained by fusing the detection data of multiple sensors are compared with the detection of the same object or environment by a single sensor. The results are more comprehensive and accurate. Therefore, multi-sensor fusion detection is mostly used in the fields of object detection or target tracking. [0003] At present, the post-fusion multi-sensor detection scheme is mainly used in the multi-sensor fusion detection scheme. A typical post-fusion processing process is as follows: figure 1 The result shown is equivalent to the fusion of results. Sensors 1 and 2 respectively transmit the sensin...

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
IPC IPC(8): G06T7/00G06V10/25G06V10/50G06V10/764G06V20/00
CPCG06T7/0002G06T2207/20081G06T2207/10028G06V20/64G06V20/00G06V10/25G06V10/50G06V10/454G06V10/764G06V10/803G06F18/2413G06F18/251G01S7/4802G01S17/42G01S17/89G06F18/253G06F18/214
Inventor 谢远帆杨子枢王亮
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap