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

A method and device for predicting pedestrian trajectory based on deep learning

A motion trajectory and deep learning technology, applied in the computer field, can solve problems such as increased network training, difficulty in labeling, and difficulty in obtaining auxiliary information

Active Publication Date: 2022-04-15
BEIJING SHENRUI BOLIAN TECH CO LTD +1
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally speaking, these auxiliary information are difficult to obtain and label, which adds difficulties to the training of the network.

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
  • A method and device for predicting pedestrian trajectory based on deep learning
  • A method and device for predicting pedestrian trajectory based on deep learning
  • A method and device for predicting pedestrian trajectory based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] The core of the present invention is to propose a scheme for predicting target trajectory by using known frame video and optical flow information, aiming at capturing the surrounding environment information in the actual scene so as to predict the accurate position of the target. The present invention firstly predicts the optical flow information between the existing frames, takes the existing frames and the optical flow info...

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 present invention provides a method and device for predicting pedestrian trajectory based on deep learning, wherein the method includes: acquiring video data, wherein the video data includes known frames, and the known frames include: time t and frames before time t; The flow prediction network predicts the optical flow information between known frames according to two adjacent known frames; the synthetic prediction network predicts the optical flow information of unknown frames according to the optical flow information between known frames and known frames, and obtains t+1 frame; the synthetic prediction network predicts the position of the target pedestrian in the t+1 frame based on the t+1 frame.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a method and device for predicting pedestrian movement trajectories based on deep learning. Background technique [0002] With the development of deep learning, pedestrian trajectory prediction based on neural network has become an important topic. By observing pedestrians in a specific frame of the video and predicting their subsequent moving direction, the visually impaired can be guided to avoid collisions. In-depth research on this direction will bring great convenience to the visually impaired. [0003] Most of the existing algorithms directly use the upper coordinates of the target pedestrian in the known frame as the input of the neural network, and use the circular convolutional neural network or other methods to directly return the position of the target pedestrian in the unknown frame to obtain the trajectory of the target pedestrian. This method There are following di...

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 Patents(China)
IPC IPC(8): G06T7/246G06T7/269G06T7/73G06N3/04G06N3/08
CPCG06T7/246G06T7/269G06T7/73G06N3/084G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30196G06T2207/30241G06N3/045
Inventor 王淑欣刘小青俞益洲李一鸣乔昕
Owner BEIJING SHENRUI BOLIAN TECH CO LTD