公开(公告)号：US10732943B2

公开(公告)日：2020-08-04

申请号：US15949150

申请日：2018-04-10

Applicant: BEIJING DEEPHI TECHNOLOGY CO., LTD.

Inventor： Xiaoming Sun ,  Lingzhi Sui ,  Hong Luo ,  Yi Shan ,  Song Yao

IPC: G06F8/41 ,  G06F8/30 ,  G06N3/08 ,  G06N3/10 ,  G06F8/71 ,  G06F8/54

Abstract: The disclosure provides a compilation method and system for heterogeneous computing platform, and a runtime method and system for supporting program execution on the heterogeneous computing platform. Inputting a trained neural network model to a Neural Network (NN) optimizing compiler to generate an NN assembly file corresponding to the neural network; inputting the NN assembly file to an NN assembler to generate an NN binary file corresponding to the neural network; compilation and assembling a neural network application developed by users in a high-level language using a host compiler toolchain to generate a corresponding host assembly file and a host binary file in sequence; and linking the NN binary file and the host binary file using a host linker to generate a single hybrid linking executable file. The technical solution of the present disclosure has the advantages such as good computing performance, strong scalability, strong compatibility and high flexibility.

公开(公告)号：US20180186452A1

公开(公告)日：2018-07-05

申请号：US15860772

申请日：2018-01-03

Applicant: Beijing Deephi Technology Co., Ltd.

Inventor： Lu Tian ,  Yi Shan ,  Song Yao

IPC: B64C39/02 ,  G05D1/00 ,  G06K9/46 ,  G06T7/70 ,  G06T11/60 ,  G06T5/20

CPC classification number: B64C39/024 ,  B64C2201/127 ,  B64C2201/141 ,  G05D1/0016 ,  G05D1/0033 ,  G05D1/0088 ,  G05D1/0094 ,  G06F3/017 ,  G06F3/0304 ,  G06K9/00369 ,  G06K9/0063 ,  G06K9/4604 ,  G06T5/20 ,  G06T7/70 ,  G06T11/60 ,  G06T2207/30196

Abstract: An unmanned aerial vehicle interactive apparatus based on a deep learning posture estimation is provided. The apparatus (10) comprises: a shooting unit (11) for shooting an object video; a key frame extraction unit (12) for extracting a key frame image relating to an object from the shot object video; a posture estimation unit (13) for recognizing an object posture with respect to the key frame image based on an image recognition algorithm of a deep convolutional neural network; and an unmanned aerial vehicle operation control unit (14) for converting the recognized object posture into a control instruction so as to control the operation of the unmanned aerial vehicle. A human posture estimation is used to control the unmanned aerial vehicle conveniently. Moreover, in the key frame extraction and posture estimation, faster and more accurate results can be obtained by using the deep convolution neural network algorithm.