2019英特爾ISEF學(xué)科最佳作品摘要 機(jī)器人與智能機(jī)器（人工智能）Best of Category Abstract: ROBOTICS AND INTELLIGENT MACHINES

獲獎(jiǎng)作品基本信息

年份	2018
學(xué)科	機(jī)器人與智能機(jī)器 ROBOTICS AND INTELLIGENT MACHINES
國(guó)家/州	TX, United States of America

獲獎(jiǎng)作品名稱

Looking through Walls with Artificial Intelligence: An Innovative Solution for Real-Time Retrieval of the Human Figure behind Visual Obstruction

獲獎(jiǎng)作品摘要

Overcoming the visual barrier and developing “see-through vision” has been one of mankind’s long-standing dreams. Unlike visible light, Radio Frequency (RF) signals penetrate opaque obstructions and reflect highly off humans. This project created a breakthrough artificial intelligence model that can be trained to reconstruct continuous video of a 15-point human skeleton even through visual occlusion using RF signals. The AI training process adopted a student/teacher learning procedure inspired by the Feynman Technique for Learning. Video frames and RF data were first collected simultaneously using a co-located setup containing an optical camera and an RF antenna array transceiver. Next, the video frames were processed with a computer-vision-based gait analysis “teacher” module to generate ground-truth human skeletons for each frame. Then, the same type of skeleton was predicted from corresponding RF data using a “student” deep-learning model consisting of a Residual Convolutional Neural Network (CNN), Region Proposal Network (RPN), and Recurrent Neural Network with Long-Short Term Memory (RNN-LSTM) that 1) extracted spatial features from RF images, 2) detected all people present in a scene, and 3) aggregated information over multiple time-steps, respectively. After reducing error between teacher-provided ground-truths and student-created predictions over thousands of training iterations, the model was shown to be capable of accurately and completely predicting the pose of any human behind visual obstruction solely using RF signals. Primary academic contributions include the novel many-to-many imaging methodology, unique RPN/RNN-LSTM integration, newly proposed objective function, and original training pipeline. A simulator was also created.

---

高中生科研 英特爾 Intel ISEF
資訊 · 課程 · 全程指導(dǎo)
請(qǐng)掃碼添加微信好友

[vc_btn title="聯(lián)系電話：(021) 63526628" color="black" align="center" css_animation="fadeIn" link="url:tel%3A02163526628||target:%20_blank|rel:nofollow"]

---

高中生科研學(xué)術(shù)活動(dòng) 英特爾 Intel ISEF 簡(jiǎn)介

英特爾國(guó)際科學(xué)與工程大獎(jiǎng)賽，簡(jiǎn)稱 "ISEF"，由美國(guó) Society for Science and the Public（科學(xué)和公共服務(wù)協(xié)會(huì)）主辦，英特爾公司冠名贊助，是全球規(guī)模最大、等級(jí)最高的中學(xué)生的科研科創(chuàng)賽事。ISEF 的學(xué)術(shù)活動(dòng)學(xué)科包括了所有數(shù)學(xué)、自然科學(xué)、工程的全部領(lǐng)域和部分社會(huì)科學(xué)。ISEF 素有全球青少年科學(xué)學(xué)術(shù)活動(dòng)的“世界杯”之美譽(yù)，旨在鼓勵(lì)學(xué)生團(tuán)隊(duì)協(xié)作，開拓創(chuàng)新，長(zhǎng)期專一深入地研究自己感興趣的課題。

>>> 實(shí)用鏈接匯總 <<<

英特爾 ISEF 學(xué)術(shù)活動(dòng)詳細(xì)介紹

英特爾 ISEF 全程指導(dǎo)方案

· 數(shù)學(xué) · 物理 · 化學(xué) · 生物 · 計(jì)算機(jī) · 工程 ·

學(xué)科簡(jiǎn)介：機(jī)器人與智能機(jī)器 ROBOTICS AND INTELLIGENT MACHINES

Studies in which the use of machine intelligence is paramount to reducing the reliance on human intervention.

Subcategories:

Biomechanics?(BIE):?Studies and apparatus which mimic the role of mechanics in biological systems.

Cognitive Systems?(COG):?Studies/apparatus that operate similarly to the ways humans think and process information. Systems that provide for increased interaction of people and machines to more naturally extend and magnify human expertise, activity, and cognition.

Control Theory?(CON):?Studies that explore the behavior of dynamical systems with inputs, and how their behavior is modified by feedback. ?This includes new theoretical results and the applications of new and established control methods, system modelling, identification and simulation, the analysis and design of control systems (including computer-aided design), and practical implementation.

Machine Learning?(MAC):?Construction and/or study of algorithms that can learn from data.

Robot Kinematics?(KIN):?The study of movement in robotic systems.

Other?(OTH):?Studies that cannot be assigned to one of the above subcategories.?If the project involves multiple subcategories, the principal subcategory should be chosen instead of Other.