《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計(jì)應(yīng)用 > 基于ResNet50對(duì)地震救援中人體姿態(tài)估計(jì)的研究
基于ResNet50對(duì)地震救援中人體姿態(tài)估計(jì)的研究
信息技術(shù)與網(wǎng)絡(luò)安全 3期
鄔春學(xué),,賀欣欣
(上海理工大學(xué) 光電信息與計(jì)算機(jī)工程學(xué)院,,上海200093)
摘要: 調(diào)查發(fā)現(xiàn),地震中死亡人數(shù)增加的原因主要是錯(cuò)過救援的黃金時(shí)間,因此可通過救援無人機(jī)自動(dòng)對(duì)受災(zāi)人員進(jìn)行行為識(shí)別與狀態(tài)分析,。人體姿態(tài)估計(jì)是指對(duì)圖像中人體關(guān)節(jié)點(diǎn)和肢體進(jìn)行檢測(cè)的過程,,在人機(jī)交互和行為識(shí)別應(yīng)用中起著重要的作用,,然而由于背景復(fù)雜,、肢體被遮擋等因素導(dǎo)致標(biāo)注人體關(guān)節(jié)點(diǎn)和肢體十分困難。因此提出一種結(jié)合ResNet50及CPM的模型,該模型通過獲取圖像特征和精調(diào)機(jī)制,,計(jì)算出關(guān)節(jié)點(diǎn)依賴關(guān)系,,最后劃分到對(duì)應(yīng)人體。實(shí)驗(yàn)表明,,該模型與其他模型對(duì)比能夠提高復(fù)雜場(chǎng)景下人體姿態(tài)估計(jì)的效果,。
中圖分類號(hào): TP391
文獻(xiàn)標(biāo)識(shí)碼: A
DOI: 10.19358/j.issn.2096-5133.2022.03.009
引用格式: 鄔春學(xué),賀欣欣. 基于ResNet50對(duì)地震救援中人體姿態(tài)估計(jì)的研究[J].信息技術(shù)與網(wǎng)絡(luò)安全,,2022,,41(3):50-58,70.
Research on human posture estimation in earthquake rescue based on ResNet50
Wu Chunxue,,He Xinxin
(School of Optical-Electrical and Computer Engineering,,University of Shanghai for Science and Technology, Shanghai 200093,,China)
Abstract: It was found that, the main reason for such a high number of deaths lies in the missing of prime rescue time. So rescue UAV can be used to recognize the behaviors of affected population automatically and analyze their status. Human pose estimation refers to the process of detecting humans′ joints and limbs in image, which plays a crucial role in human machine interaction and application of action recognition. However, due to the factors such as complex background and covering of limbs, it is very difficult to note the human joints and limbs in image. To address the issue, this paper proposed a model combining ResNet50 and convolutional pose machine(CPM). According to the model, image features are obtained by residual network and the dependence between joints is obtained by fine adjustment mechanism. Finally the key points aggregated are divided to the corresponding human body. Experiment shows that compared with other human pose estimation models, such model can enhance the effect of human post estimation under complex earthquake rescue scenario.
Key words : neural network;human pose estimation,;ResNet50,;part affinity fields;earthquake rescue

0 引言

據(jù)EM-DAT報(bào)道[1]稱,,2000年至2019年間特大地震自然災(zāi)害導(dǎo)致死亡的受災(zāi)人數(shù)在九種自然災(zāi)害死亡人數(shù)中居首位,,大約占總受災(zāi)人數(shù)的58%,在地震發(fā)生后高效率地救援十分必要,?;诔墒斓挠布O(shè)備[2],救援無人機(jī)搜尋傷員對(duì)其進(jìn)行動(dòng)作識(shí)別與狀態(tài)分析,,可顯著提高救援的效率,。因此,開展基于深度學(xué)習(xí)的實(shí)時(shí)無人機(jī)災(zāi)后救援人體姿態(tài)估計(jì)研究顯得十分必要[3-4],。

目前,,無人駕駛的多旋翼無人機(jī)配備了高清攝像頭和高性能的電池,可滿足長(zhǎng)時(shí)間懸停并傳輸震后實(shí)時(shí)救援的畫面[5],。在此基礎(chǔ)上,,通過無人機(jī)獲取的震后救援現(xiàn)場(chǎng)的實(shí)時(shí)圖像,采用深度學(xué)習(xí)檢測(cè)和跟蹤方法[6]對(duì)受災(zāi)后傷員的位置以及人體姿態(tài)進(jìn)行檢測(cè),,以供指揮中心進(jìn)行快速部署救援并能夠掌握震后的全局狀況,。通常情況下,其對(duì)人體骨骼的關(guān)鍵部件的具體檢測(cè)精度有一定的要求,,不僅要對(duì)整個(gè)人體進(jìn)行精準(zhǔn)檢測(cè),,而且還要對(duì)人體的關(guān)鍵節(jié)點(diǎn),例如頭部、肩關(guān)節(jié),、肘關(guān)節(jié),、膝蓋等部分進(jìn)行更詳細(xì)的檢測(cè)和跟蹤,從而掌握更詳細(xì)的震后人員狀態(tài),。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000004026






作者信息:

鄔春學(xué),,賀欣欣

(上海理工大學(xué) 光電信息與計(jì)算機(jī)工程學(xué)院,上海200093)




微信圖片_20210517164139.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載,。