本文關(guān)鍵詞： 手勢(shì)識(shí)別 圖像去噪 小波變換 多尺度雙邊濾波　出處：《北京理工大學(xué)學(xué)報(bào)》2017年04期 　論文類型：期刊論文

【摘要】：手勢(shì)識(shí)別是人機(jī)交互中的重要研究領(lǐng)域,車載手勢(shì)識(shí)別系統(tǒng)可以減少駕駛員手動(dòng)操作儀表導(dǎo)致的分心,提高駕駛安全性.受光照變化、汽車環(huán)境、攝像頭成像質(zhì)量等各因素的影響,車載手勢(shì)圖像中常會(huì)存在大量復(fù)雜噪聲.這些噪聲嚴(yán)重影響后續(xù)手勢(shì)分割、特征提取和手勢(shì)識(shí)別的準(zhǔn)確性.針對(duì)手勢(shì)圖像中存在的噪聲問(wèn)題,本文提出了一種適用于車載手勢(shì)圖像處理的新方法.該方法先對(duì)小波分解后的各高頻子帶采用不同方向的一維非線性擴(kuò)散濾波處理得到初步去噪手勢(shì)圖,在此基礎(chǔ)上用多尺度雙邊濾波對(duì)圖像再次處理.實(shí)驗(yàn)結(jié)果表明,本文方法可以較好地去除車載手勢(shì)圖中噪聲,抑制車載手勢(shì)圖細(xì)節(jié)的模糊.
[Abstract]:Gesture recognition is an important research field in human-computer interaction, vehicle gesture recognition system can lead to a reduction of manual operation of instrument driver distraction, improve driving safety. Affected by illumination changes, automobile environment, various factors affecting the imaging quality of the camera, due to the existence of a large number of complex vehicle gesture image noise. The noises seriously affect subsequent gesture segmentation, the accuracy of feature extraction and gesture recognition. Aiming at the problem of noise exists in gesture image, this paper proposes a new method suitable for vehicle gesture image processing. Firstly, the high frequency sub bands after wavelet decomposition of one-dimensional nonlinear diffusion filtering with different direction of preliminary denoising based on gesture map using multi scale bilateral filtering for image processing again. The experimental results show that this method can effectively remove the noise of vehicle gesture map, restraining the car The fuzziness of the details of the gestures.

【作者單位】： 太原理工大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61540007,61373100) 虛擬現(xiàn)實(shí)技術(shù)與系統(tǒng)國(guó)家重點(diǎn)實(shí)驗(yàn)室資助項(xiàng)目(BUAA-VR-15KF02,BUAA-VR-16KF-13)
【分類號(hào)】：TP391.41;U463.6

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 ;新技術(shù)[J];產(chǎn)品可靠性報(bào)告;2014年06期

，

本文編號(hào)：1527628