基于樹結(jié)構(gòu)分層隨機(jī)森林在非約束環(huán)境下的頭部姿態(tài)估計(jì)
doi: 10.11999/JEIT140433 cstr: 32379.14.JEIT140433
Head Pose Estimation Based on Tree-structure Cascaded Random Forests in Unconstrained Environment
-
摘要: 頭部姿態(tài)估計(jì)是人類行為和注意力的關(guān)鍵，受到光照、噪聲、身份、遮擋等許多因素的影響。為了提高非約束環(huán)境下的估計(jì)準(zhǔn)確率和魯棒性，該論文提出了樹結(jié)構(gòu)分層隨機(jī)森林在非約束環(huán)境下的多類頭部姿態(tài)估計(jì)。首先，為了消除不同環(huán)境的噪聲影響，提取人臉區(qū)域的組合紋理特征，對人臉區(qū)域進(jìn)行積極人臉子區(qū)域的分類，分類結(jié)果作為樹結(jié)構(gòu)分層隨機(jī)森林的先驗(yàn)知識輸入；其次，提出了一種樹結(jié)構(gòu)分層隨機(jī)森林算法，分層估計(jì)多自由度下的頭部姿態(tài)；再次，為了增強(qiáng)算法的分類能力，使用自適應(yīng)高斯混合模型作為多層次子森林葉子節(jié)點(diǎn)的投票模型。在多個(gè)公共數(shù)據(jù)集上的多種非約束實(shí)驗(yàn)環(huán)境下進(jìn)行頭部姿態(tài)估計(jì)，最終實(shí)驗(yàn)結(jié)果表明所提算法在不同質(zhì)量的圖像上都有很好的估計(jì)準(zhǔn)確率和魯棒性。
-
關(guān)鍵詞:
- 頭部姿態(tài)估計(jì) /
- 非約束環(huán)境 /
- 樹結(jié)構(gòu)分層隨機(jī)森林 /
- 人臉積極子區(qū)域先驗(yàn)分類 /
- 自適應(yīng)高斯混合模型
Abstract: Head pose estimation is an important evaluating indicator of human attention, which depends on many factors, such as illumination, noise, identification, occlusion and so on. In order to enhance estimation efficiency and accuracy, this paper presents tree-structure cascaded random forests to estimate head pose in different quality images. First, in order to eliminate the influence of different environment noise, combined texture features in random forests for positive facial patch classification are extracted, which will be the privileged inputs to estimate head pose. Second, a coarse-to-fine approach is proposed to estimate head pose both in the yaw and pitch, which is called tree-structure cascaded random forests. Third, an adaptive Gaussian mixture model is used to enhance discriminate vote energy in the tree distribution. This framework is evaluated in unconstrained environmental datasets. The experiments show that the proposed approach has a remarkable and robust performance in different quality images. -
計(jì)量
- 文章訪問數(shù): 2581
- HTML全文瀏覽量: 151
- PDF下載量: 868
- 被引次數(shù): 0
下載:
