Mixtures of Gaussian process models for human pose estimation

Discriminative human pose estimation is the problem of inferring the 3D articulated pose of a human directly from an image feature. This is a challenging problem due to the highly non-linear and multi-modal mapping from the image feature space to the pose space. To address this problem, we propose a model employing a mixture of Gaussian processes where each Gaussian process models a local region of the pose space. By employing the models in this way we are able to overcome the limitations of Gaussian processes applied to human pose estimation — their O(N³) time complexity and their uni-modal predictive distribution. Our model is able to give a multi-modal predictive distribution where each mode is represented by a different Gaussian process prediction. A logistic regression model is used to give a prior over each expert prediction in a similar fashion to previous mixture of expert models. We show that this technique outperforms existing state of the art regression techniques on human pose estimation data sets for ballet dancing, sign language and the HumanEva data set.     

用于说话人识别的基于可变因子整合的高斯混合模型

针对传统高斯混合模型在噪声环境下识别率明显下降的问题,在借鉴随机概率分布模型间的α因子融合机制基础上,提出基于可变因子α整合的高斯混合模型。该模型通过引入可变因子使得混合模型中不同成分所占的比重又得到一次调整。实验结果表明,通过对该模型参数进行重估计,在TIMIT/NTIMIT两种不同语料库和不同样本集的情况下识别率较传统高斯模型均有提高。尤其在噪声环境和α因子取最优值时,识别率可提高8%,在NIST评测数据集上与GMM-UBM系统对比,识别率也有提高。     

一种基于局部保持的隐变量模型

隐变量模型是一类有效的降维方法,但是由非线性核映射建立的隐变量模型不能保持数据空间的局部结构。为了克服这个缺点,文中提出一种保持数据局部结构的隐变量模型。该算法充分利用局部保持映射的保局性质,将局部保持映射的目标函数作为低维空间中数据的先验信息,对高斯过程隐变量中的低维数据进行约束,建立局部保持的隐变量。实验结果表明,相比原有的高斯过程隐变量,文中算法较好地保持数据局部结构的效果。     

带隐变量的回归模型EM算法

带有隐变量的回归模型具有非常广泛的应用场合,隐回归模型的参数求解问题依赖于自变量的分布假设。基于自变量的beta分布的假设条件,给出了隐回归模型的EM算法,详细地推导了模型中的参数求解过程,给出了使用牛顿法求解beta分布参数的算法,并提出一个合适的初值选择算法。在模拟数据和真实数据的基础上进行了详细的比较性试验,结果表明,对具有不同分布特征的因变量观察值,EM算法能够有效地求解隐回归模型的参数。     

基于深度信念网与隐变量模型的用户偏好建模

从高维、稀疏的用户评分数据中构建用户偏好模型,存在迭代计算复杂度高、中间结果规模大和难以实现有效推理等问题。为此,提出一种基于深度信念网(DBN)和贝叶斯网(BN)的用户偏好建模方法。采用DBN对评分数据进行分类,用隐变量表示不能直接观测到的用户偏好,利用含隐变量的BN描述评分数据中蕴含的相关属性间的依赖关系及其不确定性。在MovieLens和大众点评数据集上的实验结果表明,该方法能够有效描述评分数据中与用户偏好相关的各属性间的依赖关系,其精确率和执行效率均高于隐变量模型。     

基于高斯过程隐变量模型的图像数据降维算法

针对传统谱算法在数据降维计算复杂度高的缺点,提出一种基于高斯过程隐变量模型的图像数据降维算法。首先,通过高斯过程(Gaussian Process,GP)建立图像数据的概率模型,得到图像数据的隐变量模型;其次,利用概率最大化原则得到最优超参数,通过最优超参数求取最优数据降维结果;最后,实现图像数据降维。选取Yale,ORL两类数据集与传统算法进行人脸识别对比实验,实验结果表明:所提出的算法针对图像数据降维问题有较好的效果,结合支持向量机算法,可有效地对人脸图像进行识别,且有较高的识别率,从而体现出算法对高维数据降维的准确性。     

一种改进的混合高斯背景模型

针对经典混合高斯模型无法识别静态目标的问题,提出一种改进算法。通过加入了参数还原算法,并引入一个反馈调节环节,可以避免静态前景被学习进入背景。当目标停留超过预定帧数时,目标所覆盖的每个像素点的K个高斯函数进行参数还原,避免了目标被更新为背景的一部分。实验结果表明,提出的改进模型,不仅能检测长时间静止目标,而且能识别多模态背景。     

LDNet: Lightweight dynamic convolution network for human pose estimation

Lightweight implementation of existing human pose estimation networks limits the model representation capability, and it cannot effectively deal with problems such as changeable poses, complex backgrounds, and occlusion in practical applications. To address this problem, a lightweight human pose estimation network with dynamic convolution, called LDNet, is proposed in this study. First, we start from a lightweight feature extraction head to reduce the number of image preprocessing parameters. Then, we employ a high-resolution parallel subnetwork to predict precise keypoint heatmaps. To reduce the complexity due to high-resolution representations while maintaining good network performance, we propose a lightweight dynamic convolution. It can cope with changing human poses by adaptively learning different convolution parameters. Finally, to further exploit the relationship between the high-level semantic and spatial structure features for accurately locating different keypoints, we propose a keypoint refinement module based on our lightweight dynamic convolution to improve the keypoint detection and location results. Overall, accurate keypoint prediction results are obtained and compared with those of many existing networks, such as HRNet, the number of parameters is reduced by 82.1% and the calculation complexity is reduced by 47.9%. The model achieves an average precision of 73.5% and 88.7% on the COCO 2017 and MPII datasets, respectively. LDNet also shows good prediction accuracy and robustness on the CrowdPose dataset. The proposed network is superior to existing outstanding lightweight networks and is comparable to existing large-scale human pose estimation networks.