基于深度Alignment网络的足部测量

足部测量在很多领域有重要作用。三维足部测量受到设备和算法的限制,难以方便快捷地测量足部。结合图像测量和深度神经网络,提出一种方便快捷的足部测量方法。基于足部生理结构分析,提取足部关键点并基于关键点定义了测量参数;针对足部关键点检测,优化了DAN(Deep Alignment Network)模型的激活函数和损失函数,并定义了一种基于手持相机的数据采集方式;检测足部关键点,测量足部主要参数。结果显示,该方法基于手持相机采集数据能够便捷地测量足部参数,并具有较高的精度。

Foot Measurement Based on Deep Alignment Network

Foot measurement plays an important role in many areas. Limited by equipment and algorithms, three-dimensional foot measurement cannot make a convenient and quick foot measurement. A method is proposed by combining the image measurement with the deep neural network. Based on the physiological structure analysis of foot, key points are extracted and the measurement parameters are defined. During the key point detection of foot, the activation function and loss function of DAN (Deep Alignment Network) model is optimized, and a data acquisition method is defined based on the handheld camera. Foot key points are detected, and main parameters are measured. Experimental results show that collecting data based on handheld camera can conveniently measure foot parameters and the precision is high.