Infant attachment is a critical indicator of healthy infant social-emotional functioning, which is typically measured using the gold-standard Strange Situation Procedure (SSP). However, expert-based attachment classifications from the SSP are time-intensive (with respect both to expert training and rating), and do not provide an objective, continuous record of infant behavior. To continuously quantify predictors of key attachment behaviors and dimensions, multimodal movement and audio data were collected during the SSP. Forty-nine 1-year-olds and their mothers participated in the SSP and were tracked in three-dimensional space using five synchronized Kinect sensors; LENA recordings were used to quantify crying duration. Theoretically-informed multimodal measures of attachment-related behavior (e.g., dyadic contact duration, infant velocity of approach toward the mother, and infant crying) were used to predict expert rating scales and dimensional summaries of attachment outcomes. Stepwise regressions identified sets of multimodal objective measures that were significant predictors of eight of nine of the expert ratings of infant attachment behaviors in the SSP’s two reunions. These multimodal measures predicted approximately half of the variance in the summary approach/avoidance and resistance/disorganization attachment dimensions. Incorporating all objective measures as predictors regardless of significance levels, predicted individual ratings within an average of one point on the original Likert scales. The results indicate that relatively inexpensive Kinect and LENA sensors can be harnessed to quantify attachment behavior in a key assessment protocol, suggesting the promise of objective measurement to understanding infant-parent interaction.

婴儿依恋是婴儿社会情感功能健康的关键指标，通常使用黄金标准的陌生情境程序 (SSP) 来衡量。然而，来自 SSP 的基于专家的依恋分类是时间密集型的（在专家培训和评级方面），并且不能提供客观、连续的婴儿行为记录。为了持续量化关键依恋行为和维度的预测因素，在 SSP 期间收集了多模态运动和音频数据。49 名 1 岁儿童和他们的母亲参加了 SSP，并使用五个同步 Kinect 传感器在 3D 空间中进行跟踪；LENA 记录用于量化哭泣持续时间。依恋相关行为的理论信息多模态测量（例如，二元接触持续时间，婴儿靠近母亲的速度和婴儿哭声）被用来预测专家评分量表和依恋结果的维度总结。逐步回归确定了一组多模态客观测量值，它们是 SSP 两次重聚中婴儿依恋行为专家评级中九个的重要预测因子。这些多模态测量预测了总结方法/回避和抵抗/解体依恋维度中大约一半的方差。无论显着性水平如何，将所有客观指标都作为预测指标，在原始李克特量表上预测单个评分的平均值为 1 分。结果表明，相对便宜的 Kinect 和 LENA 传感器可用于量化关键评估协议中的依恋行为，