文献类型：期刊文献

英文题名：They Might Be Stalking Me: Edge-Based Multi-Object Tracking and Temporal Risk Modeling for Wearable Stalking Detection

作者：Aimoerfu[1,2];Pan, Yun[1];Li, Chunfang[1];Deng, Yao[3]

第一作者：Aimoerfu

通讯作者：Aimoerfu[1];Aimoerfu[2]

机构：[1]Commun Univ China, Sch Comp & Cyber Sci, Beijing 100024, Peoples R China;[2]Keio Univ, Grad Sch Sci & Technol, Minato, Tokyo 1080073, Japan;[3]Beijing Union Univ, Special Educ Coll, Beijing 100101, Peoples R China

第一机构：Commun Univ China, Sch Comp & Cyber Sci, Beijing 100024, Peoples R China

通讯机构：[1]corresponding author), Commun Univ China, Sch Comp & Cyber Sci, Beijing 100024, Peoples R China;[2]corresponding author), Keio Univ, Grad Sch Sci & Technol, Minato, Tokyo 1080073, Japan.

年份：2026

卷号：15

期号：12

外文期刊名：ELECTRONICS

收录：;EI(收录号：20262620991000);WOS:【SCI-EXPANDED(收录号:WOS:001802192300001)】；

基金：This research received no external funding.

语种：英文

外文关键词：human-centered computing accessibility; empirical studies in accessibility; accessibility design and evaluation methods; stalking detection; wearable computing; user-centered design; blind and low vision; computer vision

摘要：Computer vision (CV) has significantly advanced in object detection and multi-object tracking; however, its application to modeling safety-critical social behaviors for blind and low-vision (BLV) individuals remains limited. In particular, sustained behaviors such as stalking-characterized by persistent proximity and trajectory consistency-have not been systematically addressed within wearable assistive systems. To investigate this gap, we first conducted a formative user study combining semi-structured interviews and behavioral observations to identify safety concerns and wearable design requirements among BLV participants. The findings reveal recurring concerns regarding prolonged following behaviors and highlight the importance of privacy-preserving, socially unobtrusive device configurations. Guided by these insights, we develop a shoulder-slung wearable system integrating dual-camera sensing with an edge-based vision processing pipeline. We reformulate stalking detection as a temporal behavioral persistence problem built upon multi-object tracking (MOT). Leveraging FairMOT for identity-preserving tracking and monocular depth estimation for spatial modeling, we introduce an online temporal persistence-based risk scoring mechanism that accumulates proximity and directional consistency over time. The complete pipeline operates in real time on an embedded platform without cloud dependency. By bridging user-centered design and behavior-oriented visual inference, this work demonstrates how MOT outputs can be extended beyond identity preservation to support temporally coherent safety assessment in wearable assistive contexts.