发表机构
Manchester Metropolitan University; University of Huddersfield; The University of Manchester（曼彻斯特城市大学; 哈德斯菲尔德大学; 曼彻斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种可解释的行人路径规划方法，通过视觉-语言模型生成的标题作为中间表示来估计感知安全，在街景图像上达到与图像嵌入相当的性能，但现场验证显示基准增益未能预测部署增益。
AI 中文摘要
本文提出了一种可解释的行人路径规划方法，其中感知安全通过街景图像经由显式的自然语言中间表示来估计。在进行任何评分之前，会生成并存储视觉-语言模型的标题，而感知风险类别完全由该存储文本的结构化特征推导得出，从而使得每个路段评分对用户保持可检查性。在相同的下游流程下，对五个模型家族的九种标题生成条件与直接的对比语言-图像预训练（CLIP）图像嵌入基线进行了基准测试，发现标题介导的表示达到了与图像嵌入相当的水平，而非落后于它。该方法部署于覆盖英格兰北部两个地点（曼彻斯特和哈德斯菲尔德）36个选区共654,115张图像上。针对70次参与者会话中收集的494张图像的3,669个本地评分进行的独立现场验证，确立了统计显著但适度的协议，r=0.262，而由评分者间分歧所施加的测量噪声上限为0.737。随后的一次性确认测试发现，在监督基准上强44%的流程并未在现场产生可测量的改进（r=0.250，p=0.84），因此在此案例中，基准增益未能预测部署增益。路径选择行为随行程长度系统性地变化。在1公里以下变化可忽略不计，在3至6公里的行程中，低风险路径长度的中位数增加达到12.78%，而中位数绕行距离为2.73%。
英文摘要
This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explicit natural-language intermediate representation. A vision--language model caption is generated and stored before any scoring is undertaken, and the perceived-risk class is derived entirely from structured features of that stored text, so that every segment score remains inspectable by the user. Nine captioning conditions across five model families are benchmarked against a direct Contrastive Language--Image Pre-training (CLIP) image-embedding baseline under an identical downstream pipeline, and the caption-mediated representation is found to reach parity with the image embedding rather than to trail it. The approach was deployed over 654,115 images covering 36 electoral wards in two locations in Northern England (Manchester and Huddersfield). Independent field validation against 3,669 locally collected ratings of 494 images across 70 participant sessions established agreement that is statistically significant but modest, at $r=0.262$, against a measured noise ceiling of 0.737 imposed by disagreement between raters. A single-use confirmatory test then found that a pipeline 44\% stronger on the supervised benchmark did not produce measurable improvement in the field ($r=0.250$, $p=0.84$), so the benchmark gains did not predict the deployment gains in this case. Routing behaviour varies systematically with journey length. There is negligible change below 1\,km, reaching a median increase of 12.78\% in low-risk route length for a median detour of 2.73\% on journeys of 3 to 6 km.
