发表机构
Jilin University; Shenzhen University; Taiyuan University of Technology; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education（吉林大学; 深圳大学; 太原理工大学; 符号计算与知识工程教育部重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出DensePed-Lite轻量级框架，通过质量感知的自适应机制应对遮挡下密集行人检测，在CityPersons和CrowdHuman上实现更优的精度-效率权衡。
AI 中文摘要
行人检测在计算机视觉中扮演着关键角色，应用于自动驾驶、监控和公共安全等领域。然而，现实世界中的密集场景带来了严峻挑战，包括严重遮挡、剧烈的尺度变化以及严格的实时性要求。现有的轻量级检测器难以在准确性和效率之间取得平衡，且常常忽视质量感知特征建模以及分类与定位之间的一致性，导致在拥挤条件下的性能不稳定。为解决这些问题，我们提出了DensePed-Lite，一个基于单一原则构建的统一框架：在遮挡情况下，网络应适应其观察内容的质量，而非假设信息完整。该原则在遮挡造成最大损害的三个点上得以实现：不可靠的置信度评分（UQE）、碎片化的空间覆盖（MPSC）以及不连贯的多尺度融合（CTDM）。这三种机制相互增强而非孤立作用，且均未显著增加复杂度。在CityPersons和CrowdHuman上的实验验证了DensePed-Lite相较于近期最先进的轻量级方法实现了更优的精度-效率权衡，使其适用于密集行人场景中的实时部署。
英文摘要
Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweight detectors struggle to balance accuracy and efficiency while often neglecting quality-aware feature modeling and consistency between classification and localization, leading to unstable performance under crowded conditions. To address these issues, we propose DensePed-Lite, a unified framework built on a single principle: under occlusion the network should adapt its behavior to the quality of what it observes rather than assume complete information. This principle is realized at three points where occlusion does the most damage: unreliable confidence scoring (UQE), fragmented spatial coverage (MPSC), and incoherent multi-scale fusion (CTDM). The three mechanisms reinforce one another instead of acting in isolation, all without significantly increasing complexity. Experiments on CityPersons and CrowdHuman validate that DensePed-Lite achieves a superior accuracy-efficiency trade-off compared with recent state-of-the-art lightweight methods, making it suitable for real-time deployment in dense pedestrian scenarios.
CommentsAccepted at WISE 2026
