HS-BiFPN.

<div><p>Sewer pipeline defect detection is a critical task for ensuring the normal operation of urban infrastructure. However, the sewer environment often presents challenges such as multi-scale defects, complex backgrounds, lighting changes, and diverse defect morphologies. To address t...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Ruibo Sha (22103978) (author)
مؤلفون آخرون:	Zhifeng Zhang (444741) (author), Xiao Cui (590113) (author), Qingzheng Mu (22103981) (author)
منشور في:	2025
الموضوعات:	Biochemistry Cell Biology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified layer semantic fusion experimental results show improving detection accuracy diverse defect morphologies 35 %, floating model demonstrates potential model &# 8217 improved model achieves achieving model lightweighting distinguish complex backgrounds defect detection complex backgrounds 21 %, yolov8n model model size complex environments zw ), weighting mechanisms urban infrastructure typical defects study uses scale defects point operations paper proposes original structure normal operation lightweight cross lighting changes leveraging cross fam module data augmentation critical task capture details bifpn module backbone network 952 images 33 %.
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

HS-BiFPN.

مواد مشابهة