• Home
  • Search
  • Attention-based digital filter with anchor-free feature pyramid learning model for pedestrian detection
  • https://doi.org/10.3233/jifs-237639Copy DOI Icon

Attention-based digital filter with anchor-free feature pyramid learning model for pedestrian detection

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Ensuring real-time performance while leveraging pedestrian detection is a crucial prerequisite for intelligent driving technology. The development of lightweight models with good detection accuracy is also crucial. This work proposes a novel method, the Attention Digital Filter with Anchor-Free Feature Pyramid Learning Model (ADFAFPLM), to meet these needs. The suggested method consists of combining two networks: one is a digital filter based on an attention network that eliminates noise and other picture distortions. The attention-based residual network digital filters are chosen for their enhanced filtering performance, adaptability, efficient learning through residual connections, noise suppression, interpretability, and generalization capabilities. Next, from the input crowded and occluded photos, the pedestrian is identified using an anchor-free feature pyramid network. The Eurocity person dataset was used to train the model, and it was also tested on other datasets like CityPersons, INRIA, PennFudan, and Eurocity. The investigation was expanded to include images in hazy, noisy, and occlusion environments, among other environmental conditions. The image resolutions were also considered for analysis and it was observed that with increasing image resolution, the mAP increases. Based on the ablation study, the ADF-AFPLM adopted YOLOv8n with batch size 16, and image size 640 is considered for efficient result with different testing datasets. The model achieved a mean average precision (mAP) of approx. 87% and shows its efficacy over state-of-art models.

Similar Papers
  • Book Chapter

Hybrid Active and Passive Control of a Server Room Noise: A Comparative Study of Results Obtained by Using Different Algorithms

  • Dec 24, 2014
  • Sudarsan Sahoo +1
  • Conference Article
  • Citations15

Determination of glucose concentration from near-infrared spectra using principle component regression coupled with digital bandpass filter

  • Oct 01, 2010
  • Amneh A Al-Mbaideen +2
  • Research Article

Temporal imaging based on first-order field correlation

  • Jan 01, 2019
  • Acta Physica Sinica
  • Rui-Xue Zhang +2
  • Research Article
  • Citations35

High-resolution microseismic imaging

  • Oct 01, 2017
  • The Leading Edge
  • Vladimir Grechka +4
  • Research Article
  • Citations2

Research on Long-Term Structural Response Time-Series Prediction Method Based on the Informer-SEnet Model

  • Jan 01, 2026
  • Buildings
  • Yufeng Xu +2
  • Research Article

Physiological Measures of Reduced Listening Effort in Active Noise Canceling: Evidence from Low-β Functional Network in an Event-Related Potential Study.

  • Jan 29, 2026
  • Clinical and experimental otorhinolaryngology
  • Jihoo Kim +4
  • Research Article
  • Citations8

Deep learning powered single-cell clustering framework with enhanced accuracy and stability

  • Feb 03, 2025
  • Scientific Reports
  • Yi Zhang +3
  • Research Article
  • Citations4

Investigation of the Operation of the Extended Kalman Filter Supplemented by an Adaptive Digital Filter for Integrating Data from a Mobile Robot Control System

  • Jun 23, 2020
  • Proceedings of the Southwest State University
  • P A Bezmen
  • PDF
  • Research Article
  • Citations7

Structured low-rank reconstruction for navigator-free water/fat separated multi-shot diffusion-weighted EPI.

  • Sep 27, 2023
  • Magnetic Resonance in Medicine
  • Yiming Dong +5
  • Research Article
  • Citations3

Enhancing obSTORM imaging performance with cubic spline PSF modeling.

  • Sep 07, 2023
  • Biomedical Optics Express
  • Donghoon Koo +3
  • Research Article
  • Citations60

Transfer learning for pedestrian detection

  • May 28, 2012
  • Neurocomputing
  • Xianbin Cao +3
  • Conference Article
  • Citations2

Augmenting Information Channels in Hearing Aids and Cochlear Implants Under Adverse Conditions

  • May 14, 2006
  • Y Suhail +1
  • Research Article
  • Citations1

Active noise control in a tractor cabin: implementation challenges and experimental testing in driving conditions

  • Jan 01, 2026
  • Applied Acoustics
  • Francesco Mori +7
  • PDF
  • Research Article
  • Citations114

Boosting magnetic resonance imaging signal-to-noise ratio using magnetic metamaterials

  • Mar 26, 2019
  • Communications Physics
  • Guangwu Duan +3
  • Conference Article
  • Citations1

Application of Deep Learning Methods for Pedestrian Collision Detection Using Dashcam Videos

  • Apr 02, 2021
  • SAE technical papers on CD-ROM/SAE technical paper series
  • Shouhei Kunitomi +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.