Akses terbuka
Jurnal
Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception
Journal of Electrical and Intelligent Systems
ISSN 3163-7663
Terbit 2026-05-20
Penerbit Politeknik Elektronika Negeri Surabaya
Bahasa eng
Abstrak
Conventional object detection systems in Intelligent Transportation Systems (ITS) commonly operate in a frame-wise manner, leading to temporally inconsistent predictions under dynamic conditions. This paper proposes a motion-consistent object detection framework that integrates velocity-constrained filtering to enforce physical plausibility across consecutive frames. The main contribution of this work lies in explicitly formulating detection validation as a deterministic velocity-bounded constraint problem, enabling direct integration of motion dynamics into the perception pipeline rather than treating motion as auxiliary information. The system employs a lightweight YOLO11s-based detector for visual perception and GPS-based motion estimation to provide real-world velocity constraints. Experiments are conducted on a traffic infrastructure dataset comprising 52,135 images across 33 classes and evaluated on an Intel NUC 13 Pro edge computing platform. Results demonstrate that the proposed method improves temporal stability compared to conventional frame-wise detection while maintaining strong detection performance, achieving an mAP@0.5 of 0.945 at 20 FPS. The findings indicate that incorporating explicit motion constraints enhances detection reliability without introducing significant computational overhead. However, performance may degrade under low-speed GPS noise and challenging visual conditions such as occlusion, highlighting limitations for future improvement.
Jaringan kolaborasi para penulis
5 penulis ·
6 tautan kepenulisan bersama
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.
Sumber metadata: OAI-PMH (metadata jurnal) https://journals.pens.ac.id/index.php/jeis/oai, pertama di-harvest 6 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title xml:lang="en">Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception</dc:title>
<dc:creator xml:lang="en">Anugrah, Gusty</dc:creator>
<dc:creator xml:lang="en">Happyanto, Dedid Cahya</dc:creator>
<dc:creator xml:lang="en">Puspita, Eru</dc:creator>
<dc:subject xml:lang="en">Object detection</dc:subject>
<dc:subject xml:lang="en">motion consistency</dc:subject>
<dc:subject xml:lang="en">velocity-constrained filtering</dc:subject>
<dc:subject xml:lang="en">intelligent transportation systems</dc:subject>
<dc:subject xml:lang="en">GPS-based velocity estimation</dc:subject>
<dc:subject xml:lang="en">temporal stability</dc:subject>
<dc:description xml:lang="en">Conventional object detection systems in Intelligent Transportation Systems (ITS) commonly operate in a frame-wise manner, leading to temporally inconsistent predictions under dynamic conditions. This paper proposes a motion-consistent object detection framework that integrates velocity-constrained filtering to enforce physical plausibility across consecutive frames. The main contribution of this work lies in explicitly formulating detection validation as a deterministic velocity-bounded constraint problem, enabling direct integration of motion dynamics into the perception pipeline rather than treating motion as auxiliary information. The system employs a lightweight YOLO11s-based detector for visual perception and GPS-based motion estimation to provide real-world velocity constraints. Experiments are conducted on a traffic infrastructure dataset comprising 52,135 images across 33 classes and evaluated on an Intel NUC 13 Pro edge computing platform. Results demonstrate that the proposed method improves temporal stability compared to conventional frame-wise detection while maintaining strong detection performance, achieving an mAP@0.5 of 0.945 at 20 FPS. The findings indicate that incorporating explicit motion constraints enhances detection reliability without introducing significant computational overhead. However, performance may degrade under low-speed GPS noise and challenging visual conditions such as occlusion, highlighting limitations for future improvement.</dc:description>
<dc:publisher xml:lang="en">Politeknik Elektronika Negeri Surabaya</dc:publisher>
<dc:date>2026-05-20</dc:date>
<dc:type>info:eu-repo/semantics/article</dc:type>
<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
<dc:format>application/pdf</dc:format>
<dc:identifier>https://journals.pens.ac.id/jeis/article/view/59</dc:identifier>
<dc:identifier>10.68129/jeis.v1i1.5</dc:identifier>
<dc:source xml:lang="en">Journal of Electrical and Intelligent Systems; Vol. 1 No. 1 (2026): April; 33-41</dc:source>
<dc:source>3163-7663</dc:source>
<dc:language>eng</dc:language>
<dc:relation>https://journals.pens.ac.id/jeis/article/view/59/29</dc:relation>
<dc:rights xml:lang="en">Copyright (c) 2026 Gusty Anugrah, Dedid Cahya Happyanto, Eru Puspita (Author)</dc:rights>
<dc:rights xml:lang="en">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>
Sitasi dan pengindeksan
Jumlah menurut tiap indeks pada 13 Nov 2026; setiap indeks menghitung sitasi dengan cara berbeda.
OpenAlex juga mencatat karya ini di: crossref.
Sitasi artikel ini
APA 7
Anugrah, G., Happyanto, D. C., & Puspita, E. (2026). Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception. Journal of Electrical and Intelligent Systems, 1(1), 33–41. https://doi.org/10.68129/jeis.v1i1.5
Salin
IEEE
G. Anugrah, D. C. Happyanto, and E. Puspita, “Motion Consistent Object Detection: A Velocity Constrained Filtering Framework for Traffic Perception,” Journal of Electrical and Intelligent Systems, vol. 1, no. 1, pp. 33–41, 2026, doi: 10.68129/jeis.v1i1.5.
Salin
Dibuat dari metadata jurnal; periksa nama penulis sebelum dipakai.