Two-dimensional spatial orientation relation recognition between image objects

Recent advances in computer vision have concentrated on comprehension of the semantic features of images, particularly the spatial relations between objects—a fundamental semantic feature of visual scene understanding. This study systematically addresses the recognition problem of two-dimensional sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Gong Peiyong, Zheng Kai, Jiang Yi, Zhao Huixuan, Huai Honghao, Guan Ruijie
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Engineering Science and Technology, an International Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2215098625001296
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849326237938352128
author Gong Peiyong
Zheng Kai
Jiang Yi
Zhao Huixuan
Huai Honghao
Guan Ruijie
author_facet Gong Peiyong
Zheng Kai
Jiang Yi
Zhao Huixuan
Huai Honghao
Guan Ruijie
author_sort Gong Peiyong
collection DOAJ
description Recent advances in computer vision have concentrated on comprehension of the semantic features of images, particularly the spatial relations between objects—a fundamental semantic feature of visual scene understanding. This study systematically addresses the recognition problem of two-dimensional spatial orientation relations and develops the Target Spatial Orientation Vector Field (TSOVF) algorithm, a novel end-to-end framework to explicitly model spatial orientation dependencies. TSOVF algorithm introduces the learnable spatial orientation vector field to effectively encode the spatial orientation relation into a deep convolutional neural network model. The proposed architecture features a dual-branch design: the T-branch identifies object central points and classifies categories via keypoint estimation, while the S-branch constructs a pixel-level spatial orientation vector field. Each vector in this field quantifies the angular orientation between object pairs, with aggregated vector data determining the final spatial relation category. A dedicated fusion module synthesizes features from both branches, generating a structured triple list that documents detected objects, their inter-object spatial orientations, and associated confidence scores. Evaluated on a PASCAL VOC2012-derived dataset, TSOVF algorithm achieves 94.8 % global accuracy and a class-balanced geometric mean (G-mean) of 0.798, demonstrating robust performance across various spatial configurations. For dominant orientation categories, the algorithm attains up to 95.9 % precision and 94.7 % F1-score, establishing it as a foundational benchmark for spatial relation recognition. These results validate TSOVF’s capacity to advance fine-grained visual relationship detection while providing a reproducible framework for future research in spatial-semantic analysis.
format Article
id doaj-art-bdb795518ade4a7ead3886bcc1add38a
institution Kabale University
issn 2215-0986
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Engineering Science and Technology, an International Journal
spelling doaj-art-bdb795518ade4a7ead3886bcc1add38a2025-08-20T03:48:11ZengElsevierEngineering Science and Technology, an International Journal2215-09862025-07-016710207410.1016/j.jestch.2025.102074Two-dimensional spatial orientation relation recognition between image objectsGong Peiyong0Zheng Kai1Jiang Yi2Zhao Huixuan3Huai Honghao4Guan Ruijie5Dalian Maritime University, Marine Electrical Engineering College, Dalian 116026, ChinaDalian Maritime University, Marine Electrical Engineering College, Dalian 116026, China; Corresponding author.Dalian Maritime University, Science and Technology College, Dalian 116026, ChinaDalian Maritime University, Marine Electrical Engineering College, Dalian 116026, ChinaDalian Maritime University, Marine Electrical Engineering College, Dalian 116026, ChinaDalian Maritime University, Marine Electrical Engineering College, Dalian 116026, ChinaRecent advances in computer vision have concentrated on comprehension of the semantic features of images, particularly the spatial relations between objects—a fundamental semantic feature of visual scene understanding. This study systematically addresses the recognition problem of two-dimensional spatial orientation relations and develops the Target Spatial Orientation Vector Field (TSOVF) algorithm, a novel end-to-end framework to explicitly model spatial orientation dependencies. TSOVF algorithm introduces the learnable spatial orientation vector field to effectively encode the spatial orientation relation into a deep convolutional neural network model. The proposed architecture features a dual-branch design: the T-branch identifies object central points and classifies categories via keypoint estimation, while the S-branch constructs a pixel-level spatial orientation vector field. Each vector in this field quantifies the angular orientation between object pairs, with aggregated vector data determining the final spatial relation category. A dedicated fusion module synthesizes features from both branches, generating a structured triple list that documents detected objects, their inter-object spatial orientations, and associated confidence scores. Evaluated on a PASCAL VOC2012-derived dataset, TSOVF algorithm achieves 94.8 % global accuracy and a class-balanced geometric mean (G-mean) of 0.798, demonstrating robust performance across various spatial configurations. For dominant orientation categories, the algorithm attains up to 95.9 % precision and 94.7 % F1-score, establishing it as a foundational benchmark for spatial relation recognition. These results validate TSOVF’s capacity to advance fine-grained visual relationship detection while providing a reproducible framework for future research in spatial-semantic analysis.http://www.sciencedirect.com/science/article/pii/S2215098625001296Target spatial orientation vector fieldSpatial Orientation RelationRecognition
spellingShingle Gong Peiyong
Zheng Kai
Jiang Yi
Zhao Huixuan
Huai Honghao
Guan Ruijie
Two-dimensional spatial orientation relation recognition between image objects
Engineering Science and Technology, an International Journal
Target spatial orientation vector field
Spatial Orientation Relation
Recognition
title Two-dimensional spatial orientation relation recognition between image objects
title_full Two-dimensional spatial orientation relation recognition between image objects
title_fullStr Two-dimensional spatial orientation relation recognition between image objects
title_full_unstemmed Two-dimensional spatial orientation relation recognition between image objects
title_short Two-dimensional spatial orientation relation recognition between image objects
title_sort two dimensional spatial orientation relation recognition between image objects
topic Target spatial orientation vector field
Spatial Orientation Relation
Recognition
url http://www.sciencedirect.com/science/article/pii/S2215098625001296
work_keys_str_mv AT gongpeiyong twodimensionalspatialorientationrelationrecognitionbetweenimageobjects
AT zhengkai twodimensionalspatialorientationrelationrecognitionbetweenimageobjects
AT jiangyi twodimensionalspatialorientationrelationrecognitionbetweenimageobjects
AT zhaohuixuan twodimensionalspatialorientationrelationrecognitionbetweenimageobjects
AT huaihonghao twodimensionalspatialorientationrelationrecognitionbetweenimageobjects
AT guanruijie twodimensionalspatialorientationrelationrecognitionbetweenimageobjects