Academic Journal
MI-ACVNet: A Lightweight Stereo Matching Network for High-Precision Single-View 3D Reconstruction of Kirin Watermelons.
| Τίτλος: | MI-ACVNet: A Lightweight Stereo Matching Network for High-Precision Single-View 3D Reconstruction of Kirin Watermelons. |
|---|---|
| Συγγραφείς: | Li, Zetong, Xu, Xufeng, Gao, Yuan, Lei, Wenqian, Rao, Xiuqin |
| Πηγή: | Agriculture; Basel; Jul2026, Vol. 16 Issue 13, p1475, 21p |
| Θεματικοί όροι: | Three-dimensional imaging, Point cloud, Artificial neural networks, Feature extraction, Depth maps (Digital image processing), Real-time computing |
| Περίληψη: | Three-dimensional surface reconstruction is essential for accurately acquiring the external quality parameters of watermelons, such as size, volume, and defect area. Binocular stereo vision provides a low-cost and easily deployable solution for the single-view 3D reconstruction of watermelons. However, watermelons present highly similar surface textures, and as typical spheroid-like objects, the excessive angle between surface normals of edge regions and the camera optical axis leads to insufficient feature representation. Consequently, directly applying existing stereo matching algorithms often introduces matching ambiguities, and lightweight networks struggle to balance real-time performance with matching accuracy. This study focuses on the high-precision single-view point cloud generation of Kirin watermelons. To address these issues, we first construct a cross-modal, high-precision Kirin watermelon stereo matching dataset. Building upon the Fast-ACVNet+ architecture, we then propose MI-ACVNet, a lightweight stereo matching network tailored for high-precision watermelon point cloud acquisition. In the feature extraction stage, a Multi-Scale Stereo Feature Extraction (MSFE) module is adapted. By incorporating the re-parameterized network MobileOne and Epipolar-Enhanced Coordinate Attention (E2CA), MSFE improves the discriminative capability for weak and similar textures without compromising inference speed. For cost computation, a Coarse-to-Fine Cascaded Residual Correction (C2F-CRC) strategy is incorporated to construct a fine-grained cost volume via sub-pixel interpolation, enhancing the network's ability to capture subtle surface fluctuations. Furthermore, a Semantics-Guided Region-Aware Loss (SGRA-Loss) is formulated, leveraging semantic masks to apply differentiated supervision weights across edge, center, and background regions to significantly improve edge matching accuracy. Ablation studies validate the effectiveness of the MSFE, C2F-CRC, and SGRA-Loss components. Compared to the baseline model, the full MI-ACVNet reduces the End-Point Error (EPE) by 19.5% and the Bad-0.5 error rate by 34.5% in the watermelon region. Furthermore, when compared against five mainstream algorithms (StereoNet, AANet, HSMNet, LightStereo-L, and NMRF-swint), MI-ACVNet achieves state-of-the-art performance: EPE and Bad-0.5 are reduced to 0.091 pixels and 1.159%, respectively, with a single-frame inference time of only 46 ms. The average depth error of the reconstructed point clouds is merely 0.26 mm. By ensuring both real-time efficiency and high-precision depth estimation, this method demonstrates promising potential for deployment in industrial Kirin watermelon sorting lines, driving sorting equipment toward higher precision and intelligence. [ABSTRACT FROM AUTHOR] |
| Copyright of Agriculture; Basel is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=20770472&ISBN=&volume=16&issue=13&date=20260701&spage=1475&pages=1475-1495&title=Agriculture; Basel&atitle=MI-ACVNet%3A%20A%20Lightweight%20Stereo%20Matching%20Network%20for%20High-Precision%20Single-View%203D%20Reconstruction%20of%20Kirin%20Watermelons.&aulast=Li%2C%20Zetong&id=DOI:10.3390/agriculture16131475 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 195442603 RelevancyScore: 1082 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1082.42175292969 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: MI-ACVNet: A Lightweight Stereo Matching Network for High-Precision Single-View 3D Reconstruction of Kirin Watermelons. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Li%2C+Zetong%22">Li, Zetong</searchLink><br /><searchLink fieldCode="AR" term="%22Xu%2C+Xufeng%22">Xu, Xufeng</searchLink><br /><searchLink fieldCode="AR" term="%22Gao%2C+Yuan%22">Gao, Yuan</searchLink><br /><searchLink fieldCode="AR" term="%22Lei%2C+Wenqian%22">Lei, Wenqian</searchLink><br /><searchLink fieldCode="AR" term="%22Rao%2C+Xiuqin%22">Rao, Xiuqin</searchLink> – Name: TitleSource Label: Source Group: Src Data: Agriculture; Basel; Jul2026, Vol. 16 Issue 13, p1475, 21p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Depth+maps+%28Digital+image+processing%29%22">Depth maps (Digital image processing)</searchLink><br /><searchLink fieldCode="DE" term="%22Real-time+computing%22">Real-time computing</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Three-dimensional surface reconstruction is essential for accurately acquiring the external quality parameters of watermelons, such as size, volume, and defect area. Binocular stereo vision provides a low-cost and easily deployable solution for the single-view 3D reconstruction of watermelons. However, watermelons present highly similar surface textures, and as typical spheroid-like objects, the excessive angle between surface normals of edge regions and the camera optical axis leads to insufficient feature representation. Consequently, directly applying existing stereo matching algorithms often introduces matching ambiguities, and lightweight networks struggle to balance real-time performance with matching accuracy. This study focuses on the high-precision single-view point cloud generation of Kirin watermelons. To address these issues, we first construct a cross-modal, high-precision Kirin watermelon stereo matching dataset. Building upon the Fast-ACVNet+ architecture, we then propose MI-ACVNet, a lightweight stereo matching network tailored for high-precision watermelon point cloud acquisition. In the feature extraction stage, a Multi-Scale Stereo Feature Extraction (MSFE) module is adapted. By incorporating the re-parameterized network MobileOne and Epipolar-Enhanced Coordinate Attention (E2CA), MSFE improves the discriminative capability for weak and similar textures without compromising inference speed. For cost computation, a Coarse-to-Fine Cascaded Residual Correction (C2F-CRC) strategy is incorporated to construct a fine-grained cost volume via sub-pixel interpolation, enhancing the network's ability to capture subtle surface fluctuations. Furthermore, a Semantics-Guided Region-Aware Loss (SGRA-Loss) is formulated, leveraging semantic masks to apply differentiated supervision weights across edge, center, and background regions to significantly improve edge matching accuracy. Ablation studies validate the effectiveness of the MSFE, C2F-CRC, and SGRA-Loss components. Compared to the baseline model, the full MI-ACVNet reduces the End-Point Error (EPE) by 19.5% and the Bad-0.5 error rate by 34.5% in the watermelon region. Furthermore, when compared against five mainstream algorithms (StereoNet, AANet, HSMNet, LightStereo-L, and NMRF-swint), MI-ACVNet achieves state-of-the-art performance: EPE and Bad-0.5 are reduced to 0.091 pixels and 1.159%, respectively, with a single-frame inference time of only 46 ms. The average depth error of the reconstructed point clouds is merely 0.26 mm. By ensuring both real-time efficiency and high-precision depth estimation, this method demonstrates promising potential for deployment in industrial Kirin watermelon sorting lines, driving sorting equipment toward higher precision and intelligence. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Agriculture; Basel is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=195442603 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/agriculture16131475 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 1475 Subjects: – SubjectFull: Three-dimensional imaging Type: general – SubjectFull: Point cloud Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Depth maps (Digital image processing) Type: general – SubjectFull: Real-time computing Type: general Titles: – TitleFull: MI-ACVNet: A Lightweight Stereo Matching Network for High-Precision Single-View 3D Reconstruction of Kirin Watermelons. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Li, Zetong – PersonEntity: Name: NameFull: Xu, Xufeng – PersonEntity: Name: NameFull: Gao, Yuan – PersonEntity: Name: NameFull: Lei, Wenqian – PersonEntity: Name: NameFull: Rao, Xiuqin IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 07 Text: Jul2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20770472 Numbering: – Type: volume Value: 16 – Type: issue Value: 13 Titles: – TitleFull: Agriculture; Basel Type: main |
| ResultId | 1 |