Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 36 min ago
Peer-reviewedCC BY 4.0Frontiers in Plant Science

Citrus leaf disease detection via multi-scale directional features and adaptive cross-scale modulation

  1. 1College of Information Technology, Nanchang Vocational University
  2. 2School of Electronic and Information Engineering, Lanzhou Jiaotong University

Abstract

To address the challenges of small lesion scales, overlapping leaf occlusion, and complex background interference in citrus leaf disease detection, this study proposes MSAF-DETR, a detection method specifically designed for citrus leaf diseases. First, an MSGC-C2f-ResNet18 backbone is developed for feature extraction. By embedding a multi-scale directional feature scanning module into the C2f stages of C2f-ResNet18, horizontal, vertical, and diagonal scanning mechanisms are employed to strengthen the representation of small lesions and disease regions affected by occlusion. Subsequently, a lightweight global context modeling module, termed SDTA, is introduced. It combines depthwise convolution with cross-channel transposed self-attention to enhance disease-related responses while suppressing irrelevant background interference. In addition, an Adaptive Cross-Scale Modulation (ACSM) fusion module is constructed to achieve effective alignment and integration of shallow spatial details with deep semantic features through dynamic local relation refinement and cascaded dilated convolution. Finally, the Focal-DIoU loss is introduced to reduce localization errors during bounding-box regression. Experimental results on the public CLS dataset and the self-constructed JXCL citrus leaf disease dataset show that MSAF-DETR achieves mAP values of 88.74% and 99.23%, respectively, representing improvements of 6.94% and 3.52% over the baseline RT-DETR model. The proposed method also maintains high detection accuracy and robustness under challenging orchard conditions, including uneven illumination, branch and leaf occlusion, and small-scale disease lesions, providing an efficient and reliable solution for the visual perception systems of citrus-picking robots.

Related

  1. AGC-YOLO: adaptive gated channel network for rice leaf disease detection
    Fei Wang, Yuan Lv, Li Zhao +5
    Frontiers in Plant SciencePeer-reviewedCC BY 4.0Full textPlant biologyCrossrefEurope PMCEurope PMCPMC
  2. Wildlife disease surveillance under uncertainty: an adaptive search-theoretic framework for early detection of transboundary animal diseases
    A. J. Bengsen, S. Comte, L. K. Parker +4
    bioRxivPreprintCC BY-NC-NDFull textZoology & animal behaviourbioRxiv
  3. Adaptive gating-based fusion of sequential and local features for predicting drug-drug interactions
    Guolongwei Dai, Tao Luo, Tao Lin +3
    iSciencePeer-reviewedCC BY-NC 4.0Bioinformatics & computational biologyCell PressCrossref
  4. Adaptive modulation of theta sweeps in the brain’s navigation circuit
    Abraham Z. Vollan, Michael F. Schellenberger, Richard J. Gardner +2
    SciencePeer-reviewedCC BY19 citedNeuroscienceOpenAlex
  5. Characterizing fatigue-related neural signatures via multi-band EEG features and a three-stage feature optimization strategy for driver fatigue detection
    Jichi Chen, Guangxiang Yuan, Chunfeng Wei
    Measurement Science and TechnologyPeer-reviewedLicence not statedFull text8 citedNeuroscienceOpenAlex
BibTeX
@article{lu2026citrus,
  title = {{Citrus leaf disease detection via multi-scale directional features and adaptive cross-scale modulation}},
  author = {Feifei Lu and Baijing Wu and Ke Gao and Guanghui Yan},
  journal = {Frontiers in Plant Science},
  year = {2026},
  month = nov,
  doi = {10.3389/fpls.2026.1987151},
  url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1987151/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Citrus leaf disease detection via multi-scale directional features and adaptive cross-scale modulation
AU  - Feifei Lu
AU  - Baijing Wu
AU  - Ke Gao
AU  - Guanghui Yan
PY  - 2026
DA  - 2026/11/16
JO  - Frontiers in Plant Science
DO  - 10.3389/fpls.2026.1987151
UR  - https://www.frontiersin.org/articles/10.3389/fpls.2026.1987151/full
AB  - To address the challenges of small lesion scales, overlapping leaf occlusion, and complex background interference in citrus leaf disease detection, this study proposes MSAF-DETR, a detection method specifically designed for citrus leaf diseases. First, an MSGC-C2f-ResNet18 backbone is developed for feature extraction. By embedding a multi-scale directional feature scanning module into the C2f stages of C2f-ResNet18, horizontal, vertical, and diagonal scanning mechanisms are employed to strengthen the representation of small lesions and disease regions affected by occlusion. Subsequently, a lightweight global context modeling module, termed SDTA, is introduced. It combines depthwise convolution with cross-channel transposed self-attention to enhance disease-related responses while suppressing irrelevant background interference. In addition, an Adaptive Cross-Scale Modulation (ACSM) fusion module is constructed to achieve effective alignment and integration of shallow spatial details with deep semantic features through dynamic local relation refinement and cascaded dilated convolution. Finally, the Focal-DIoU loss is introduced to reduce localization errors during bounding-box regression. Experimental results on the public CLS dataset and the self-constructed JXCL citrus leaf disease dataset show that MSAF-DETR achieves mAP values of 88.74% and 99.23%, respectively, representing improvements of 6.94% and 3.52% over the baseline RT-DETR model. The proposed method also maintains high detection accuracy and robustness under challenging orchard conditions, including uneven illumination, branch and leaf occlusion, and small-scale disease lesions, providing an efficient and reliable solution for the visual perception systems of citrus-picking robots.
SN  - 1664-462X
ER  -