AgriLiteNet: Lightweight Multi-Scale Tomato Pest and Disease Detection for Agricultural Robots
文献类型： 外文期刊
作者： Yang, Chenghan 1 ; Zhao, Baidong 1 ; Mansurova, Madina 1 ; Zhou, Tianyan 2 ; Liu, Qiyuan 3 ; Bao, Junwei 4 ; Zheng, Dingkun 1 ;
作者机构： 1.Al Farabi Kazakh Natl Univ, Fac Informat Technol, Alma Ata 050040, Kazakhstan
2.Nanjing Univ Aeronaut & Astronaut, Coll Mech & Elect Engn, Nanjing 210001, Peoples R China
3.Xian Jiaotong Liverpool Univ, Sch Robot, Suzhou 215123, Peoples R China
4.Inner Mongolia Acad Agr & Anim Husb Sci, Hohhot 010031, Peoples R China
关键词： tomato; pests and diseases; agricultural robotics; multi-scale detection; lightweight
期刊名称：HORTICULTURAE （ 影响因子：3.0； 五年影响因子：3.2 ）
ISSN：
年卷期： 2025 年 11 卷 6 期
页码：
收录情况： SCI
摘要： Real-time detection of tomato pests and diseases is essential for precision agriculture, as it requires high accuracy, speed, and energy efficiency of edge-computing agricultural robots. This study proposes AgriLiteNet (Lightweight Networks for Agriculture), a lightweight neural network integrating MobileNetV3 for local feature extraction and a streamlined Swin Transformer for global modeling. AgriLiteNet is further enhanced by a lightweight channel-spatial mixed attention module and a feature pyramid network, enabling the detection of nine tomato pests and diseases, including small targets like spider mites, dense targets like bacterial spot, and large targets like late blight. It achieves a mean average precision at an intersection-over-union threshold of 0.5 of 0.98735, which is comparable to Suppression Mask R-CNN (0.98955) and Cas-VSwin Transformer (0.98874), and exceeds the performance of YOLOv5n (0.98249) and GMC-MobileV3 (0.98143). With 2.0 million parameters and 0.608 GFLOPs, AgriLiteNet delivers an inference speed of 35 frames per second and power consumption of 15 watts on NVIDIA Jetson Orin NX, surpassing Suppression Mask R-CNN (8 FPS, 22 W) and Cas-VSwin Transformer (12 FPS, 20 W). The model's efficiency and compact design make it highly suitable for deployment in agricultural robots, supporting sustainable farming through precise pest and disease management.
- 相关文献
作者其他论文 更多>>
-
Temporal segmentation method for 30-meter long-term mapping of abandoned and reclaimed croplands in Inner Mongolia, China
作者：Wuyun, Deji;Sun, Liang;Chen, Ruiqing;Sun, Zheng;Zhao, Hongwei;Chen, Zhongxin;Crusiol, Luis Guilherme Teixeira;Dong, Jinwei;Wu, Nitu;Hasituya;Bao, Junwei
关键词：Abandoned cropland; Agricultural natural zone; Google Earth Engine; Sample adaptive optimization; Agricultural sustainability
-
Impact of vegetation restoration on soil moisture dynamics in temperate water-limited regions
作者：Lan, Lihua;Zhang, Tingting;Zhang, Tingting;Zhang, Tingting;Zhang, Tingting;Lan, Lihua;He, Fei;Lan, Lihua;He, Fei;Wang, Baolin;Bao, Junwei
关键词：Vegetation restoration; NDVI; Climate response; Interactive effect; Soil moisture; PLS-SEM; Restoration phase
-
Intelligent Path Tracking for Single-Track Agricultural Machinery Based on Variable Universe Fuzzy Control and PSO-SVR Steering Compensation
作者：Liu, Huanyu;Han, Zhihang;Luo, Jiahao;Yu, Hao;Wang, Shuang;Liu, Xiangnan;Bao, Junwei
关键词：electric tracked agricultural chassis; single-track braking steering; path tracking; variable universe fuzzy control; support vector regression; particle swarm optimization
-
Nitrogen use efficiencies, flows, and losses of typical dairy farming systems in Inner Mongolia
作者：Qili, Moge;Yang, Fuyu;Qili, Moge;Bao, Junwei;Wu, Nier;Gou, Baomin;Ying, Ying;Bilige, Batu;Sun, Lin;Xue, Yanlin;Zhao, Zhanqing
关键词：dairy farm; nitrogen use efficiency; nitrogen flows; nitrogen losses; nitrogen management
-
Generating Salt-Affected Irrigated Cropland Map in an Arid and Semi-Arid Region Using Multi-Sensor Remote Sensing Data
作者：Wuyun, Deji;Bao, Junwei;Wulan, Tuya;Xin, Qingqiang;Hou, Anhong;Ren, Tingting;Wuyun, Deji;Sun, Liang;Wu, Shangrong;Sun, Zheng;Chen, Ruiqing;Crusiol, Luis Guilherme Teixeira;Peng, Jingyu;Xu, Hongtao;Wu, Nitu;Wu, Lan;Ren, Tingting
关键词：irrigation district; cropland; quantile and quantile plots testing; dry season; Google Earth Engine
