Real-time and accurate detection of citrus in complex scenes based on HPL-YOLOv4

Xu, Lijia; Wang, Yihan; Shi, Xiaoshi; Tang, Zuoliang; Chen, Xinyuan; Wang, Yuchao; Zou, Zhiyong; Huang, Peng; Bi, Liu; Yang, Ning; Lü, Zhiwei; He, Yong; Zhao, Yongpeng

doi:10.1016/j.compag.2022.107590

Cited by 32 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This article uses GhostNet (Xu et al, 2023) to replace the backbone network of YOLOX, which not only stabilizes the average accuracy but also greatly reduces the number of network parameters. 7, the inference speed of ASFL-YOLOX is 3.5 times that of the Faster R-CNN series models, indicating that the Faster R-CNN series models have greater limitations in terms of inference speed, and ASFL-YOLOX has obvious advantages.…”

Section: Discussionmentioning

confidence: 99%

ASFL-YOLOX: an adaptive spatial feature fusion and lightweight detection method for insect pests of the Papilionidae family

Xu,

Shi,

Tang

et al. 2023

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

IntroductionInsect pests from the family Papilionidae (IPPs) are a seasonal threat to citrus orchards, causing damage to young leaves, affecting canopy formation and fruiting. Existing pest detection models used by orchard plant protection equipment lack a balance between inference speed and accuracy.MethodsTo address this issue, we propose an adaptive spatial feature fusion and lightweight detection model for IPPs, called ASFL-YOLOX. Our model includes several optimizations, such as the use of the Tanh-Softplus activation function, integration of the efficient channel attention mechanism, adoption of the adaptive spatial feature fusion module, and implementation of the soft Dlou non-maximum suppression algorithm. We also propose a structured pruning curation technique to eliminate unnecessary connections and network parameters.ResultsExperimental results demonstrate that ASFL-YOLOX outperforms previous models in terms of inference speed and accuracy. Our model shows an increase in inference speed by 29 FPS compared to YOLOv7-x, a higher mAP of approximately 10% than YOLOv7-tiny, and a faster inference frame rate on embedded platforms compared to SSD300 and Faster R-CNN. We compressed the model parameters of ASFL-YOLOX by 88.97%, reducing the number of floating point operations per second from 141.90G to 30.87G while achieving an mAP higher than 95%.DiscussionOur model can accurately and quickly detect fruit tree pest stress in unstructured orchards and is suitable for transplantation to embedded systems. This can provide technical support for pest identification and localization systems for orchard plant protection equipment.

show abstract

Section: Discussionmentioning

confidence: 99%

ASFL-YOLOX: an adaptive spatial feature fusion and lightweight detection method for insect pests of the Papilionidae family

Xu,

Shi,

Tang

et al. 2023

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…These vectors undergo processing through a Sigmoid activation function and are multiplied channel-by-channel with the input feature map, yielding a weighted feature map. The weighted feature map is then scaled and panned to generate the final feature map [21]. The specific structure of the ECANet module is depicted in Figure 5.…”

Section: Feature Fusion Network Of Channel Attention Mechanismmentioning

confidence: 99%

Detection and Localization of Tea Bud Based on Improved YOLOv5s and 3D Point Cloud Processing

Zhu,

Zhang,

Lin

et al. 2023

Agronomy

View full text Add to dashboard Cite

Currently, the detection and localization of tea buds within the unstructured tea plantation environment are greatly challenged due to their small size, significant morphological and growth height variations, and dense spatial distribution. To solve this problem, this study applies an enhanced version of the YOLOv5 algorithm for tea bud detection in a wide field of view. Also, small-size tea bud localization based on 3D point cloud technology is used to facilitate the detection of tea buds and the identification of picking points for a renowned tea-picking robot. To enhance the YOLOv5 network, the Efficient Channel Attention Network (ECANet) module and Bi-directional Feature Pyramid Network (BiFPN) are incorporated. After acquiring the 3D point cloud for the region of interest in the detection results, the 3D point cloud of the tea bud is extracted using the DBSCAN clustering algorithm to determine the 3D coordinates of the tea bud picking points. Principal component analysis is then utilized to fit the minimum outer cuboid to the 3D point cloud of tea buds, thereby solving for the 3D coordinates of the picking points. To evaluate the effectiveness of the proposed algorithm, an experiment is conducted using a collected tea image test set, resulting in a detection precision of 94.4% and a recall rate of 90.38%. Additionally, a field experiment is conducted in a tea experimental field to assess localization accuracy, with mean absolute errors of 3.159 mm, 6.918 mm, and 7.185 mm observed in the x, y, and z directions, respectively. The average time consumed for detection and localization is 0.129 s, which fulfills the requirements of well-known tea plucking robots in outdoor tea gardens for quick identification and exact placement of small-sized tea shoots with a wide field of view.

show abstract

“…In contrast, with the advancement of deep learning research, visible light-based method, which can use readily available commercial even consumer-class cameras, offering competitive cost advantage. Thanks to the rapid development of deep learning, visible light-based method has shown comparable or even better results on HLB detection task [6,7,[16][17][18] . Furthermore, research and experiments have been conducted to apply AI techniques and robotic platforms, such as Unmanned Aerial Vehicle (UAV), for orchard monitoring and detecting HLB in the field [19][20][21][22][23][24] .…”

Section: Introductionmentioning

confidence: 99%

Towards Huanglongbing In-field detection system with AI edge computing

Rao,

Zhao,

Huang

2024

International Conference on Algorithm, Imaging Processing, and Machine Vision (AIPMV 2023)

View full text Add to dashboard Cite

To address the low efficiency of manual inspection methods used for Citrus Huanglongbing prevention and control, a system design of citrus huanglongbing in-field detection with AI edge computing device is proposed and evaluated. The system consist of Image Capture Robotic Devices, AI Edge Computing Service, Cloud Service, and Remote Control Client. A citrus Huanglongbing detection neural network model was trained with 84.1%mAP, which can be deployed on an AI edge computing device, such as Jetson Nano to detect HLB with lower delay than using a cloud-based AI approach. Therefore, robotic devices such as UAVs, surveillance cameras can be used to efficiently inspect citrus orchard, process images of citrus leaves collected from cameras in real-time. Experimental result shows that this system has great potential to apply on Citrus Huanglongbing field detection scenario to enhance the inspection efficiency of citrus orchards.

show abstract

Real-time and accurate detection of citrus in complex scenes based on HPL-YOLOv4

Cited by 32 publications

References 39 publications

ASFL-YOLOX: an adaptive spatial feature fusion and lightweight detection method for insect pests of the Papilionidae family

ASFL-YOLOX: an adaptive spatial feature fusion and lightweight detection method for insect pests of the Papilionidae family

Detection and Localization of Tea Bud Based on Improved YOLOv5s and 3D Point Cloud Processing

Towards Huanglongbing In-field detection system with AI edge computing

Contact Info

Product

Resources

About