PcMNet: An efficient lightweight apple detection algorithm in natural orchards
Apple detection plays a critical role in enabling the functionality of harvesting robots within natural orchard environments. To address challenges related to low detection accuracy, slow inference speed, and high parameter count, we present PcMNet, a lightweight detection model based on an improved...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375524002284 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846124971320934400 |
|---|---|
| author | Shiwei Wen Jianguo Zhou Guangrui Hu Hao Zhang Shan Tao Zeyu Wang Jun Chen |
| author_facet | Shiwei Wen Jianguo Zhou Guangrui Hu Hao Zhang Shan Tao Zeyu Wang Jun Chen |
| author_sort | Shiwei Wen |
| collection | DOAJ |
| description | Apple detection plays a critical role in enabling the functionality of harvesting robots within natural orchard environments. To address challenges related to low detection accuracy, slow inference speed, and high parameter count, we present PcMNet, a lightweight detection model based on an improved YOLOv8 network. Initially, we employed Partial Convolution (Pconv) to construct a PR module, forming the Pconv-block, which subsequently replaced the original C2f feature extraction module within the YOLOv8n backbone. This replacement led to improvements in both detection accuracy and speed, while simultaneously reducing computational complexity (FLOPs), parameter count, and model size. Furthermore, the Cross-Scale Feature Fusion (CCFF) module was refined into Faster-Cross-Scale Feature Fusion (Faster-CCFF) with the integration of Pconv-block, significantly enhancing the model's feature extraction and fusion capabilities. Additionally, we introduced Mixed Local Channel Attention (MLCA) to further strengthen the model's capacity to capture essential features while effectively suppressing background noise. Experimental results demonstrate that PcMNet achieved a detection accuracy of 92.8 % and an mAP@0.5 of 95.5 %, representing improvements of 1.4 and 0.7 percentage points, respectively, over YOLOv8n. Moreover, PcMNet successfully reduced FLOPs, parameter count, and model size to 5.1 G, 1.4 M, and 3.2 MB, respectively. The per-image detection time was reduced to 2.3 ms, indicating reductions of 37.80 %, 53.33 %, 49.21 %, and 56.60 % in FLOPs, parameters, model size, and detection time compared to YOLOv8n. When deployed on edge computing devices with TensorRT acceleration, PcMNet achieved a detection rate of 92 FPS. Field validation experiments conducted in natural orchard environments confirmed PcMNet's superior ability to detect apples under challenging conditions, such as occlusions and varying lighting conditions. Its lightweight design and rapid detection capabilities provide a valuable reference for achieving real-time apple detection in automated and intelligent harvesting robots, thereby contributing to advancements in smart agriculture. |
| format | Article |
| id | doaj-art-a6b1aa3fe4894fe0803bdfdc7c0613e5 |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-a6b1aa3fe4894fe0803bdfdc7c0613e52024-12-13T11:08:06ZengElsevierSmart Agricultural Technology2772-37552024-12-019100623PcMNet: An efficient lightweight apple detection algorithm in natural orchardsShiwei Wen0Jianguo Zhou1Guangrui Hu2Hao Zhang3Shan Tao4Zeyu Wang5Jun Chen6College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaCorresponding author.; College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi 712100, PR ChinaApple detection plays a critical role in enabling the functionality of harvesting robots within natural orchard environments. To address challenges related to low detection accuracy, slow inference speed, and high parameter count, we present PcMNet, a lightweight detection model based on an improved YOLOv8 network. Initially, we employed Partial Convolution (Pconv) to construct a PR module, forming the Pconv-block, which subsequently replaced the original C2f feature extraction module within the YOLOv8n backbone. This replacement led to improvements in both detection accuracy and speed, while simultaneously reducing computational complexity (FLOPs), parameter count, and model size. Furthermore, the Cross-Scale Feature Fusion (CCFF) module was refined into Faster-Cross-Scale Feature Fusion (Faster-CCFF) with the integration of Pconv-block, significantly enhancing the model's feature extraction and fusion capabilities. Additionally, we introduced Mixed Local Channel Attention (MLCA) to further strengthen the model's capacity to capture essential features while effectively suppressing background noise. Experimental results demonstrate that PcMNet achieved a detection accuracy of 92.8 % and an mAP@0.5 of 95.5 %, representing improvements of 1.4 and 0.7 percentage points, respectively, over YOLOv8n. Moreover, PcMNet successfully reduced FLOPs, parameter count, and model size to 5.1 G, 1.4 M, and 3.2 MB, respectively. The per-image detection time was reduced to 2.3 ms, indicating reductions of 37.80 %, 53.33 %, 49.21 %, and 56.60 % in FLOPs, parameters, model size, and detection time compared to YOLOv8n. When deployed on edge computing devices with TensorRT acceleration, PcMNet achieved a detection rate of 92 FPS. Field validation experiments conducted in natural orchard environments confirmed PcMNet's superior ability to detect apples under challenging conditions, such as occlusions and varying lighting conditions. Its lightweight design and rapid detection capabilities provide a valuable reference for achieving real-time apple detection in automated and intelligent harvesting robots, thereby contributing to advancements in smart agriculture.http://www.sciencedirect.com/science/article/pii/S2772375524002284Apple detectionLightweight modelYOLOv8Partial convolutionFaster-CCFFEdge computing devices |
| spellingShingle | Shiwei Wen Jianguo Zhou Guangrui Hu Hao Zhang Shan Tao Zeyu Wang Jun Chen PcMNet: An efficient lightweight apple detection algorithm in natural orchards Smart Agricultural Technology Apple detection Lightweight model YOLOv8 Partial convolution Faster-CCFF Edge computing devices |
| title | PcMNet: An efficient lightweight apple detection algorithm in natural orchards |
| title_full | PcMNet: An efficient lightweight apple detection algorithm in natural orchards |
| title_fullStr | PcMNet: An efficient lightweight apple detection algorithm in natural orchards |
| title_full_unstemmed | PcMNet: An efficient lightweight apple detection algorithm in natural orchards |
| title_short | PcMNet: An efficient lightweight apple detection algorithm in natural orchards |
| title_sort | pcmnet an efficient lightweight apple detection algorithm in natural orchards |
| topic | Apple detection Lightweight model YOLOv8 Partial convolution Faster-CCFF Edge computing devices |
| url | http://www.sciencedirect.com/science/article/pii/S2772375524002284 |
| work_keys_str_mv | AT shiweiwen pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT jianguozhou pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT guangruihu pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT haozhang pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT shantao pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT zeyuwang pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards AT junchen pcmnetanefficientlightweightappledetectionalgorithminnaturalorchards |