Lightweight Detection and Counting of Maize Tassels in UAV RGB Images
By integrating unmanned aerial vehicle (UAV) remote sensing with advanced deep object detection techniques, it can achieve large-scale and high-throughput detection and counting of maize tassels. However, challenges arise from high sunlight, which can obscure features in reflective areas, and low su...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549037274136576 |
|---|---|
| author | Hang Yang Jiaji Wu Yi Lu Yuning Huang Pinwei Yang Yurong Qian |
| author_facet | Hang Yang Jiaji Wu Yi Lu Yuning Huang Pinwei Yang Yurong Qian |
| author_sort | Hang Yang |
| collection | DOAJ |
| description | By integrating unmanned aerial vehicle (UAV) remote sensing with advanced deep object detection techniques, it can achieve large-scale and high-throughput detection and counting of maize tassels. However, challenges arise from high sunlight, which can obscure features in reflective areas, and low sunlight, which hinders feature identification. Existing methods struggle to balance real-time performance and accuracy. In response to these challenges, we propose DLMNet, a lightweight network based on the YOLOv8 framework. DLMNet features: (1) an efficient channel and spatial attention mechanism (ECSA) that suppresses high sunlight reflection noise and enhances details under low sunlight conditions, and (2) a dynamic feature fusion module (DFFM) that improves tassel recognition through dynamic fusion of shallow and deep features. In addition, we built a maize tassel detection and counting dataset (MTDC-VS) with various sunlight conditions (low, normal, and high sunlight), containing 22,997 real maize tassel targets. Experimental results show that on the MTDC-VS dataset, DLMNet achieves a detection accuracy <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi><mn>50</mn></mrow></semantics></math></inline-formula> of 88.4%, which is 1.6% higher than the baseline YOLOv8 model, with a 31.3% reduction in the number of parameters. The counting metric <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> for DLMNet is 93.66%, which is 0.9% higher than YOLOv8. On the publicly available maize tassel detection and counting dataset (MTDC), DLMNet achieves an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi><mn>50</mn></mrow></semantics></math></inline-formula> of 83.3%, which is 0.7% higher than YOLOv8, further demonstrating DLMNet’s excellent generalization ability. This study enhances the model’s adaptability to sunlight, enabling high performance under suboptimal conditions and offering insights for real-time intelligent agriculture monitoring with UAV technology. |
| format | Article |
| id | doaj-art-f30b4679e10b445c92e70aefdfa40b76 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-f30b4679e10b445c92e70aefdfa40b762025-01-10T13:19:55ZengMDPI AGRemote Sensing2072-42922024-12-01171310.3390/rs17010003Lightweight Detection and Counting of Maize Tassels in UAV RGB ImagesHang Yang0Jiaji Wu1Yi Lu2Yuning Huang3Pinwei Yang4Yurong Qian5School of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Software, Xinjiang University, Urumqi 830091, ChinaSchool of Computer Science and Technology, Xinjiang University, Urumqi 830046, ChinaBy integrating unmanned aerial vehicle (UAV) remote sensing with advanced deep object detection techniques, it can achieve large-scale and high-throughput detection and counting of maize tassels. However, challenges arise from high sunlight, which can obscure features in reflective areas, and low sunlight, which hinders feature identification. Existing methods struggle to balance real-time performance and accuracy. In response to these challenges, we propose DLMNet, a lightweight network based on the YOLOv8 framework. DLMNet features: (1) an efficient channel and spatial attention mechanism (ECSA) that suppresses high sunlight reflection noise and enhances details under low sunlight conditions, and (2) a dynamic feature fusion module (DFFM) that improves tassel recognition through dynamic fusion of shallow and deep features. In addition, we built a maize tassel detection and counting dataset (MTDC-VS) with various sunlight conditions (low, normal, and high sunlight), containing 22,997 real maize tassel targets. Experimental results show that on the MTDC-VS dataset, DLMNet achieves a detection accuracy <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi><mn>50</mn></mrow></semantics></math></inline-formula> of 88.4%, which is 1.6% higher than the baseline YOLOv8 model, with a 31.3% reduction in the number of parameters. The counting metric <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> for DLMNet is 93.66%, which is 0.9% higher than YOLOv8. On the publicly available maize tassel detection and counting dataset (MTDC), DLMNet achieves an <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>A</mi><mi>P</mi><mn>50</mn></mrow></semantics></math></inline-formula> of 83.3%, which is 0.7% higher than YOLOv8, further demonstrating DLMNet’s excellent generalization ability. This study enhances the model’s adaptability to sunlight, enabling high performance under suboptimal conditions and offering insights for real-time intelligent agriculture monitoring with UAV technology.https://www.mdpi.com/2072-4292/17/1/3maize tasselsunmanned aerial vehicle (UAV)detection and countingsunlight intensityremote sensing |
| spellingShingle | Hang Yang Jiaji Wu Yi Lu Yuning Huang Pinwei Yang Yurong Qian Lightweight Detection and Counting of Maize Tassels in UAV RGB Images Remote Sensing maize tassels unmanned aerial vehicle (UAV) detection and counting sunlight intensity remote sensing |
| title | Lightweight Detection and Counting of Maize Tassels in UAV RGB Images |
| title_full | Lightweight Detection and Counting of Maize Tassels in UAV RGB Images |
| title_fullStr | Lightweight Detection and Counting of Maize Tassels in UAV RGB Images |
| title_full_unstemmed | Lightweight Detection and Counting of Maize Tassels in UAV RGB Images |
| title_short | Lightweight Detection and Counting of Maize Tassels in UAV RGB Images |
| title_sort | lightweight detection and counting of maize tassels in uav rgb images |
| topic | maize tassels unmanned aerial vehicle (UAV) detection and counting sunlight intensity remote sensing |
| url | https://www.mdpi.com/2072-4292/17/1/3 |
| work_keys_str_mv | AT hangyang lightweightdetectionandcountingofmaizetasselsinuavrgbimages AT jiajiwu lightweightdetectionandcountingofmaizetasselsinuavrgbimages AT yilu lightweightdetectionandcountingofmaizetasselsinuavrgbimages AT yuninghuang lightweightdetectionandcountingofmaizetasselsinuavrgbimages AT pinweiyang lightweightdetectionandcountingofmaizetasselsinuavrgbimages AT yurongqian lightweightdetectionandcountingofmaizetasselsinuavrgbimages |