Considering precision agriculture, recent technological developments have sparked the emergence of several new tools that can help to automate the agricultural process. For instance, accurately detecting and counting apples in orchards is essential for maximizing harvests and ensuring effective resource management. However, there are several intrinsic difficulties with traditional techniques for identifying and counting apples in orchards. To identify, recognize, and detect apples, apple target detection algorithms, such as YOLOv7, have shown a great deal of reflection and accuracy. But occlusions, electrical wiring, branches, and overlapping pose severe issues for precisely detecting apples. Thus, to overcome these issues and accurately recognize apples and find the depth of apples from drone-based videos in complicated backdrops, our proposed model combines a multi-head attention system with the YOLOv7 object identification framework. Furthermore, we provide the ByteTrack method for apple counting in real time, which guarantees effective monitoring of apples. To verify the efficacy of our suggested model, a thorough comparison assessment is performed with several current apple detection and counting techniques. The outcomes adequately proved the effectiveness of our strategy, which continuously surpassed competing methods to achieve exceptional accuracies of 0.92, 0.96, and 0.95 with respect to precision, recall, and F1 score, and a low MAPE of 0.027, respectively.

A Seamless Deep Learning Approach for Apple Detection, Depth Estimation, and Tracking Using YOLO Models Enhanced by Multi-Head Attention Mechanism / Sekharamantry, Praveen Kumar; Melgani, Farid; Malacarne, Jonni; Ricci, Riccardo; de Almeida Silva, Rodrigo; Marcato Junior, Jose. - In: COMPUTERS. - ISSN 2073-431X. - 2024, 13:3(2024), pp. 8301-8325. [10.3390/computers13030083]

A Seamless Deep Learning Approach for Apple Detection, Depth Estimation, and Tracking Using YOLO Models Enhanced by Multi-Head Attention Mechanism

Sekharamantry, Praveen Kumar;Melgani, Farid;Ricci, Riccardo;
2024-01-01

Abstract

Considering precision agriculture, recent technological developments have sparked the emergence of several new tools that can help to automate the agricultural process. For instance, accurately detecting and counting apples in orchards is essential for maximizing harvests and ensuring effective resource management. However, there are several intrinsic difficulties with traditional techniques for identifying and counting apples in orchards. To identify, recognize, and detect apples, apple target detection algorithms, such as YOLOv7, have shown a great deal of reflection and accuracy. But occlusions, electrical wiring, branches, and overlapping pose severe issues for precisely detecting apples. Thus, to overcome these issues and accurately recognize apples and find the depth of apples from drone-based videos in complicated backdrops, our proposed model combines a multi-head attention system with the YOLOv7 object identification framework. Furthermore, we provide the ByteTrack method for apple counting in real time, which guarantees effective monitoring of apples. To verify the efficacy of our suggested model, a thorough comparison assessment is performed with several current apple detection and counting techniques. The outcomes adequately proved the effectiveness of our strategy, which continuously surpassed competing methods to achieve exceptional accuracies of 0.92, 0.96, and 0.95 with respect to precision, recall, and F1 score, and a low MAPE of 0.027, respectively.
2024
3
Sekharamantry, Praveen Kumar; Melgani, Farid; Malacarne, Jonni; Ricci, Riccardo; de Almeida Silva, Rodrigo; Marcato Junior, Jose
A Seamless Deep Learning Approach for Apple Detection, Depth Estimation, and Tracking Using YOLO Models Enhanced by Multi-Head Attention Mechanism / Sekharamantry, Praveen Kumar; Melgani, Farid; Malacarne, Jonni; Ricci, Riccardo; de Almeida Silva, Rodrigo; Marcato Junior, Jose. - In: COMPUTERS. - ISSN 2073-431X. - 2024, 13:3(2024), pp. 8301-8325. [10.3390/computers13030083]
File in questo prodotto:
File Dimensione Formato  
2024_Computers-UAV.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 7.14 MB
Formato Adobe PDF
7.14 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/437940
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 4
  • OpenAlex ND
social impact