Deep Learning with Data Augmentation for Fruit Counting

Pawara, Pornntiwa; Boshchenko, Alina; Schomaker, Lambert; Wiering, Marco A.

doi:10.1007/978-3-030-61401-0_20

Cited by 3 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, all apple data are obtained from publicly available datasets or free images on the Internet, among which we thank the authors of [26] for providing different quality classification apple datasets and [2] for the publicly available tropical fruit dataset, we segment the apple dataset from the tropical fruit dataset and subsequently take out the good apple from the dataset in [26] together as the apple for this experiment training data. Considering the agricultural scenario, the probability of bad apples in the harvest season is low, so bad apples are discarded.…”

Section: Building the Data Setmentioning

confidence: 99%

See 1 more Smart Citation

Fruit Detection and Counting in Apple Orchards Based on Improved Yolov7 and Multi-Object Tracking Methods

Hu,

Fan,

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

With the increasing popularity of online fruit sales, accurately predicting fruit yields has become crucial for optimizing logistics and storage strategies. However, existing manual vision-based systems and sensor methods have proven inadequate for solving the complex problem of fruit yield counting, as they struggle with issues such as crop overlap and variable lighting conditions. Recently CNN-based object detection models have emerged as a promising solution in the field of computer vision, but their effectiveness is limited in agricultural scenarios due to challenges such as occlusion and dissimilarity among the same fruits. To address this issue, we propose a novel variant model that combines the self-attentive mechanism of Vision Transform, a non-CNN network architecture, with Yolov7, a state-of-the-art object detection model. Our model utilizes two attention mechanisms, CBAM and CA, and is trained and tested on a dataset of apple images. In order to enable fruit counting across video frames in complex environments, we incorporate two multi-objective tracking methods based on Kalman filtering and motion trajectory prediction, namely SORT, and Cascade-SORT. Our results show that the Yolov7-CA model achieved a 91.3% mAP and 0.85 F1 score, representing a 4% improvement in mAP and 0.02 improvement in F1 score compared to using Yolov7 alone. Furthermore, three multi-object tracking methods demonstrated a significant improvement in MAE for inter-frame counting across all three test videos, with an 0.642 improvement over using yolov7 alone achieved using our multi-object tracking method. These findings suggest that our proposed model has the potential to improve fruit yield assessment methods and could have implications for decision-making in the fruit industry.

show abstract

Section: Building the Data Setmentioning

confidence: 99%

“…Fruit counting is typically categorized into two types: detection-based fruit counting and regression-based fruit counting. The former is generally regarded as superior in performance, according to recent research [2]. For detection-based fruit counting, accurate fruit detection and localization are key determinants of model performance.…”

Section: Introductionmentioning

confidence: 99%