Detection of tomato plant phenotyping traits using YOLOv5-based single stage detectors

Cardellicchio, Angelo; Solimani, Firozeh; Dimauro, Giovanni; Petrozza, Angelo; Summerer, Stephan; Cellini, Francesco; Renò, Vito

doi:10.1016/j.compag.2023.107757

Cited by 69 publications

(33 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [23], developed a channel pruning YOLOV5S model, to detect apple bunches before fruit thinning, and achieved the same detection accuracy as the YOLOV5S model but with 92.7% fewer parameters. Cardellicchio et al [24], analyzed different versions of the YOLOV5 model to identify tomatoes, flowers, and nodes, using TTA (test-time augmentation) and model ensembling methods to improve the accuracy. Dananjayan et al [25] detected citrus leaf diseases, based on scaled YOLOV4 P7.…”

Section: Research On Plant Detectionmentioning

confidence: 99%

Banana Pseudostem Visual Detection Method Based on Improved YOLOV7 Detection Algorithm

Cai

Liang

et al. 2023

Agronomy

View full text Add to dashboard Cite

Detecting banana pseudostems is an indispensable part of the intelligent management of banana cultivation, which can be used in settings such as counting banana pseudostems and smart fertilization. In complex environments, dense and occlusion banana pseudostems pose a significant challenge for detection. This paper proposes an improved YOLOV7 deep learning object detection algorithm, YOLOV7-FM, for detecting banana pseudostems with different growth conditions. In the loss optimization part of the YOLOV7 model, Focal loss is introduced, to optimize the problematic training for banana pseudostems that are dense and sheltered, so as to improve the recognition rate of challenging samples. In the data augmentation part of the YOLOV7 model, the Mixup data augmentation is used, to improve the model’s generalization ability for banana pseudostems with similar features to complex environments. This paper compares the AP (average precision) and inference speed of the YOLOV7-FM algorithm with YOLOX, YOLOV5, YOLOV3, and Faster R-CNN algorithms. The results show that the AP and inference speed of the YOLOV7-FM algorithm is higher than those models that are compared, with an average inference time of 8.0 ms per image containing banana pseudostems and AP of 81.45%. This improved YOLOV7-FM model can achieve fast and accurate detection of banana pseudostems.

show abstract

Section: Research On Plant Detectionmentioning

confidence: 99%

Banana Pseudostem Visual Detection Method Based on Improved YOLOV7 Detection Algorithm

Cai

Liang

et al. 2023

Agronomy

View full text Add to dashboard Cite

show abstract

“…On the Tesla V100, the real-time detection speed of the COCO2017 dataset reaches 156 FPS, and the accuracy rate is 56.8% AP. At present, YOLOV5 is widely used in many different application scenarios, such as agriculture [ 21 , 22 ], industry [ 23 , 24 ] and other industries. In this paper, YOLOV5s is selected as the basic algorithm, taking into account the balance between the target detection accuracy and speed.…”

Section: Related Workmentioning

confidence: 99%

Strip Surface Defect Detection Algorithm Based on YOLOv5

et al. 2023

View full text Add to dashboard Cite

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

show abstract

“…The detection accuracy reached 94.4%, respectively, but the frame rate was only 19.23 FPS on mobile computers, which did not meet the real-time requirements. Cardellicchio et al [29] achieved high scores in detecting nodes, fruits and flowers using tomato plant phenotypic traits based on the YOLOv5 structure. Wu et al [30] constructed a new YOLOv5-B model using the Involu-tionBottleneck module of the YOLOv5 network structure and combined it with edge detection methods to complete the 3D localisation of bananas.…”

Section: Introductionmentioning

confidence: 99%

A lightweight waxberry fruit detection model based on YOLOv5

Yang,

Liu,

2024

IET Image Processing

View full text Add to dashboard Cite

In order to solve the safety and efficiency problems in the picking process of Waxberry, the slow speed and low precision of high‐density Waxberry target detection under a complex background were studied. A lightweight Waxberry target detection algorithm based on YOLOv5 is studied. In this study, C3‐Faster1 and C3‐Faster2 modules are proposed, which are located in the backbone and neck of the network: C3‐Faster1 can improve the model speed with a simple structure; C3‐Faster2 integrates the context attention mechanism and transform module based on C3‐Faster1 to make the network pay attention to the information of Waxberry image context and expand the channel receptive field. A new pyramid module, SPPFCSPC, is proposed to expand the sensing field and improve the accuracy of boundary detection. It also combines the Coordinate Attention (CA) and Dyhead dynamic detection head to suppress useless information and enhance the detection ability of small targets. Compared to YOLOv4, YOLOv7, and YOLOv8, mean accuracy percentage (mAP) improved by 5.7%, 9.4%, 8.3%. Compared to the base YOLOv5 model, mAP has improved from 86.5% to 91.9%, running on 2 GB Jeston nano, and the improved model is 5.03 frames per second (FPS) faster than YOLOv5. Experiments show that the designed module is more effective in Waxberry detection tasks.

show abstract

Detection of tomato plant phenotyping traits using YOLOv5-based single stage detectors

Cited by 69 publications

References 30 publications

Banana Pseudostem Visual Detection Method Based on Improved YOLOV7 Detection Algorithm

Banana Pseudostem Visual Detection Method Based on Improved YOLOV7 Detection Algorithm

Strip Surface Defect Detection Algorithm Based on YOLOv5

A lightweight waxberry fruit detection model based on YOLOv5

Contact Info

Product

Resources

About