Tea chrysanthemum detection under unstructured environments using the TC-YOLO model

Chen, Qi; Gao, Junfeng; Pearson, Simon; Harman, Helen; Chen, Kunjie; Shu, Lei

doi:10.1016/j.eswa.2021.116473

Cited by 35 publications

(23 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most studies in which the YOLO is used to establish the target recognition model, the researchers consider the box loss and object loss of the model as well as the recall rate and average precision calculated from the former two indicators when evaluating the accuracy of the model [ 25 , 32 ]. In this study, the YOLO-v5 model is trained based on reducing the box loss without considering the object loss of the model.…”

Section: Discussionmentioning

confidence: 99%

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Sun

Zhang

Tong

et al. 2022

Foods

View full text Add to dashboard Cite

This study aims to develop a high-speed and nondestructive mildewed rice grain detection method. First, a set of microscopic images of rice grains contaminated by Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea are acquired to serve as samples, and the mildewed regions are marked. Then, three YOLO-v5 models for identifying regions of rice grain with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in microscopic images are established. Finally, the relationship between the proportion of mildewed regions and the total number of colonies is analyzed. The results show that the proposed YOLO-v5 models achieve accuracy levels of 89.26%, 91.15%, and 90.19% when detecting mildewed regions with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in the microscopic images of the verification set. The proportion of the mildewed region area of rice grain with contamination of Aspergillus niger/Penicillium citrinum/Aspergillus cinerea is logarithmically correlated with the logarithm of the total number of colonies (TVC). The corresponding determination coefficients are 0.7466, 0.7587, and 0.8148, respectively. This study provides a reference for future research on high-speed mildewed rice grain detection methods based on MCV technology.

show abstract

Section: Discussionmentioning

confidence: 99%

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Sun

Zhang

Tong

et al. 2022

Foods

View full text Add to dashboard Cite

show abstract

“…Finally, the above-processed images were selected manually to delete the obscure images, leaving 11592 Bochrysanthemum images in the dataset, of which 221 images were reserved after the above processing step. Qi et al (2022b) showed that up to 3000 images are sufficient to train and achieve better detection precision in the TC-YOLO model. Thus, in the dataset, the number of labelled images for each type of tea chrysanthemum was limited to 3000.…”

Section: Image Annotation and Dataset Productionmentioning

confidence: 99%

“…as well as differences in maturity, colour, and the direction of chrysanthemums' flower heads. Many researchers have identified chrysanthemums by overcoming some of the above (Yang et al, 2018;Yuan et al, 2018;Liu et al, 2019;Yang et al, 2019;et al, 2020;Qi et al, 2021;Qi et al, 2022a;Qi et al, 2022b), and these studies indicate that:…”

Section: Introductionmentioning

confidence: 99%

“…(4) Photographing conditions: A large number of occlusions, overlap, direct light (The green circle in Figure 1), shadow (the red circle in Figure 1), and backlight (The orange circle in Figure 1) images are collected under the photographing conditions, such as wind and the light intensity changes. To reduce these external factor influences on image quality, a large number of images are necessary to detection models (Qi et al, 2022b).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image dataset of tea chrysanthemums in complex outdoor scenes

et al. 2023

Self Cite

View full text Add to dashboard Cite

“…In this article, our goal is to generate datasets that can be used for the tea chrysanthemum detection task. We tested the images generated by TC-GAN on some state-of-the-art object detection models, as well as our own proposed detection model (TC-YOLO) ( Qi et al, 2022 ). Moreover, for subsequent development work on an automated selective chrysanthemum picking robot, we chose to test the images generated by TC-GAN on a low-power embedded GPU platform, the NVIDIA Jetson TX2, as shown in Figure 1 .…”

Section: Introductionmentioning

confidence: 99%

Tea Chrysanthemum Detection by Leveraging Generative Adversarial Networks and Edge Computing

et al. 2022

Self Cite

View full text Add to dashboard Cite

A high resolution dataset is one of the prerequisites for tea chrysanthemum detection with deep learning algorithms. This is crucial for further developing a selective chrysanthemum harvesting robot. However, generating high resolution datasets of the tea chrysanthemum with complex unstructured environments is a challenge. In this context, we propose a novel tea chrysanthemum – generative adversarial network (TC-GAN) that attempts to deal with this challenge. First, we designed a non-linear mapping network for untangling the features of the underlying code. Then, a customized regularization method was used to provide fine-grained control over the image details. Finally, a gradient diversion design with multi-scale feature extraction capability was adopted to optimize the training process. The proposed TC-GAN was compared with 12 state-of-the-art generative adversarial networks, showing that an optimal average precision (AP) of 90.09% was achieved with the generated images (512 × 512) on the developed TC-YOLO object detection model under the NVIDIA Tesla P100 GPU environment. Moreover, the detection model was deployed into the embedded NVIDIA Jetson TX2 platform with 0.1 s inference time, and this edge computing device could be further developed into a perception system for selective chrysanthemum picking robots in the future.

show abstract

Tea chrysanthemum detection under unstructured environments using the TC-YOLO model

Cited by 35 publications

References 23 publications

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Image dataset of tea chrysanthemums in complex outdoor scenes

Tea Chrysanthemum Detection by Leveraging Generative Adversarial Networks and Edge Computing

Contact Info

Product

Resources

About