Fast location and classification of small targets using region segmentation and a convolutional neural network

Wu, Zhengmin; Luo, Kun; Cao, Chengmao; Liu, Guangzong; Wang, Errui; Li, Wenbao

doi:10.1016/j.compag.2019.105207

Cited by 10 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can also use a custom polyhedron to import the particle model. Considering that the main purpose of the simulation process is to discern the movement track of tea particles in the pot groove and their full turnover in this groove, different shapes of tea particles could prolong the time required for the simulation's operation (Wu et al, 2020). Therefore, in practice, the axial length of tea particles should exceed their radial length of tea particles, so simplifying tea particles to spherical particles is inappropriate.…”

Section: Establishing the Simulation Model Of Tea Particlesmentioning

confidence: 99%

Porous Hot Air Tea De-Enzyming and Carding Machine Under Gas–solid Coupling Conditions: Numerical Simulations and Performance Testing

BI,

JIA,

QIN

et al. 2023

INMATEH

Self Cite

View full text Add to dashboard Cite

The gas–solid coupling of a porous hot-air tea de-enzyming and carding machine was studied by means of computational fluid dynamics and discrete element coupling. In the numerical model, the discrete phase of tea particles was simulated using Rocky-DEM software, while the gas phase was described by ANSYS Fluent software. A mathematical model of the movement characteristics of tea particles in air was established according to the principle of fluid mechanics, to carry out dynamic analysis of tea particles’ movement process and derive how the motion of gas and tea particles is governed. Three sets of prototype tests were carried out on the basis of the design and simulation, and the average of their results taken. This showed that the hourly output of the test prototype was 3.89 kg/h, the bar-type rate was 89.14%, the de-enzyming moderation rate was 91.67%, and the average value of the measured effective operating temperature of the pot slot was 189 °C. The performance of the prototype was also tested and analyzed. After conducting a tea sensory evaluation expert appraisal, the sensory evaluation indices of the prototype-processed tea satisfied all current market requirements, being superior to those of the conventional de-enzyming and carding machine. The quality of the finished tea also met the agronomic standards and the operational requirements of the de-enzyming and carding machine.

show abstract

Section: Establishing the Simulation Model Of Tea Particlesmentioning

confidence: 99%

Porous Hot Air Tea De-Enzyming and Carding Machine Under Gas–solid Coupling Conditions: Numerical Simulations and Performance Testing

BI,

JIA,

QIN

et al. 2023

INMATEH

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed method could correctly segment 99.4% of the object regions in the test images and correctly classified 96.5% of the foreign objects in the validation images; it correctly detected 100.0% of the test images. In a separate study, walnut shell-breaking matter is processed using machine vision to accurately sort kernels, shells, and unseparated bodies with an overall recognition accuracy of 96% [14]. Overall, exogenous foreign bodies and ground nutshells are easily identifiable, since their superficial characteristics differ significantly from those of walnut kernels.…”

Section: Introductionmentioning

confidence: 99%

WT-YOLOM: An Improved Target Detection Model Based on YOLOv4 for Endogenous Impurity in Walnuts

et al. 2023

View full text Add to dashboard Cite

Since impurities produced during walnut processing can cause serious harm to human health, strict quality control must be carried out during production. However, most detection equipment still uses photoelectric detection technology to automatically sort heterochromatic particles, which is unsuitable for detecting endogenous foreign bodies with similar colors. Therefore, this paper proposes an improved YOLOv4 deep learning object detection algorithm, WT-YOLOM, for detecting endogenous impurities in walnuts—namely, oily kernels, black spot kernels, withered kernels, and ground nutshells. In the backbone of the model, a lightweight MobileNet module was used as the encoder for the extraction of features. The spatial pyramid pooling (SPP) structure was improved to spatial pyramid pooling—fast (SPPF), and the model size was further reduced. Loss function was replaced in this model with a more comprehensive SIoU loss. In addition, efficient channel attention (ECA) mechanisms were applied after the backbone feature map to improve the model’s recognition accuracy. This paper compares the recognition speed and accuracy of the WT-YOLOM algorithm with the Faster R-CNN, EfficientDet, CenterNet, and YOLOv4 algorithms. The results showed that the average precision of this model for different kinds of endogenous impurities in walnuts reached 94.4%. Compared with the original model, the size was reduced by 88.6%, and the recognition speed reached 60.1 FPS, which was an increase of 29.0%. The metrics of the WT-YOLOM model were significantly better than those of comparative models and can significantly improve the detection efficiency of endogenous foreign bodies in walnuts.

show abstract

“…Wang et al [19] used the YOLOv5 algorithm for the real-time recognition of apple stem and calyx, laying the foundation for the automation of fruit loading and packaging systems. Wu et al [20] applied the deep convolutional neural network algorithm to detect walnut shell kernels, achieving good recognition results when the shell kernels were dispersed and classified. Meng et al [21] detected tea buds amidst complex backgrounds using the YOLOv7 algorithm, providing a theoretical basis for intelligent tea picking.…”

Section: Introductionmentioning

confidence: 99%

Machine Vision-Based Chinese Walnut Shell–Kernel Recognition and Separation

Zhang,

Wang,

Liu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Walnut shell–kernel separation is an essential step in the deep processing of walnut. It is a crucial factor that prevents the increase in the added value and industrial development of walnuts. This study proposes a walnut shell–kernel detection method based on YOLOX deep learning using machine vision and deep-learning technology to address common issues, such as incomplete shell–kernel separation in the current airflow screening, high costs and the low efficiency of manually assisted screening. A dataset was produced using Labelme by acquiring walnut shell and kernel images following shellshock. This dataset was transformed into the COCO dataset format. Next, 110 epochs of training were performed on the network. When the intersection over the union threshold was 0.5, the average precision (AP), the average recall rate (AR), the model size, and floating point operations per second were 96.3%, 84.7%, 99 MB, and 351.9, respectively. Compared with YOLOv3, Faster Region-based Convolutional Neural Network (Faster R-CNN), and Single Shot MultiBox Detector algorithms (SSD), the AP value of the proposed algorithm was increased by 2.1%, 1.3%, and 3.4%, respectively. Similarly, the AR was increased by 10%, 2.3%, and 9%, respectively. Meanwhile, walnut shell–kernel detection was performed under different situations, such as distinct species, supplementary lighting, or shielding conditions. This model exhibits high recognition and positioning precision under different walnut species, supplementary lighting, and shielding conditions. It has high robustness. Moreover, the small size of this model is beneficial for migration applications. This study’s results can provide some technological references to develop faster walnut shell–kernel separation methods.

show abstract

Fast location and classification of small targets using region segmentation and a convolutional neural network

Cited by 10 publications

References 21 publications

Porous Hot Air Tea De-Enzyming and Carding Machine Under Gas–solid Coupling Conditions: Numerical Simulations and Performance Testing

Porous Hot Air Tea De-Enzyming and Carding Machine Under Gas–solid Coupling Conditions: Numerical Simulations and Performance Testing

WT-YOLOM: An Improved Target Detection Model Based on YOLOv4 for Endogenous Impurity in Walnuts

Machine Vision-Based Chinese Walnut Shell–Kernel Recognition and Separation

Contact Info

Product

Resources

About