Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system

Wang, Zhipeng; Jin, Luoyi; Wang, Shuai; Xu, Huirong

doi:10.1016/j.postharvbio.2021.111808

Cited by 111 publications

(19 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the novelty of YOLOv5, not a lot of research has been undertaken using it. Table 4 and Table 5 shows the comparison between the work in [ 42 , 47 ] and our model. For a sound comparison, we used their trained model and tested it on our dataset.…”

Section: Resultsmentioning

confidence: 99%

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Batra

Hussain

Ahad

et al. 2022

Sensors

View full text Add to dashboard Cite

With the rapid development of deep learning techniques, new innovative license plate recognition systems have gained considerable attention from researchers all over the world. These systems have numerous applications, such as law enforcement, parking lot management, toll terminals, traffic regulation, etc. At present, most of these systems rely heavily on high-end computing resources. This paper proposes a novel memory and time-efficient automatic license plate recognition (ALPR) system developed using YOLOv5. This approach is ideal for IoT devices that usually have less memory and processing power. Our approach incorporates two stages, i.e., using a custom transfer learned model for license plate detection and an LSTM-based OCR engine for recognition. The dataset that we used for this research was our dataset consisting of images from the Google open images dataset and the Indian License plate dataset. Along with training YOLOv5 models, we also trained YOLOv4 models on the same dataset to illustrate the size and performance-wise comparison. Our proposed ALPR system results in a 14 megabytes model with a mean average precision of 87.2% and 4.8 ms testing time on still images using Nvidia T4 GPU. The complete system with detection and recognition on the other hand takes about 85 milliseconds.

show abstract

Section: Resultsmentioning

confidence: 99%

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

Batra

Hussain

Ahad

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Although this model has the ability to detect SAR (Synthetic Aperture Radar) ships in real-time, it is difficult to deploy in coal mines because of the complex lighting environment. The papers [18][19][20][21] have deployed object detection models on embedded platforms using model pruning, which has been widely used in many fields such as industry, agriculture, and so on. The above approaches mainly use the scale factors of BN layers as the criteria of filter importance.…”

Section: Model Pruningmentioning

confidence: 99%

“…It has the advantages of high real-time performance and fewer parameters compared with two-stage models [17]. In order to deploy YOLO on embedded platforms, researchers have undertaken a lot of work to reduce the number of parameters and calculations [18][19][20][21]. However, how to identify redundant channels or filters is still a challenge.…”

Section: Introductionmentioning

confidence: 99%

CAP-YOLO: Channel Attention Based Pruning YOLO for Coal Mine Real-Time Intelligent Monitoring

Meng

et al. 2022

Sensors

View full text Add to dashboard Cite

Real-time coal mine intelligent monitoring for pedestrian identifying and positioning is an important means to ensure safety in production. Traditional object detection models based on neural networks require significant computational and storage resources, which results in difficulty of deploying models on edge devices for real-time intelligent monitoring. To address the above problems, CAP-YOLO (Channel Attention based Pruning YOLO) and AEPSM (adaptive image enhancement parameter selection module) are proposed in this paper to achieve real-time intelligent analysis for coal mine surveillance videos. Firstly, DCAM (Deep Channel Attention Module) is proposed to evaluate the importance level of channels in YOLOv3. Secondly, the filters corresponding to the low importance channels are pruned to generate CAP-YOLO, which recovers the accuracy through fine-tuning. Finally, considering the lighting environments are varied in different coal mine fields, AEPSM is proposed to select parameters for CLAHE (Contrast Limited Adaptive Histogram Equalization) under different fields. Experiment results show that the weight size of CAP-YOLO is 8.3× smaller than YOLOv3, but only 7% lower than mAP, and the inference speed of CAP-YOLO is three times faster than that of YOLOv3. On NVIDIA Jetson TX2, CAP-YOLO realizes 31 FPS inference speed.

show abstract

“…Los métodos que generalmente se utilizan para la clasificación de variedades y detección de defectos superficiales de la manzana se basan en técnicas de procesamiento de imágenes digitales que consideran la eliminación del fondo, segmentación de defectos y la identificación de las zonas del tallo y del cáliz (Wang et al, 2022).…”

Section: Clasificación De Manzanas Con Redes Neuronales Convolucionalesunclassified

“…Para resolver la tarea de clasificación de la manzana, en muchos casos los productores implementan líneas de inspección visual donde personas son entrenadas para identificar clase, tamaño, grado de madurez, textura y daños principalmente; sin embargo, estos métodos son subjetivos y dificultan la inspección de grandes lotes del fruto o análisis en masa, pues son de alto costo y baja eficiencia (Wang et al, 2022).…”

Section: Clasificación De Manzanas Con Redes Neuronales Convolucionalesunclassified

Clasificación De Manzanas Con Redes Neuronales Convolucionales

Olguín-Rojas¹,

Vasquez-Gomez

López-Canteñs

et al. 2022

RevFitotecMex

View full text Add to dashboard Cite

Actualmente, en puntos de venta y en empresas agroindustriales de México, la clasificación de manzanas (Malus domestica) la realizan personas de forma manual, lo que genera deficiencias en la calidad del producto. Estos problemas se pueden reducir con la implementación de equipos de visión en sitio equipados con algoritmos de aprendizaje automático. En este estudio se analizaron varias arquitecturas de red neuronal convolucional (CNN) y se seleccionó una que permite clasificar manzanas en sanas y dañadas en el proceso en postcosecha. Las variedades utilizadas fueron Red Delicious, Granny Smith, Golden Delicious y Gala. Se comparó la exactitud de las CNN LeNet5 y VGG16. Se realizó una serie de tratamientos (combinación de red con hiperparámetros) que se utilizaron para la clasificación del objeto de estudio. Al probarse cada tratamiento se midió su rendimiento. Al finalizar, el tratamiento con mejor rendimiento fue LeNet5 entrenada desde cero con el optimizador RMSProp, que obtuvo una exactitud del 97 %.

show abstract

Apple stem/calyx real-time recognition using YOLO-v5 algorithm for fruit automatic loading system

Cited by 111 publications

References 30 publications

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

A Novel Memory and Time-Efficient ALPR System Based on YOLOv5

CAP-YOLO: Channel Attention Based Pruning YOLO for Coal Mine Real-Time Intelligent Monitoring

Clasificación De Manzanas Con Redes Neuronales Convolucionales

Contact Info

Product

Resources

About