Three-dimensional perception of orchard banana central stock enhanced by adaptive multi-vision technology

Chen, Mingyou; Tang, Yunchao; Zou, Xiangjun; Huang, Kuang Yu; Huang, Zhengxu; Zhou, Huaibei; Chen, Zhong; Lian, Guoping

doi:10.1016/j.compag.2020.105508

Cited by 90 publications

(56 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clark et al [58] detected banana plantations through aerial images and used U-NET neural network to draw maps, but did not conduct detection and research on banana fruits. Chen et al [59] detected the banana central stocks using Deeplab V3 + network with two binocular cameras, and obtained satisfactory results.…”

Section: B Research On Fruit and Vegetable Detectionmentioning

confidence: 99%

Fast and Accurate Detection of Banana Fruits in Complex Background Orchards

Duan

Zou

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The detection of banana fruits is an important part of intelligent management in the banana plantation. To detect the banana fruit quickly and accurately in the complex orchard environment, this paper proposes a method based on the latest deep learning algorithm to detect the banana fruit. Using a monocular camera, we applied the YOLOv4 neural network algorithm to extract the deep features of banana fruits, realizing accurate detection of different banana sizes. The detection algorithm achieved a 99.29% detection rate, the average execution time was 0.171s, the shortest execution time was 0.135s, and the AP was 0.9995. Moreover, the detection results were discussed with the YOLOv3 algorithm and the machine learning algorithm. Compared with the machine learning algorithm, deep learning algorithm was superior to both detection accuracy and detection time. YOLOv4 had higher detection confidence and higher detection rate than YOLOv3. The results show that the proposed method could realize the fast detection of different varieties and different maturity in banana plantations, under different illumination and occlusion conditions, and provide information for banana picking, maturity and yield estimation. INDEX TERMS Banana detection, orchard environment, deep learning, green fruit, YOLOv4. L.Fu et al.: Fast and Accurate Detection of Banana Fruits in Complex Background Orchards L.Fu et al.: Fast and Accurate Detection of Banana Fruits in Complex Background Orchards

show abstract

Section: B Research On Fruit and Vegetable Detectionmentioning

confidence: 99%

Fast and Accurate Detection of Banana Fruits in Complex Background Orchards

Duan

Zou

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…A combination of two cameras was used for imaging and crop boundary estimation. Recently, multiple cameras were used to estimate the 3D coordinates of banana bunches in an orchard in [25]. A triangulation technique has been used for picking point estimation.…”

Section: Robotic Harvestingmentioning

confidence: 99%

A Sample Weight and AdaBoost CNN-Based Coarse to Fine Classification of Fruit and Vegetables at a Supermarket Self-Checkout

2020

View full text Add to dashboard Cite

The physical features of fruit and vegetables make the task of vision-based classification of fruit and vegetables challenging. The classification of fruit and vegetables at a supermarket self-checkout poses even more challenges due to variable lighting conditions and human factors arising from customer interactions with the system along with the challenges associated with the colour, texture, shape, and size of a fruit or vegetable. Considering this complex application, we have proposed a progressive coarse to fine classification technique to classify fruit and vegetables at supermarket checkouts. The image and weight of fruit and vegetables have been obtained using a prototype designed to simulate the supermarket environment, including the lighting conditions. The weight information is used to change the coarse classification of 15 classes down to three, which are further used in AdaBoost-based Convolutional Neural Network (CNN) optimisation for fine classification. The training samples for each coarse class are weighted based on AdaBoost optimisation, which are updated on each iteration of a training phase. Multi-class likelihood distribution obtained by the fine classification stage is used to estimate a final classification with a softmax classifier. GoogleNet, MobileNet, and a custom CNN have been used for AdaBoost optimisation, with promising classification results.

show abstract

“…The computer vision is an intuitive detection method for fruit maturity (Avila, Mora, Oyarce, Zuniga, & Fredes, 2015; Siswantoro, Arwoko, & Widiasri, 2020). Through image collection and processing, the surface information of fruit, such as size, color, volume, and shape can be extracted to evaluate the maturity (Chen et al, 2020). Takahashi, Maki, Nishina, and Takayama (2013) obtained RGB values from tomato images and formulated a comprehensive color feature to evaluate the tomato maturity stages.…”

Section: Introductionmentioning

confidence: 99%

Identification of tomato maturity based on multinomial logistic regression with kernel clustering by integrating color moments and physicochemical indices

Jiang

Bian

Wang

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

The identification of tomato maturity is significant to extend the fruit shelf life and generate the scientific processing strategy. Tomato maturation is a gradual process, and the internal physicochemical characteristics are most related to maturity states. Merely choosing visual features to identify maturity would cause discriminant errors. This study designed a simple and effective identification method for tomato maturity by integrating color moments and physicochemical indices. The color moments were extracted by an adaptive K-means clustering image processing program, and firmness, soluble solid content and sensory evaluation were measured by professional techniques. The optimal multidimensional index set was formulated according to color moments and physicochemical indices simultaneously. To reduce the confusion between adjacent stages, a novel multinomial logistic regression with kernel clustering (MLRKC) method was designed to identify maturity, and the accuracy was 95.83% for tomato testing set. Moreover, the traditional image features set and some classic methods were applied to verify the performance of proposed method, respectively. Finally, the proposed method was applied to identify the tomatoes in the realistic circumstance. The identification results demonstrated satisfactory performances and promising applications of MLRKC method integrating color moments and physicochemical indices. Practical Applications Tomato is a climacteric fruit which could mature after harvesting. Identification tomato maturity stage is significant to decide the optimal transportation modes, inventory strategies and processing technology. Traditional methods for identifying tomato maturity were high-cost and complicated, which were inefficient for small-scale production. The method proposed in this study could simply the identification steps and reduce the operating cost, and also provide more accurate and valuable information. The investigated theoretical basis could be incorporated into the small farmers and small-scale food processing companies to achieve tomato precision processing with low additional costs. 1 | INTRODUCTION Tomato is rich in nutrients such as vitamins, carotenes, dietary fiber, and is an essential part of human daily diets (Feng, Zhang, Adhikari, & Guo, 2019). As one of the climacteric fruits, tomato has the postharvest maturity characteristics, that is, maturing after harvesting

show abstract

Three-dimensional perception of orchard banana central stock enhanced by adaptive multi-vision technology

Cited by 90 publications

References 41 publications

Fast and Accurate Detection of Banana Fruits in Complex Background Orchards

Fast and Accurate Detection of Banana Fruits in Complex Background Orchards

A Sample Weight and AdaBoost CNN-Based Coarse to Fine Classification of Fruit and Vegetables at a Supermarket Self-Checkout

Identification of tomato maturity based on multinomial logistic regression with kernel clustering by integrating color moments and physicochemical indices

Contact Info

Product

Resources

About