Fruit Harvesting Robot Using Computer Vision

Mangaonkar, Sahil Mahendra; Khandelwal, Ritvik; Shaikh, Saquib Ahmed; Chandaliya, Sameep; Ganguli, Shrenik

doi:10.1109/iconat53423.2022.9726126

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 n k=n ∑ k=1 AP k (7) where AP k is the AP of class k, and n is the number of classes. Finally, from the confusion matrix, the following performance metrics can be derived:…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Many methods have been proposed for automating the tomato harvesting process [4][5][6][7]. Zhang et al [8] developed a deep-learning model for tomato classification with an accuracy of 91.9% and a recognition time of just 0.01 s per 100 images.…”

Section: Introductionmentioning

confidence: 99%

“…It was shown that the model achieved an F1 score of 92% and thus provided a reliable approach for automating the harvesting process. In general, the methods proposed in [4][5][6][7][8][9][10][11] have the potential to improve the tomato yield and go some way to alleviating the labor shortage problem caused by the COVID-19 pandemic [12,13]. However, these existing automated fruit harvesting methods still encounter challenges related to harsh environments and environmental interference, leading to compromised detection accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tomato Fruit Detection Using Modified Yolov5m Model with Convolutional Neural Networks

Tsai,

Nguyen,

Duong

et al. 2023

Plants

View full text Add to dashboard Cite

The farming industry is facing the major challenge of intensive and inefficient harvesting labors. Thus, an efficient and automated fruit harvesting system is required. In this study, three object classification models based on Yolov5m integrated with BoTNet, ShuffleNet, and GhostNet convolutional neural networks (CNNs), respectively, are proposed for the automatic detection of tomato fruit. The various models were trained using 1508 normalized images containing three classes of cherry tomatoes, namely ripe, immature, and damaged. The detection accuracy for the three classes was found to be 94%, 95%, and 96%, respectively, for the modified Yolov5m + BoTNet model. The model thus appeared to provide a promising basis for the further development of automated harvesting systems for tomato fruit.

show abstract

“…1 n k=n ∑ k=1 AP k (7) where AP k is the AP of class k, and n is the number of classes. Finally, from the confusion matrix, the following performance metrics can be derived:…”

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tomato Fruit Detection Using Modified Yolov5m Model with Convolutional Neural Networks

Tsai,

Nguyen,

Duong

et al. 2023

Plants

View full text Add to dashboard Cite

show abstract

“…eΦ(a) characterizes the effect of light on the color and contrast of a low-light image, as it propagates in a low-light environment. In formula (1), XΦ(1-eΦ(a)) characterizes the illumination backscattering component of the low-light environment. Therefore, the effective enhancement of lowlight images aims to estimate XΦ and eΦ(a), two key parameters for the effective enhancement of low-light images.…”

Section: Optical Imaging and Effective Color Enhancement Of Low-light...mentioning

confidence: 99%

“…Most computer vision applications demand input images to meet their specific requirements [1][2][3][4][5][6][7][8]. Take tax detection for example, the input image must be clear and complete.…”

Section: Introductionmentioning

confidence: 99%

Low-Light Image Enhancement and Target Detection Based on Deep Learning

Yao¹

2022

View full text Add to dashboard Cite

Most computer vision applications demand input images to meet their specific requirements. To complete different vision tasks, e.g., object detection, object recognition, and object retrieval, low-light images must be enhanced by different methods to achieve different processing effects. The existing image enhancement methods, which are based on non-physical imaging models, and image generation methods, which are based on deep learning, are not ideal for low-light image processing. To solve the problem, this paper explores low-light image enhancement and target detection based on deep learning. Firstly, a simplified expression was constructed for the optical imaging model of low-light images, and a Haze-line was proposed for color correction of low-light images, which can effectively enhance low-light images based on the global background light and medium transmission rate of the optical imaging model of such images. Next, network framework adopted by the proposed low-light image enhancement model was introduced in detail: the framework includes two deep domain adaptation modules that realize domain transformation and image enhancement, respectively, and the loss functions of the model were presented. To detect targets based on the output enhanced image, a joint enhancement and target detection method was proposed for low-light images. The effectiveness of the constructed model was demonstrated through experiments.

show abstract