Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Ostovar, Ahmad; Ringdahl, Ola; Hellström, Thomas

doi:10.3390/robotics7010011

Cited by 22 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research achieved the lowest F-score (65) with the method of [11] for red and green pepper plants, while oranges obtained the highest F-score (96.4) with that of [24]. Previous reported results (Table 1) revealed a 91.5 and 92.6 F-score for peppers in [19,34], respectively, versus our method, which resulted in an F-score of 99.43. For apple images, our method obtained similar F-score performances as in previous work (~93), even though the dataset was much smaller (64 vs. 9 images).…”

Section: Discussionmentioning

confidence: 94%

“…As can be seen in the table, most algorithms focus on pixel-based detection (e.g., segmentation). This is indeed a common method in fruit detection (e.g., [31,32,33,34]). Many segmentation algorithms have been developed [35] including: K-means [36], mean shift analysis [37], Artificial Neural Networks (ANN) [38], Support Vector Machines (SVM) [39], deep learning [25], and several others.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Parameter Tuning for Adaptive Thresholding in Fruit Detection

Zemmour

Kurtser

Edan

2019

Sensors

View full text Add to dashboard Cite

This paper presents an automatic parameter tuning procedure specially developed for a dynamic adaptive thresholding algorithm for fruit detection. One of the major algorithm strengths is its high detection performances using a small set of training images. The algorithm enables robust detection in highly-variable lighting conditions. The image is dynamically split into variably-sized regions, where each region has approximately homogeneous lighting conditions. Nine thresholds were selected to accommodate three different illumination levels for three different dimensions in four color spaces: RGB, HSI, LAB, and NDI. Each color space uses a different method to represent a pixel in an image: RGB (Red, Green, Blue), HSI (Hue, Saturation, Intensity), LAB (Lightness, Green to Red and Blue to Yellow) and NDI (Normalized Difference Index, which represents the normal difference between the RGB color dimensions). The thresholds were selected by quantifying the required relation between the true positive rate and false positive rate. A tuning process was developed to determine the best fit values of the algorithm parameters to enable easy adaption to different kinds of fruits (shapes, colors) and environments (illumination conditions). Extensive analyses were conducted on three different databases acquired in natural growing conditions: red apples (nine images with 113 apples), green grape clusters (129 images with 1078 grape clusters), and yellow peppers (30 images with 73 peppers). These databases are provided as part of this paper for future developments. The algorithm was evaluated using cross-validation with 70% images for training and 30% images for testing. The algorithm successfully detected apples and peppers in variable lighting conditions resulting with an F-score of 93.17% and 99.31% respectively. Results show the importance of the tuning process for the generalization of the algorithm to different kinds of fruits and environments. In addition, this research revealed the importance of evaluating different color spaces since for each kind of fruit, a different color space might be superior over the others. The LAB color space is most robust to noise. The algorithm is robust to changes in the threshold learned by the training process and to noise effects in images.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: Literature Reviewmentioning

confidence: 99%

Automatic Parameter Tuning for Adaptive Thresholding in Fruit Detection

Zemmour

Kurtser

Edan

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…In this work, the segmentation quality shows how well the area of the detected object matches to the manually labeled object. We used two measures to estimate the segmentation quality: segmentation-overlap and segmentation-efficiency (see Figure 3) [39,40]. Segmentation-overlap is defined as the ratio between the overlapped region ( O ) and the manually labeled region ( L ), where overlap is the common area between the segmented region ( S ) and the manually labeled region ( L ).…”

Section: Methodsmentioning

confidence: 99%

Detection and Classification of Root and Butt-Rot (RBR) in Stumps of Norway Spruce Using RGB Images and Machine Learning

Ostovar

Talbot

Puliti

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Root and butt-rot (RBR) has a significant impact on both the material and economic outcome of timber harvesting, and therewith on the individual forest owner and collectively on the forest and wood processing industries. An accurate recording of the presence of RBR during timber harvesting would enable a mapping of the location and extent of the problem, providing a basis for evaluating spread in a climate anticipated to enhance pathogenic growth in the future. Therefore, a system to automatically identify and detect the presence of RBR would constitute an important contribution to addressing the problem without increasing workload complexity for the machine operator. In this study, we developed and evaluated an approach based on RGB images to automatically detect tree stumps and classify them as to the absence or presence of rot. Furthermore, since knowledge of the extent of RBR is valuable in categorizing logs, we also classify stumps into three classes of infestation; rot = 0%, 0% < rot < 50% and rot ≥ 50%. In this work we used deep-learning approaches and conventional machine-learning algorithms for detection and classification tasks. The results showed that tree stumps were detected with precision rate of 95% and recall of 80%. Using only the correct output (TP) of the stump detector, stumps without and with RBR were correctly classified with accuracy of 83.5% and 77.5%, respectively. Classifying rot into three classes resulted in 79.4%, 72.4%, and 74.1% accuracy for stumps with rot = 0%, 0% < rot < 50%, and rot ≥ 50%, respectively. With some modifications, the developed algorithm could be used either during the harvesting operation to detect RBR regions on the tree stumps or as an RBR detector for post-harvest assessment of tree stumps and logs.

show abstract

“…For example, a project supported by the National Technology Research and Development Program of China, proposed a custom designed tool and a lifting support for tomatoes harvesting [17]. Other studies focuses on vision-based algorithms for fruit targeting, as showed in recent works by the Department of Computing Science of Umeå University, which aims to automate the harvest of sweet pepper in greenhouses proposing RGB vision servo control [18], or by Washington State University, which focuses on depth camera-based techniques for robotic cherry harvesting [19]. In general, the design of agricultural mobile robots for grasping activities is considered the most challenging because of the complexity of the mechatronic system [20].…”

Section: Introductionmentioning

confidence: 99%

Design of a UGV Powered by Solar Energy for Precision Agriculture

et al. 2020

View full text Add to dashboard Cite

In this paper, a novel UGV (unmanned ground vehicle) for precision agriculture, named “Agri.q,” is presented. The Agri.q has a multiple degrees of freedom positioning mechanism and it is equipped with a robotic arm and vision sensors, which allow to challenge irregular terrains and to perform precision field operations with perception. In particular, the integration of a 7 DOFs (degrees of freedom) manipulator and a mobile frame results in a reconfigurable workspace, which opens to samples collection and inspection in non-structured environments. Moreover, Agri.q mounts an orientable landing platform for drones which is made of solar panels, enabling multi-robot strategies and solar power storage, with a view to sustainable energy. In fact, the device will assume a central role in a more complex automated system for agriculture, that includes the use of UAV (unmanned aerial vehicle) and UGV for coordinated field monitoring and servicing. The electronics of the device is also discussed, since Agri.q should be ready to send-receive data to move autonomously or to be remotely controlled by means of dedicated processing units and transmitter-receiver modules. This paper collects all these elements and shows the advances of the previous works, describing the design process of the mechatronic system and showing the realization phase, whose outcome is the physical prototype.

show abstract

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Cited by 22 publications

References 37 publications

Automatic Parameter Tuning for Adaptive Thresholding in Fruit Detection

Automatic Parameter Tuning for Adaptive Thresholding in Fruit Detection

Detection and Classification of Root and Butt-Rot (RBR) in Stumps of Norway Spruce Using RGB Images and Machine Learning

Design of a UGV Powered by Solar Energy for Precision Agriculture

Contact Info

Product

Resources

About