Many CNN architectures have been developed, including AlexNet, GoogLeNet, VGGNet, and ResNet. Among these models, convolutional neural networks (CNN) are one of the most commonly applied. The emergence of deep learning technology has led to the development of many machine learning models for image recognition purposes. Furthermore, machine learning methods have poor robustness in complex scenes, and it is extremely difficult to transfer these methods from one kind of fruit to another.
However, most methods are complicated in design, have low-level abstraction, and are adapted only to certain specific conditions. The F1, recall, and precision scores were 92.15%, 94.41%, and 90.00%, respectively. A coarse-to-fine scanner was used for tomato detection, false color removal (FCR) to remove false-positive rejection, and non-maximum suppression (NMS) to merge overlapping results. The histograms of oriented gradients (HOG) method was used to train the support vector machine (SVM) classifier. employed an automatic tomato detection method for ordinary color images. The proposed method has an accuracy of 96.56%. used the AdaBoost framework and multiple color components obtained from the vision sensor to automatically identify clusters of ripe grapes on a farm. Based on the shape, texture, color properties, and Haar-like features of ordinary color images, the proposed algorithm has an accuracy of 96.5% when detecting ripe tomatoes. proposed the AdaBoost algorithm combined with the average pixel value (APV) for tomato fruit detection. Many machine learning methods have been proposed for fruit classification based on color detection, edge detection, etc. Thus, the development of AI technology has prompted significant interest in the potential for applying machine learning to computer vision tasks, such as harvesting, in agriculture. Moreover, as the detection algorithms are complicated and have many fixed thresholds, it is difficult to adapt them to other fruits and/or environments. However, the detection accuracy of such methods is heavily dependent on the illumination conditions. Conventional techniques rely mainly on color, texture, shape, and other shallow features of the image for detection. Many techniques have been developed for fruit detection over the last decade. Of the two steps, fruit detection is the most crucial, since it is vital that only the fruit which are ripe and ready for consumption are harvested, while the remainder are left on the branch or vine to mature. Robotic harvesting comprises two main steps: fruit detection using a computer vision system and fruit picking using a robot arm. However, with the development of artificial intelligence (AI), much of this work can now be performed by robots. Fruit harvesting is labor-intensive and time-consuming work.
0 kommentar(er)
