Accurate detection of pear flowers is an important measure for pear orchard yield estimation, which plays a vital role in improving pear yield and predicting pear price trends. This study proposed an improved YOLOv4 model called YOLO-PEFL model for accurate pear flower detection in the natural environment. Pear flower targets were artificially synthesized with pear flower’s surface features. The synthetic pear flower targets and the backgrounds of the original pear flower images were used as the inputs of the YOLO-PEFL model. ShuffleNetv2 embedded by the SENet (Squeeze-and-Excitation Networks) module replacing the original backbone network of the YOLOv4 model formed the backbone of the YOLO-PEFL model. The parameters of the YOLO-PEFL model were fine-tuned to change the size of the initial anchor frame. The experimental results showed that the average precision of the YOLO-PEFL model was 96.71%, the model size was reduced by about 80%, and the average detection speed was 0.027s. Compared with the YOLOv4 model and the YOLOv4-tiny model, the YOLO-PEFL model had better performance in model size, detection accuracy, and detection speed, which effectively reduced the model deployment cost and improved the model efficiency. It implied the proposed YOLO-PEFL model could accurately detect pear flowers with high efficiency in the natural environment.
Automatic transplanting of seedlings is of great significance to vegetable cultivation factories. Accurate and efficient identification of healthy seedlings is the fundamental process of automatic transplanting. This study proposed a computer vision-based identification framework of healthy seedlings. Vegetable seedlings were planted in trays in the form of potted seedlings. Two-color index operators were proposed for image preprocessing of potted seedlings. An optimal thresholding method based on the genetic algorithm and the three-dimensional block-matching algorithm (BM3D) was developed to denoise and segment the image of potted seedlings. The leaf area of the potted seedling was measured by machine vision technology to detect the growing status and position information of the potted seedling. Therefore, a smart identification framework of healthy vegetable seedlings (SIHVS) was constructed to identify healthy potted seedlings. By comparing the identification accuracy of 273 potted seedlings images, the identification accuracy of the proposed method is 94.33%, which is higher than 89.37% obtained by the comparison method.
With the development of the fruit farming industry, there have been breakthroughs in both scale and harvesting requirements, and the resulting problem is that the demand of picking robot is more and more high, the function, cost and quality of the harvest and picking efficiency compared with the traditional manual operation mode with strong competitiveness for market, that is to say, in terms of cost cheaper, picking at a faster rate, and can avoid damage on the fruit in the process of picking. Therefore, in terms of mechanical structure design, the transmission accuracy and efficiency of the picking robot should be improved. At the same time, the structural design of the picking robot should simplify the structure as much as possible, reduce the manufacturing cost, and ensure the feasibility of the picking robot’s functions. Picking robot combined with automatic walking system, automatic detection system and control system-centered intelligent system, can achieve accurate and efficient work in various conditions. Realize picking robot toward automation, intelligence, scientific development. The design of this topic is mainly aimed at the development of the picking robot and the use of analysis, determine the feasibility of the picking robot design and virtual simulation.
Line structured light systems have been widely applied in the measurement of various fields. Calibration has been a hot research topic as a vitally important process of the line structured light system. The accurate calibration directly affects the measurement result of the line structured light system. However, the external environment factors, such as uneven illumination and uncertain light stripe width, can easily lead to an inaccurate extraction of light stripe center, which will affect the accuracy of the calibration. An image analysis-based framework in the calibration process was proposed for the line structure light system in this paper. A three-dimensional (3D) vision model of line structure light system was constructed. An image filtering model was established to equalize the uneven illumination of light stripe image. After segmenting the stripe image, an adaptive window was developed, and the width of the light stripe was estimated by sliding the window over the light stripe image. The light stripe center was calculated using the gray centroid method. The light plane was fitted based on the calibration points coordinates acquired by the camera system. In the measurement experiment of standard gauge block width, the maximum and minimum average deviations of 0.021 pixels and 0.008 pixels and the maximum and minimum absolute deviations of 0.023 pixels and 0.009 pixels could be obtained by using the proposed method, which implies the accuracy of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.