Abstract
Fast and accurate detection of ripe tomatoes on plant, which replaces manual labor with a robotic vision-based harvesting system, is a challenging task. Tomatoes in adjacent positions are easily mistaken as a single tomato by image recognition methods. In this study, a ripe tomato detection method that combines deep learning with edge contour detection is proposed. Our approach efficiently separates target tomatoes from overlapping tomatoes to detect individual fruits. This approach yields several improvements. First, deep learning requires less time and extracts deeper features than traditional methods for assessing candidate ripe tomato regions. Second, we use Gaussian density function of H and S in the HSV color space to help segment tomato regions from the background, followed by erosion and dilation on the tomato body to separate adjacent tomatoes and remove peripheral subpixels from all detected ripe tomatoes. Third, an adaptive threshold intuitionistic fuzzy set (IFS) method was developed to identify the tomato's edge, and it performs well in detecting blurred edges in overlapping regions. To improve the efficiency and stability of edge detection under natural conditions, we adopted an illumination adjustment algorithm for the tomato image before edge detection. As samples, we collected images showing tomatoes that were separated, adjacent, overlapped, and even shaded by leaves. The widths and heights of these tomato samples were calculated and analyzed to evaluate the detection performance of the proposed method. The root mean square error (RMSE) results for tomato width and height using the proposed method are 2.996 pixels and 3.306 pixels, respectively. The mean relative error percent (MRE%) values for horizontal and vertical center position shift are 0.261% and 1.179%, respectively. These results demonstrate that the proposed method improves tomato detection accuracy and that it can be further applied in the harvesting process of agricultural robots.
Highlights
In Section III.B, the contour segmentation processes of tomatoes in four different states were described to show the applicability of our proposed method for tomato segmentation
The results showed that the trained Faster R-CNN classifier can accurately and quickly localize candidate ripe tomato regions
Different tomato samples were segmented manually and used to establish the Gaussian density function to remove the background from single tomatoes detected by Faster R-CNN to obtain the candidate tomato body
Summary
Tomatoes offer humans many essential and beneficial nutrients such as antioxidants and vitamins C and A. Manual harvesting is time consuming and costly, and as China’s labor costs. Rise, the adoption of agricultural automation processes is inevitable. Such processes are of great significance for reducing agriculture labor costs and improving a country’s industrial structure. It is necessary to develop automatic tomato pickers. Most agricultural robots— fruit harvesting systems in particular—use computer vision to detect fruit targets, accurate fruit detection is a challenging research topic. It is difficult to develop a vision system that functions as intelligently as a human and can identify fruit, especially in the presence of overlapping fruits or large leaf occlusions.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
