Camera Coordinate Research Articles

Development of an in-situ real-time laser targeting algorithm for a 3D LiDAR-integrated galvanometric laser scanner system

A Galvanometric laser scanner utilizes mirrors attached to dual galvanometers to direct laser beams. GLS systems are widely employed across various industrial sectors due to their compact size, high resolution, and high positional repeatability. Extensive research has been conducted to calibrate these systems to steer lasers to desired positions accurately. However, much of this research has traditionally focused on fixed working distances, which does not align well with the portable capabilities that GLS systems offer in non-destructive evaluation fields. This study explores an algorithm that enables real-time laser targeting using a 3D LiDAR camera integrated into a GLS system. The research involved developing and calculating a projection matrix that projects 3D camera coordinates into 2D bit coordinates input to each galvanometer, based on linear assumptions. To address the non-linear errors that emerge from the linear assumption process, compensation was applied through 3rd-order regression and Artificial neural networks. As a result, the algorithm facilitated highly accurate laser targeting within a range of 0.5 m to 2.5 m based on coordinates acquired by the LiDAR camera.

DDGPnP: Differential degree graph based PnP solution to handle outliers

Existing external relationships for outlier removal in the perspective-n-point problem are generally spatial coherence among the neighbor correspondences. In the situation of high noise or spatially incoherent distributions, pose estimation is relatively inaccurate due to a small number of detected inliers. To address these problems, this paper explores the globally coherent external relationships for outlier removal and pose estimation. To this end, the differential degree graph (DDG) is proposed to employ the intersection angles between rays of correspondences to handle outliers. Firstly, a pair of two degree graphs are constructed to establish the external relationships between 3D-2D correspondences in the world and camera coordinates. Secondly, the DDG is estimated through subtracting the two degree graphs and operating binary operation with a degree threshold. Besides, this paper mathematically proves that the maximum clique of the DDG represents the inliers. Thirdly, a novel vertice degree based method is put forward to extract the maximum clique from DDG for outlier removal. Besides, this paper proposes a novel pipeline of DDG based PnP solution, i.e. DDGPnP, to achieve accurate pose estimation. Experiments demonstrate the superiority and effectiveness of the proposed method in the aspects of outlier removal and pose estimation by comparison with the state of the arts. Especially for the high noise situation, the DDGPnP method can achieve not only accurate pose but also a large number of correct correspondences.

Implicit calibration method for underwater stereo cameras

Underwater stereo cameras can effectively capture intricate environments with restricted accessibility, offering an appealing solution for precise perception. Stereo imaging is however susceptible to distortions caused by the refraction of incoming rays. These distortions are nonlinear and challenge the standard single viewpoint projection assumption. In this paper, we propose a data-driven implicit calibration method for underwater stereo cameras. To address the imaging characteristics and aberration distributions across different coordinates of underwater stereo cameras, we have developed the corresponding coordinates regression network and fusion strategy, thereby converting the calibration process into network-based learning. Secondly, we designed an underwater self-luminous calibration target system and the underwater corner point extraction strategy for sample dataset acquisition. We evaluated the proposed method comprehensively in terms of measurement, camera posture estimation, and 3D reconstruction, and compared it with other explicit calibration methods. The experimental results show that the proposed implicit calibration method is superior to other explicit calibration. We demonstrate with real experiments that our method enables efficient camera calibration for underwater vision applications.

Multi-Object Tracking Model Based on Detection Tracking Paradigm in Panoramic Scenes

Multi-Object Tracking (MOT) technology is dedicated to continuously tracking multiple targets of interest in a sequence of images and accurately identifying their specific positions at different times. This technology is crucial in key application areas such as autonomous driving and security surveillance. However, the application process often requires the coordination of cameras from multiple angles for tracking. Directly studying Multi-Object Tracking algorithms in panoramic scenes is an effective way to address this issue. The uniqueness of panoramic scenes causes target position changes at the boundaries and tracking difficulties due to continuous changes in target scales. To ensure the accuracy of target tracking, this study explores a detection-based tracking method using the newly improved YOLOx detector and the adjusted DeepSORT algorithm. Firstly, YOLOx_s was chosen as the detector because its simple network structure ensures a fast computational speed. During the feature extraction stage, we used the Polarized Self-Attention (PSA) mechanism to capture more feature information, thereby improving the tracking performance on small-scale targets. Secondly, the tracker was improved by adding a camera motion compensation module before predicting the target’s position to mitigate the impact of camera shake on tracking. Finally, to address the difficulty of continuously tracking targets in specific areas of panoramic scenes, this study proposes specific tracking strategies. These strategies effectively resolve the problem of tracking failure caused by target position changes at the boundaries. Experimental results show that improved algorithms have a superior performance on multiple evaluation metrics compared to other algorithms in the field. Compared to the original algorithm, the improved algorithm exhibits a 6% increase in the quantitative metric MOTA, a 7% increase in IDF1, and a 40% decrease in IDSWs, demonstrating its leading performance.

Structure-aware neural radiance fields without posed camera

The neural radiance fields (NeRF) for realistic novel view synthesis require camera poses to be pre-acquired by a structure-from-motion (SfM) approach. This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis. We integrate pose extraction and view synthesis into a jointly optimized process so that they can benefit from each other. For network training, only images are given without pre-known camera poses. The camera poses are obtained by the depth-consistent constraint in which the identical feature in different views has the same world coordinates transformed from the local camera coordinates according to the extracted poses. The depth-consistent constraint is jointly optimized with the pixel color constraint. The poses are represented by a CNN-based deep network, whose input is the related frames. This joint optimization enables NeRF to be aware of the scene’s structure, resulting in improved generalization performance. Experiments on three datasets demonstrate the effectiveness of camera pose estimation and novel view synthesis. Code is available at https://github.com/XTU-PR-LAB/SaNerf.

EPMF: Efficient Perception-Aware Multi-Sensor Fusion for 3D Semantic Segmentation.

We study multi-sensor fusion for 3D semantic segmentation that is important to scene understanding for many applications, such as autonomous driving and robotics. For example, for autonomous cars equipped with RGB cameras and LiDAR, it is crucial to fuse complementary information from different sensors for robust and accurate segmentation. Existing fusion-based methods, however, may not achieve promising performance due to the vast difference between the two modalities. In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) to effectively exploit perceptual information from two modalities, namely, appearance information from RGB images and spatio-depth information from point clouds. To this end, we first project point clouds to the camera coordinate using perspective projection. In this way, we can process both inputs from LiDAR and cameras in 2D space while preventing the information loss of RGB images. Then, we propose a two-stream network that consists of a LiDAR stream and a camera stream to extract features from the two modalities, separately. The extracted features are fused by effective residual-based fusion modules. Moreover, we introduce additional perception-aware losses to measure the perceptual difference between the two modalities. Last, we propose an improved version of PMF,i.e., EPMF, which is more efficient and effective by optimizing data pre-processing and network architecture under perspective projection. Specifically, we propose cross-modal alignment and cropping to obtain tight inputs and reduce unnecessary computational costs. We then explore more efficient contextual modules under perspective projection and fuse the LiDAR features into the camera stream to boost the performance of the two-stream network. Extensive experiments on benchmark data sets show the superiority of our method. For example, on nuScenes test set, our EPMF outperforms the state-of-the-art method,i.e., RangeFormer, by 0.9% in mIoU. Compared to PMF, EPMF also achieves 2.06× acceleration with 2.0% improvement in mIoU. Our source code is available at https://github.com/ICEORY/PMF.

Research on the Relative Position Detection Method between Orchard Robots and Fruit Tree Rows.

The relative position of the orchard robot to the rows of fruit trees is an important parameter for achieving autonomous navigation. The current methods for estimating the position parameters between rows of orchard robots obtain low parameter accuracy. To address this problem, this paper proposes a machine vision-based method for detecting the relative position of orchard robots and fruit tree rows. First, the fruit tree trunk is identified based on the improved YOLOv4 model; second, the camera coordinates of the tree trunk are calculated using the principle of binocular camera triangulation, and the ground projection coordinates of the tree trunk are obtained through coordinate conversion; finally, the midpoints of the projection coordinates of different sides are combined, the navigation path is obtained by linear fitting with the least squares method, and the position parameters of the orchard robot are obtained through calculation. The experimental results show that the average accuracy and average recall rate of the improved YOLOv4 model for fruit tree trunk detection are 5.92% and 7.91% higher, respectively, than those of the original YOLOv4 model. The average errors of heading angle and lateral deviation estimates obtained based on the method in this paper are 0.57° and 0.02 m. The method can accurately calculate heading angle and lateral deviation values at different positions between rows and provide a reference for the autonomous visual navigation of orchard robots.

Robot manipulator visual servoing based on image moments and improved firefly optimization algorithm-based extreme learning machine

We propose an improved extreme learning machine (ELM) to solve the decoupling problem between the camera coordinates and the image moment features for robot manipulator image-based visual servoing system, that is, determine the nonlinear relationship between them. First, an improved firefly optimization algorithm (IFOA) based on an adaptive inertial weight and individual variations is proposed. Then, the IFOA is optimized the weight and hidden bias in ELM algorithm; this improves the training accuracy of the ELM. Finally, the improved firefly optimization algorithm is integrated into ELM (IFOA-ELM) to solve the decoupling problem and ensure stable performance. The results of experiment show that the estimated error of the rotation angle around the camera frame in the visual servoing system determined by the IFOA-ELM algorithm is less than 0.25°, confirming that the proposed algorithm exhibits good robustness and stability.

An improved camera model for oblique-viewing laparoscopes: high reprojection accuracy independent of telescope rotation

Objective. Oblique-viewing laparoscopes are popular in laparoscopic surgeries where the target anatomy is located in narrow areas. Their viewing direction can be shifted by telescope rotation without changing the laparoscope pose. This rotation also changes laparoscope camera parameters that are estimated by camera calibration to be able to reproject an anatomical model onto the laparoscopic view, creating augmented reality (AR). The aim of this study was to develop a camera model that accounts for these changes, achieving high reprojection accuracy for any telescope rotation. Approach. Camera parameters were acquired by calibrations encompassing a wide telescope rotation range. For those parameters showing periodic changes upon rotation, interpolation models were created and used to establish an updatable camera model. With this model, corner points of a tracked checkerboard were reprojected onto the checkerboard laparoscopic images, at random rotation angles. Root-mean-square reprojection errors (RMSEs) were calculated between the reprojected and imaged corner points. Main results. Reprojection RMSEs were low and approximately independent on telescope rotation angle, over a wide rotation range of 320°. The mean reprojection RMSE was 2.8 0.7 pixels for a conventional laparoscope and 3.6 0.7 pixels for a chip-on-the-tip (COTT) laparoscope, corresponding to 0.3 0.1 mm and 0.4 0.1 mm in world coordinates respectively. Worst-case reprojection errors were about 9 pixels (0.8 mm) for both laparoscopes. Significance. The camera model developed in this study improves on existing models for oblique-viewing laparoscopes because it provides high reprojection accuracy independent of the telescope rotation angle and is applicable for conventional and chip-on-a-tip oblique-viewing laparoscopes. The work presented here is an important step towards creating accurate AR in image-guided interventions where oblique-viewing laparoscopes are used while simultaneously providing the surgeon the flexibility to rotate the telescope to any desired rotation angle. Acronyms. CC: camera coordinates; CCToolbox: camera calibration toolbox; COTT: chip-on-the-tip; CS: camera sensor; DD: decentering distortion; FL: focal length; OTS: optical tracking system; PP: principal point; RD: radial distortion; SI: supplementary information; hand-eye translation component

RGB-D 데이터를 이용한 비전 기반 로봇 간 상대 위치 및 자세 추정 기법 연구

In this paper, a vision-based robot-to-robot relative pose estimation method is proposed for markerless wheeled mobile robots using an RGB-D camera. The proposed method comprises three parts: (i) object detection using a machine vision technique with RGB data, (ii) relative position estimation averaging over the point cloud with outlier rejection, and (iii) relative orientation estimation using point cloud scan matching through iterative closest point (ICP) methods. The neighboring or target robots are detected using YOLOv3-tiny so that the position of the robot can be determined in pixel coordinates. To estimate the 3D position of the target robot in the camera coordinates of the ego-robot, the object detection results are used along with the depth information and the precalibrated pinhole camera model. To estimate the orientation of the target robot, a point cloud is generated using the depth image, downsampled, and then used for scan matching by using ICP methods. For experimental verification, the proposed relative pose estimation method was implemented as a robot operating system package and tested on a small-scale differential-driving wheeled mobile robot, TurtleBot3; the estimation results were compared with the ground truth in real-world environments.

Simple and precise calibration of the line-structured light vision system using a planar target.

When calibrating a line-structured light vision system using a planar target, noise easily affects the solution of the coordinates of light stripe points at the camera coordinate frame. Therefore, the planar target must be placed in the measurement space many times to capture more target images for improving calibration stability and achieving relatively high calibration accuracy. This complicates the calibration process. This paper proposes a calibration method considering the measurement baselines of a planar target. The planar target is placed only two times, and two target images are captured correspondingly. A three-point subset is made up of the two calibration points that form the measurement baseline with the longest 2D projection and any other calibration point. In this way, it is less affected by noise when using the three-point subsets to establish the equations. Then, we use the lengths of the measurement baselines provided by all three-point subsets and their 2D projections to solve the coordinates of light stripe points at the camera coordinate frame more accurately to calibrate the line-structured light vision system. Both the simulation and actual experiment results demonstrate the feasibility of our method. Based on our calibration method, the RMS error is 0.035mm for length measurement and 0.054mm for height measurement. Compared with other existing methods, our method needs only two target images. It can also achieve more accurate calibration results than the other methods. In addition, our calibration method increases the applicability of the line-structured light measurement method by reducing the number of target swings.

Influence of On-Site Camera Calibration with Sub-Block of Images on the Accuracy of Spatial Data Obtained by PPK-Based UAS Photogrammetry

Unmanned Aerial Systems (UAS) Photogrammetry has become widely used for spatial data acquisition. Nowadays, RTK (Real Time Kinematic) and PPK (Post Processed Kinematic) are the main correction methods for accurate positioning used for direct measurements of camera station coordinates in UAS imagery. Thus, 3D camera coordinates are commonly used as additional observations in Bundle Block Adjustment to perform Global Navigation Satellite System-Assisted Aerial Triangulation (GNSS-AAT). This process requires accurate Interior Orientation Parameters to ensure the quality of photogrammetric intersection. Therefore, this study investigates the influence of on-site camera calibration with a sub-block of images on the accuracy of spatial data obtained by PPK-based UAS Photogrammetry. For this purpose, experiments of on-the-job camera self-calibration in the Metashape software with the SfM approach were performed. Afterward, experiments of GNSS-Assisted Aerial Triangulation with on-site calibration in the Erdas Imagine software were performed. The outcomes show that only the experiment of GNSS-AAT with three Ground Control Points yielded horizontal and vertical accuracies close to nominal precisions of the camera station positions by GNSS-PPK measurements adopted in this study, showing horizontal RMSE (Root-Mean Square Error) of 0.222 m and vertical RMSE of 0.154 m. Furthermore, the on-site camera calibration with a sub-block of images significantly improved the vertical accuracy of the spatial information extraction.

Wheelchair-Centered Omnidirectional Gaze-Point Estimation in the Wild

In this article, we propose a dataset named Wheelchair-OmniGaze and a method of estimating the gaze point of a wheelchair user that can cope with large head motion as the first step for understanding the intention of a wheelchair user. In the proposed method, the wheelchair user's face is observed by two remote cameras, called face cameras, mounted on the two front sides of the wheelchair, while a spherical camera with a 360° field of view, called a spherical scene camera, is mounted to the top rear to observe the surrounding scenes. A user's gaze point at the environment is determined by combining the facial information acquired by the face cameras with the spherical image acquired by the spherical scene camera. Concretely, a convolutional neural network–long short-term memory network is used to learn gaze points of the spherical image from the two face image sequences. Using two face cameras enables a user's face to be observed even for a large head motion. Using a spherical scene camera mounted on a wheelchair, the representation of a user's gaze points at a wheelchair-centered spherical camera coordinate can be obtained, which is independent of a user's head motion. The experimental results show that our method achieved competitive performance in comparison with the state-of-the-art method. Since our problem definition is different from the existing research, the experimental results of this article can be seen as a baseline for our built dataset.

Research on Calibration Method of Line-Structured Light Based on Multiple Geometric Constraints

Line-structured light calibration is an important step in the process of the visual measurement of structured light, and in the calibration process, the light plane equation is fitted by the camera coordinates of the data points on the light plane. There is error in solving the spatial coordinates of the data points, and the existing methods generally cannot effectively find the deviation points in the fitted data points, which leads to deviation when solving the parameters of the light plane equation. To correct the error caused by the deviation point in the calibration, this paper established a calibration method based on geometric constraints. In the method, the first constraint was that all fit points involved in the fitting had a certain consistency, and a part of the error points could be filtered by the distance from the data point to the light plane. In order to further improve the calibration accuracy, the laser was moved on a linear guide, the optimized objective function was established by the second geometric constraint, and the constraint was the relationship that the light plane at each position was parallel. In the experiment, a high-precision gauge block was used as the measured object, and the measurement results could be obtained. The calibration method can improve the calibration accuracy according to the experimental results.

A low-cost indoor positioning system based on data-driven modeling for robotics research and education

AbstractThis paper presents a low-cost, accurate indoor positioning system that integrates image acquisition and processing and data-driven modeling algorithms for robotics research and education. Multiple overhead cameras are used to obtain normalized image coordinates of ArUco markers, and a new procedure is developed to convert them to the camera coordinate frame. Various data-driven models are proposed to establish a mapping relationship between the camera and the world coordinates. One hundred fifty data pairs in the camera and world coordinates are generated by measuring the ArUco marker at different locations and then used to train and test the data-driven models. With the model, the world coordinate values of the ArUco marker and its robot carrier can be determined in real time. Through comparison, it is found that a straightforward polynomial regression outperforms the other methods and achieves a positioning accuracy of about 1.5 cm. Experiments are also carried out to evaluate its feasibility for use in robot control. The developed system (both hardware and algorithms) is shared as an open source and is anticipated to contribute to robotic studies and education in resource-limited environments and underdeveloped regions.

A unified calibration method of 3D laser profile measurement with different of laser-line lengths

PurposeExisting calibration methods mainly focus on the camera laser-plane calibration of a single laser-line length, which is not convenient and cannot guarantee the consistency of the results when several three-dimensional (3D) scanners are involved. Thus, this study aims to provide a unified step for different laser-line length calibration requirements for laser profile measurement (LPM) systems.Design/methodology/approach3D LPM is the process of converting physical objects into 3D digital models, wherein camera laser-plane calibration is critical for ensuring system precision. However, conventional calibration methods for 3D LPM typically use a calibration target to calibrate the system for a single laser-line length, which needs multiple calibration patterns and makes the procedure complicated. In this paper, a unified calibration method was proposed to automatically calibrate the camera laser-plane parameters for the LPM systems with different laser-line lengths. The authors designed an elaborate planar calibration target with different-sized rings that mounted on a motorized linear platform to calculate the laser-plane parameters of the LPM systems. Then, the camera coordinates of the control points are obtained using the intersection line between the laser line and the planar target. With a new proposed error correction model, the errors caused by hardware assembly can be corrected. To validate the proposed method, three LPM devices with different laser-line lengths are used to verify the proposed system. Experimental results show that the proposed method can calibrate the LPM systems with different laser-line lengths conveniently with standard steps.FindingsThe repeatability and accuracy of the proposed calibration prototypes were evaluated with high-precision workpieces. The experiments have shown that the proposed method is highly adaptive and can automatically calibrate the LPM system with different laser-line lengths with high accuracy.Research limitations/implicationsIn the repeatability experiments, there were errors in the measured heights of the test workpieces, and this is because the laser emitter had the best working distance and laser-line length.Practical implicationsBy using this proposed method and device, the calibration of the 3D scanning laser device can be done in an automatic way.Social implicationsThe calibration efficiency of a laser camera device is increased.Originality/valueThe authors proposed a unified calibration method for LPM systems with different laser-line lengths that consist of a motorized linear joint and a calibration target with elaborately designed ring patterns; the authors realized the automatic parameter calibration.

Dual Networks Based 3D Multi-Person Pose Estimation From Monocular Video.

Monocular 3D human pose estimation has made progress in recent years. Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.e., the coordinates based on the center of the target person. Hence, these methods are inapplicable for multi-person 3D pose estimation, where the absolute coordinates (e.g., the camera coordinates) are required. Moreover, multi-person pose estimation is more challenging than single pose estimation, due to inter-person occlusion and close human interactions. Existing top-down multi-person methods rely on human detection (i.e., top-down approach), and thus suffer from the detection errors and cannot produce reliable pose estimation in multi-person scenes. Meanwhile, existing bottom-up methods that do not use human detection are not affected by detection errors, but since they process all persons in a scene at once, they are prone to errors, particularly for persons in small scales. To address all these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. To address the common gaps between training and testing data, we do optimization during the test time, by refining the estimated 3D human poses using high-order temporal constraint, re-projection loss, and bone length regularizations. We also introduce a two-person pose discriminator that enforces natural two-person interactions. Finally, we apply a semi-supervised method to overcome the 3D ground-truth data scarcity. Our evaluations demonstrate the effectiveness of the proposed method and its individual components. Our code and pretrained models are available publicly: https://github.com/3dpose/3D-Multi-Person-Pose.

IFKD: Implicit field knowledge distillation for single view reconstruction.

In 3D reconstruction tasks, camera parameter matrix estimation is usually used to present the single view of an object, which is not necessary when mapping the 3D point to 2D image. The single view reconstruction task should care more about the quality of reconstruction instead of the alignment. So in this paper, we propose an implicit field knowledge distillation model (IFKD) to reconstruct 3D objects from the single view. Transformations are performed on 3D points instead of the camera and keep the camera coordinate identified with the world coordinate, so that the extrinsic matrix can be omitted. Besides, a knowledge distillation structure from 3D voxel to the feature vector is established to further refine the feature description of 3D objects. Thus, the details of a 3D model can be better captured by the proposed model. This paper adopts ShapeNet Core dataset to verify the effectiveness of the IFKD model. Experiments show that IFKD has strong advantages in IOU and other core indicators compared with the camera matrix estimation methods, which verifies the feasibility of the new proposed mapping method.

A Three-Dimensional Structured Light Vision System by Using a Combination of Single-Line and Three-Line Lasers

A multi-line structured light measurement method that combines a single-line and a three-line laser, in which precision sliding rails and displacement measurement equipment are not required, is proposed in this paper. During the measurement, the single-line structured light projects onto the surface of an object and the three-line structured light remains fixed. The single-line laser is moved and intersects with the three-line laser to form three intersection points. The single-line light plane can be solved using the camera coordinates of three intersection points, thus completing the real-time calibration of the scanned light plane. The single-line laser can be scanned at any angle to determine the overall complete three-dimensional (3D) shape of the object during the process. Experimental results show that this method overcomes the difficulty of obtaining information about certain angles and locations and can effectively recover the 3D shape of the object. The measurement system's repetition error is under 0.16 mm, which is sufficient to measure the 3D shapes of complicated workpieces.

Automatic Brix Measurement for Watermelon Breeding

Sweetness or sugar content, represented by soluble solids contents (SSC), is a vital quality trait in watermelon breeding which can be assessed by the refractive index method. However, sampling watermelon juice out of the pulp is a process that is both labor-intensive and error-prone. In this study, we developed an automatic SSC measurement system for watermelon breeding to improve efficiency and decrease costs. First, we built an automatic cutting system to cut watermelons into precise halves, in which a laser rangefinder is used to measure the distance from the upper surface of the watermelon to itself, and thus, the diameter is estimated. The experiments showed a high correlation between the estimated diameters and the ground truths, with and . Then, we built an automatic Brix measurement system to obtain the Brix data from a central point on the watermelon’s section, where an image analysis procedure is applied to locate the testing point. This is then transformed to the camera coordination system, and a refractometer is driven by a 3-axis robotic arm to reach the testing point. Brix measurement experiments were conducted using three vertical gaps and four lateral gaps between the probe of the refractometer and the pulp. The result showed that the best parameters were a vertical gap of 4 mm and a lateral gap of 2 mm. The average accuracy reached 98.74%, which indicates that this study has the potential to support watermelon breeding research.