Search results

Laser-based measurement techniques offer various advantages over conventional measurement techniques, such as no-destructive, no-contact, fast and long measuring distance. In cooperative laser ranging systems, it’s crucial to extract center coordinates of retroreflectors to accomplish automatic measurement. To solve this problem, this paper aims to propose a novel method.

We propose a method using Mask RCNN (Region Convolutional Neural Network), with ResNet101 (Residual Network 101) and FPN (Feature Pyramid Network) as the backbone, to localize retroreflectors, realizing automatic recognition in different backgrounds. Compared with two other deep learning algorithms, experiments show that the recognition rate of Mask RCNN is better especially for small-scale targets. Based on this, an ellipse detection algorithm is introduced to obtain the ellipses of retroreflectors from recognized target areas. The center coordinates of retroreflectors in the camera coordinate system are obtained by using a mathematics method.

To verify the accuracy of this method, an experiment was carried out: the distance between two retroreflectors with a known distance of 1,000.109 mm was measured, with 2.596 mm root-mean-squar error, meeting the requirements of the coarse location of retroreflectors.

The research limitations/implications are as follows: (i) As the data set only has 200 pictures, although we have used some data augmentation methods such as rotating, mirroring and cropping, there is still room for improvement in the generalization ability of detection. (ii) The ellipse detection algorithm needs to work in relatively dark conditions, as the retroreflector is made of stainless steel, which easily reflects light.

The originality/value of the article lies in being able to obtain center coordinates of multiple retroreflectors automatically even in a cluttered background; being able to recognize retroreflectors with different sizes, especially for small targets; meeting the recognition requirement of multiple targets in a large field of view and obtaining 3 D centers of targets by monocular model-based vision.

Picking up pistons in arbitrary poses is an important step on car engine assembly line. The authors usually use vision system to estimate the pose of the pistons and then guide a stable grasp. However, a piston in some poses, e.g. the mouth of the piston faces forward, is hardly to be directly grasped by the gripper. Thus, we need to reorient the piston to achieve a desired pose, i.e. let its mouth face upward, for grasping.

This paper aims to present a vision-based picking system that can grasp pistons in arbitrary poses. The whole picking process is divided into two stages. At localization stage, a hierarchical approach is proposed to estimate the piston’s pose from image which usually involves both heavy noise and edge distortions. At grasping stage, multi-step robotic manipulations are designed to enable the piston to follow a nominal trajectory to reach to the minimum of the distance between the piston’s center and the support plane. That is, under the design input, the piston would be pushed to achieve a desired orientation.

A target piston in arbitrary poses would be picked from the conveyor belt by the gripper with the proposed method.

The designed robotic bin-picking system using vision is an advantage in terms of flexibility in automobile manufacturing industry.

The authors develop a methodology that uses a pneumatic gripper and 2D vision information for picking up multiple pistons in arbitrary poses. The rough pose of the parts are detected based on a hierarchical approach for detection of multiple ellipses in the environment that usually involve edge distortions. The pose uncertainties of the piston are eliminated by multi-step robotic manipulations.

The purpose of this paper is to provide crystal size distribution (CSD) using photogrammetric and image analysis techniques. A new algorithm is proposed to detect CSDs and a comparison is carried out with conventional watershed segmentation algorithm.

Polished granite plates were prepared to designate the metrics of CSD measurements. There are many important metrics for measurements on CSD. Some of them are orientation, size, position, area, aspect ratio, convexity, circularity, perimeter, convex hull, bounding box, eccentricity, shape, max-min length of CSD's fitted and corrected ellipse, and population density in a per unit area. Prior to image processing stage, camera calibration was performed to remove the image distortion errors. Image processing techniques were applied to corrected images for detecting the CSD parameters.

The proposed algorithm showed the improved preservation of size and shape characteristics of the crystal material when compared to the watershed segmentation. According to the experimental results, proposed algorithm revealed promising results in identifying CSDs more easily and efficiently.

This paper describes CSD of granitic rocks by using automated grain boundary detection methods in polished plate images. Some metrics of CSDs were detected by employing a new procedure. A computer-based image analysis technique was developed to measure the CSDs on the granitic rock plates. A validation is done by superimposing digitally detected CSD metrics to original samples.

Wheeled mobile robots (WMR) are the most widely used robots. Avoiding obstacles in unstructured environments, especially dynamic obstacles such as pedestrians, is a serious challenge for WMR. This paper aims to present a hybrid obstacle avoidance method that combines an informed-rapidly exploring random tree* algorithm with a three-dimensional (3D)-object detection approach and model prediction controller (MPC) to conduct obstacle perception, collision-free path planning and obstacle avoidance for WMR in unstructured environments.

Given a reference orientation and speed, the hybrid method uses parametric ellipses to represent obstacle expansion boundaries based on the 3D target detection results, and a collision-free reference path is planned. Then, the authors build on a model predictive control for tracking the collision-free reference path by incorporating the distance between the robot and obstacles. The proposed framework is a mapless method for WMR.

The authors present experimental results with a mobile robot for obstacle avoidance in indoor environments crowded with obstacles, such as chairs and pedestrians. The results show that the proposed hybrid obstacle avoidance method can satisfy the application requirements of mobile robots in unstructured environments.

In this study, the parameter ellipse is used to represent the area occupied by the obstacle, which takes the velocity as the parameter. Therefore, the motion direction and position of dynamic obstacles can be considered in the planning stage, which enhances the success rate of obstacle avoidance. In addition, the distance between the obstacle and robot is increased in the MPC optimization function to ensure a safe distance between the robot and the obstacle.

Collision avoidance is considered as a crucial issue in mobile robotic navigation to guarantee the safety of robots as well as working surroundings, especially for humans. Therefore, the position and velocity of obstacles appearing in the working space of the self-driving mobile robot should be observed to help the robot predict the collision and choose traversable directions. This paper aims to propose a new approach for obstacle tracking, dubbed MoDeT.

First, all long lines, such as walls, are extracted from the 2D-laser scan and considered as static obstacles (or mapped obstacles). Second, a density-based procedure is implemented to cluster nonwall obstacles. These clusters are then geometrically fitted as ellipses. Finally, the combination of Kalman filter and global nearest-neighbor (GNN) method is used to track obstacles’ position and velocity.

The proposed method (MoDeT) is experimentally verified by using an autonomous mobile robot (AMR) named AMR SR300. The MoDeT is found to provide better performance in comparison with previous methods for self-driving mobile robots.

The robot can only see a part of the object, depending on the light detection and ranging scan view. As a consequence, geometrical features of the obstacle are sometimes changed, especially when the robot is moving fast.

This proposed method is to serve the navigation and path planning for the AMR.

(a) Proposing an extended weighted line extractor, (b) proposing a density-based obstacle detection and (c) implementing a combination of methods [in (a) and (b) constant acceleration Kalman and GNN] to obtain obstacles’ properties.

An interactive processing scheme is proposed to improve the target detection probability as well as the tracking performance of the radar system.

Firstly, with the spatial-correlated features extracted from the foreground and background statistical models, the thresholds were adapted to distinguish the dim small targets from clutters in the complex incoherent radar images. Then, the target trajectories were constructed with the target tracking algorithm. According to the temporal correlation with the target life cycle, the thresholding values were modified in the neighbourhood of the predicted positions to improve the detection sensitivity in these areas during the tracking process. Finally, the temporal-correlated features of the remained clutters were used to further reduce the false alarm rate.

The proposed algorithm was applied on the simulated data, as well as the image sequences obtained with the incoherent marine radars. The detection results demonstrated that the interactive algorithm could detect and track the dim small targets with relatively low false alarm rate.

The interactive processing scheme could be applied for low-altitude airspace surveillance with incoherent marine radar.

The proposed scheme outperforms the classical radar target detection algorithms and the state-of-the-art image processing algorithms for video-based surveillance.

This paper aims to study six degrees-of-freedom (6DOF) pose measurement of reflective metal casts by machine vision, analyze the problems existing in the positioning of metal casts by stereo vision sensor in unstructured environment and put forward the visual positioning and grasping strategy that can be used in industrial robot cell.

A multikeypoints detection network Binocular Attention Hourglass Net is constructed, which can complete the two-dimensional positioning of the left and right cameras of the stereo vision system at the same time and provide reconstruction information for three-dimensional pose measurement. Generate adversarial networks is introduced to enhance the image of local feature area of object surface, and the three-dimensional pose measurement of object is completed by combining RANSAC ellipse fitting algorithm and triangulation method.

The proposed method realizes the high-precision 6DOF positioning and grasping of reflective metal casts by industrial robots; it has been applied in many fields and solves the problem of difficult visual measurement of reflective casts. The experimental results show that the system exhibits superior recognition performance, which meets the requirements of the grasping task.

Because of the chosen research approach, the research results may lack generalizability. The proposed method is more suitable for objects with plane positioning features.

This paper realizes the 6DOF pose measurement of reflective casts by vision system, and solves the problem of positioning and grasping such objects by industrial robot.

Laser absolute distance measurement has the characteristics of high precision, wide range and non-contact. In laser ranging system, tracking and aiming measurement point is the precondition of automatic measurement. To solve this problem, this paper aims to propose a novel method.

For the central point of the hollow angle coupled mirror, this paper proposes a method based on correlation filtering and ellipse fitting. For non-cooperative target points, this paper proposes an extraction method based on correlation filtering and feature matching. Finally, a visual tracking and aiming system was constructed by combining the two-axis turntable, and experiments were carried out.

The target tracking algorithm has an accuracy of 91.15% and a speed of 19.5 frames per second. The algorithm can adapt to the change of target scale and short-term occlusion. The mean error and standard deviation of the center point extraction of the hollow Angle coupling mirror are 0.20 and 0.09 mm. The mean error and standard deviation of feature points matching for non-cooperative target were 0.06 mm and 0.16 mm. The visual tracking and aiming system can track a target running at a speed of 0.7 m/s, aiming error mean is 1.74 pixels and standard deviation is 0.67 pixel.

The results show that this method can achieve fast and high precision target tracking and aiming and has great application value in laser ranging.

When simulating the behaviour of granular assemblies and multi‐body systems using a discrete element analysis, the shape representation of the bodies and the contact detection algorithm greatly influence the flexibility, accuracy and efficiency of the simulation. Several geometrical shape descriptors of two and three dimensional arbitrary rigid bodies are reviewed and a flexible 3‐D descriptor introduced. The aim is to identify appropriate shape descriptors which allow a variety of types of bodies to be investigated while ensuring accurate and efficient detection of inter‐particle contacts. Polygons/polyhedrons, and continuous and discrete function representations are examined. The investigation favours discrete representations due to their efficiency and flexibility, but illustrates the elegance and efficiency of using a continuous function representation, e.g. a superquadric, to generate the discrete representation and simplify the contact detection process.

Incipient detection of pavement deterioration (such as crack identification) is critical to optimizing road maintenance because it enables preventative steps to be implemented to mitigate damage and possible failure. Traditional visual inspection has been largely superseded by semi-automatic/automatic procedures given significant advancements in image processing. Therefore, there is a need to develop automated tools to detect and classify cracks.

The literature review is employed to evaluate existing attempts to use Hough transform algorithm and highlight issues that should be improved. Then, developing a simple low-cost crack detection method based on the Hough transform algorithm for pavement crack detection and classification.

Analysis results reveal that model accuracy reaches 92.14% for vertical cracks, 93.03% for diagonal cracks and 95.61% for horizontal cracks. The time lapse for detecting the crack type for one image is circa 0.98 s for vertical cracks, 0.79 s for horizontal cracks and 0.83 s for diagonal cracks. Ensuing discourse serves to illustrate the inherent potential of a simple low-cost image processing method in automated pavement crack detection. Moreover, this method provides direct guidance for long-term pavement optimal maintenance decisions.

The outcome of this research can help highway agencies to detect and classify cracks accurately for a very long highway without a need for manual inspection, which can significantly minimize cost.

Hough transform algorithm was tested in terms of detect and classify a large dataset of highway images, and the accuracy reaches 92.14%, which can be considered as a very accurate percentage regarding automated cracks and distresses classification.