Straight Line Detection Method Research Articles

A deep learning-based method for deviation status detection in intelligent conveyor belt system

Belt deviation is one of the most common faults of belt conveyors . Its occurrence not only causes materials to be scattered and affect the environment but also results in abnormal wear of equipment and increased energy consumption, which severely affects the green production and sustainable development of enterprises. Therefore, the rapid and timely detection of the deviation state of conveyor belts is of great significance for ensuring the safe and efficient operation of transportation systems. In view of the disadvantages of the available technology in terms of detection speed, a novel conveyor belt deviation monitoring method based on deep learning is proposed in this paper, which is realized by improving the output results of a general target detection network, YOLOv5, such that the network is enhanced with the ability to detect straight lines instead of bounding box , which effectively solves the problem of rapid feature extraction and deviation judgment of the edges of the conveyor belt of a belt conveyor against a complex background. Experiments show that the proposed method balances detection accuracy and speed, with a detection accuracy of up to 90% and a detection speed of up to 67 frames per second (FPS), and shows good real-time performance. The method greatly simplifies the process of straight-line feature extraction in complex environments, helps realize the intellectualization of conveyors, and achieves unmanned operation and energy savings in coal mines to realize green, energy-saving, and sustainable development while ensuring safe and efficient transportation. • General target detection network-based straight line detection method. • Efficient conveyor belt edge detection under complex scenes. • New detection method of belt deviation to ensure safe and clean transportation.

Linear Correction and Matching Method for 3D Line Structure Reconstruction

The 3D reconstruction technique using the straight-line segments as features has high precision and low computational cost. The method is especially suitable for large-scale urban datasets. However, the line matching step in the existing method has a mismatching problem. The two main reasons for this problem are the line detection result is not located at the true edge of the image and there is no consistency check of the matching pair. In order to solve this problem, a linear correction and matching method for 3D reconstruction of target line structure is proposed in this paper. Firstly, the edge features of the image are extracted to obtain a binarized edge map. Then, the extended gradient map is calculated using the edge map and the gradient to establish the gradient gravitational map. Secondly, the straight-line detection method is used to extract all the linear features used for the 3D reconstruction image, and the linear position is corrected by the gradient gravitational map. Finally, the point feature matching result is used to calculate the polar line, and the line matching results of the adjacent three images are used to determine the final partial check feature area. Then, random sampling is used to obtain the feature similarity check line matching result in the small neighborhood. The aforementioned steps can eliminate the mismatched lines. The experimental results demonstrate that the 3D model obtained using the proposed method has higher integrity and accuracy than the existing methods.

Shape Detection of Silicon Single Crystal Based on the MUSIC Algorithm

To improve the accuracy and speed of detecting crystal shape during the growth of Czochralski silicon single crystals, a straight line detection method is proposed based on the multiple signal classification (MUSIC) algorithm. First, in order to obtain multi-snapshot signals to meet the MUSIC algorithm requirements, we add multiple sets of zero-mean Gaussian noise. These sets of noise obey the same distribution (i.e., zero-mean Gaussian). This supports the generation of multiple images, which are converted into multi-snapshot signals of a virtual sensor array. These multi-snapshot signals are used to construct a far-field model; the tilt angle estimation problem of a straight line is transformed into a search problem, which seeks the direction of arrival in the virtual input sources. Finally, a near-field model is constructed, and the estimated potential offsets corresponding to the tilt angles are calculated to determine the parameters of the straight line. The simulation and engineering experiments show that the proposed method can accurately and quickly detect the tilt angle and the offset of the straight line, and is superior to existing methods.

Fast Straight Line Detection Method Based on Directional Coding

The Standard Hough Transform (SHT) is robust in detecting dashed or broken lines, but the main parts of it, blind vote, can cause excessive consumption of computation. To overcome this disadvantage, a fast straight line detection method based on directional coding(DCHT) is described in this paper. The algorithm turns the exhausted task of voting for all directions into an elegant task by constructing a sniffer and predicting direction of straight lines around the pixels. By using directional coding approach, the algorithm proposed here treats each direction of edge pixels differently, voting for a smaller angle range covering the direction of straight line which contains this edge pixel. In this way, half or more voting is removed. Experimental results show that DCHT algorithm has significant performance in reducing both execution time and the influence of noise on parameter space.

Green Grape Detection and Picking-Point Calculation in a Night-Time Natural Environment Using a Charge-Coupled Device (CCD) Vision Sensor with Artificial Illumination.

Night-time fruit-picking technology is important to picking robots. This paper proposes a method of night-time detection and picking-point positioning for green grape-picking robots to solve the difficult problem of green grape detection and picking in night-time conditions with artificial lighting systems. Taking a representative green grape named Centennial Seedless as the research object, daytime and night-time grape images were captured by a custom-designed visual system. Detection was conducted employing the following steps: (1) The RGB (red, green and blue). Color model was determined for night-time green grape detection through analysis of color features of grape images under daytime natural light and night-time artificial lighting. The R component of the RGB color model was rotated and the image resolution was compressed; (2) The improved Chan–Vese (C–V) level set model and morphological processing method were used to remove the background of the image, leaving out the grape fruit; (3) Based on the character of grape vertical suspension, combining the principle of the minimum circumscribed rectangle of fruit and the Hough straight line detection method, straight-line fitting for the fruit stem was conducted and the picking point was calculated using the stem with an angle of fitting line and vertical line less than 15°. The visual detection experiment results showed that the accuracy of grape fruit detection was 91.67% and the average running time of the proposed algorithm was 0.46 s. The picking-point calculation experiment results showed that the highest accuracy for the picking-point calculation was 92.5%, while the lowest was 80%. The results demonstrate that the proposed method of night-time green grape detection and picking-point calculation can provide technical support to the grape-picking robots.

Drivers’ Seat Belts Detection at Crossroads Based on OpenCV

Considering the limitations of current approaches of traffic detection after the new traffic laws are introduced, an intelligent detection system of driver’s seat belts is proposed based on OpenCV in this paper. It is combined with the appliance of linear fitting method, straight line detection method and gray integral projection method. Thus, whether the drivers wear their seat belts or not can be analyzed and judged by the system from acquired images, which can ensure the road traffic security and the safety of drivers and help to increase the efficiency of the police. We can accurately distinguish the drivers’ violation and realize the intelligent transportation.

Straight line detection from remote sensing images by rule-based feature fusion

Straight line detection is a fundamental problem in target recognition from remote sensing images since many man-made objects have straight boundaries. In this study, an integrated straight line detection method for remote sensing images is proposed. In this method, the edge-based straight lines are extracted using a chain code tracing method and the phase-based straight lines are extracted using a phase grouping method. The two types of lines are combined using a rule-based feature fusion method by removing redundant line extraction. Since this method integrates the specialties of edge- and phase-based straight line detection methods, it can detect straight lines from remote sensing images with high correctness and robustness.