Edge detection based on Retinex theory and wavelet multiscale product for mine images

Du, Yuxin; Tong, Minman; Zhou, Lingling; Dong, Haibo

doi:10.1364/ao.55.009625

Cited by 16 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to address the issues related to uneven illumination, unclear details, and poor contrast in coal mine images caused by large artificial light sources, Du et al [42] put forward an edge feature detection method based on the Retinex theory and wavelet multiscale product after spectral analysis of low-illumination images. In addition, during image acquisition, camera vibrations may lead to inaccurate or even incorrect measurement results.…”

Section: ) Image Preprocessingmentioning

confidence: 99%

Applications of Machine Vision in Coal Mine Fully Mechanized Tunneling Faces: A Review

Du,

Zhang,

Liang

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

The realization of intelligent mining is the only method for realizing high-quality development in the coal industry. As the forefront working link in mine production, achieving automatic roadway tunneling control is key to improving production efficiency, enhancing intelligence, and reducing accident rates at fully mechanized tunneling working faces. Among various detection techniques, machine vision technology stands out with advantages of non-contact measurement, rich information acquisition, and high detection accuracy. The detection and control of tunneling equipment groups based on machine vision has become a research hotspot in the intelligence process of coal mines. This study first introduces the key technologies of a visual detection system, including camera calibration, image preprocessing, feature extraction, visual matching, target segmentation and recognition, visual measurement, and 3D reconstruction. It then elaborates on detection principles, workflows, limitations, precautions, and development status of various vision detection systems in practical application scenarios at tunneling faces, such as tunneling equipments, anchoring systems, transportation systems, and safety auxiliary systems, which significantly improve production safety and efficiency. Finally, considering challenging work conditions and strong interference in mines, the successful adaptation of machine vision to excavation sites relies on addressing technical challenges related to poor environment adaptability, limited imaging field of view, and low intelligence level. Furthermore, according to existing research results and the current technical status, this paper forecasts key technologies that need to be developed in the future for coal mine intelligent equipment systems based on machine vision, including multi-sensor information fusion, equipment group collaborative control, and digital twin-driven remote monitoring.INDEX TERMS Machine vision, coal machinery equipment, detection and measurement, roadway fully mechanized tunneling faces, unmanned coal mine.

show abstract

Section: ) Image Preprocessingmentioning

confidence: 99%

Applications of Machine Vision in Coal Mine Fully Mechanized Tunneling Faces: A Review

Du,

Zhang,

Liang

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…So, in this way, these transitions of illumination between two regions indicate the edges of an element or object. A proposal is made to use the gradient function to identify the transition between two regions, and this is related to the edge detection techniques [24]. The gradient function quantifies the change rate of local variations by creating a vector whose direction points to the direction of maximum variation of the intensity level, as illustrated in Equation ),

\nabla I ((), x, y) = ([], \begin{matrix} \frac{\partial I ((), x, normaly)}{\partial x} \\ \frac{\partial I ((), x, y)}{\partial y} \end{matrix})

where ∇ I ( x , y ) is the gradient of the grayscale image I ( x , y ) .…”

Section: Proposed Algorithmmentioning

confidence: 99%

Lighting source classification applied in color images to contrast enhancement

Dehesa‐González

Rosales

Gallegos‐Funes

et al. 2020

Color Research & Application

View full text Add to dashboard Cite

A novel methodology is proposed to identify the distribution of the intensity of the illuminant across a real‐world image; with this information, the image can be classified as a homogeneous or nonhomogeneous lighting source. A criterion is proposed for deciding whether the illumination in the tested image is homogeneous or nonhomogeneous. This criterion is based on well‐established methods that are dedicated to improving color characteristics and are commonly used to determine the color of the lighting source during a captured scene. The classification of homogeneous or nonhomogeneous illumination in real‐world images is implemented in the BSD500 database, and the results are compared with a manual classification of images—proposed under subjective criteria—by the authors; in this way, one can analyze how the lighting source affects the image. This procedure provides a classification methodology for real‐world image databases found in the scientific literature.

show abstract

“…During the movement, when the robot turns in place, it cannot avoid measurement errors from the electronic compass and gyro, because of the slipping between the robot track and ground. Then, the movement trajectory can be integrated with the characteristics of the environment in the video [ 21 ] obtained by two cameras and the drawings of the coal mine structure to determine the robot position. Although this method has many defects, it can help the rescue team localize the robot.…”

Section: The Control System Of Msrbotsmentioning

confidence: 99%

A Search-and-Rescue Robot System for Remotely Sensing the Underground Coal Mine Environment

Zhao

Gao

Zhao

et al. 2017

Sensors

View full text Add to dashboard Cite

This paper introduces a search-and-rescue robot system used for remote sensing of the underground coal mine environment, which is composed of an operating control unit and two mobile robots with explosion-proof and waterproof function. This robot system is designed to observe and collect information of the coal mine environment through remote control. Thus, this system can be regarded as a multifunction sensor, which realizes remote sensing. When the robot system detects danger, it will send out signals to warn rescuers to keep away. The robot consists of two gas sensors, two cameras, a two-way audio, a 1 km-long fiber-optic cable for communication and a mechanical explosion-proof manipulator. Especially, the manipulator is a novel explosion-proof manipulator for cleaning obstacles, which has 3-degree-of-freedom, but is driven by two motors. Furthermore, the two robots can communicate in series for 2 km with the operating control unit. The development of the robot system may provide a reference for developing future search-and-rescue systems.

show abstract

Edge detection based on Retinex theory and wavelet multiscale product for mine images

Cited by 16 publications

References 17 publications

Applications of Machine Vision in Coal Mine Fully Mechanized Tunneling Faces: A Review

Applications of Machine Vision in Coal Mine Fully Mechanized Tunneling Faces: A Review

Lighting source classification applied in color images to contrast enhancement

A Search-and-Rescue Robot System for Remotely Sensing the Underground Coal Mine Environment

Contact Info

Product

Resources

About