scispace - formally typeset
Search or ask a question
Author

Huang Lifang

Bio: Huang Lifang is an academic researcher. The author has contributed to research in topics: Image segmentation & Pixel. The author has an hindex of 2, co-authored 2 publications receiving 7 citations.

Papers
More filters
Patent
22 Sep 2017
TL;DR: In this paper, an image segmentation method and device and a segmentation threshold value is calculated according to the two-dimensional histogram of the image, and the to-be-tested object in the image is segmented precisely through a watershed method.
Abstract: The invention discloses an image segmentation method and device and an image segmentation method and device applied to slag pieces The method comprises the steps that a grayscale average of a neighborhood of each pixel point is calculated based on a grayscale value of each pixel point in an image of a to-be-tested object; a two-dimensional histogram of the image is constructed according to the calculated grayscale value of each pixel point and the grayscale average of the neighborhood of each pixel point; an optimal segmentation threshold value is calculated according to the two-dimensional histogram of the image; the to-be-tested object in the image is segmented based on the optimal segmentation threshold value to obtain an initial segmented binary image; and the to-be-tested object in the initial segmented binary image is segmented precisely through a watershed method Through the image segmentation method and device and the image segmentation method and device applied to the slag pieces, the image can be segmented precisely

5 citations

Patent
15 Sep 2017
TL;DR: In this paper, a method and system for measuring the volume flow of a material on a conveying belt is presented, which can measure the volume of a solid material having an irregular surface on the conveying belts.
Abstract: The invention discloses a method and system for measuring the volume flow of a material on a conveying belt, which can measure the volume flow of a solid material having an irregular surface on the conveying belt. The measurement method includes: a, acquiring first position information of a plurality of points of a surface of thee conveying belt, wherein the plurality of points are positioned in the same section; b, acquiring second position information of a plurality of points of a material surface in each section of a plurality of sections of the material, wherein the plurality of points of the material surface in each section are corresponding to the plurality of points of the step a in a one-to-one manner; c, acquiring a distance between every two corresponding points in each section of the plurality of sections of the material according o the first position information and the second position information; d, drawing up a plurality of class trapezoids according to the distance between every two corresponding points, calculating the areas of the plurality of class trapezoids, and calculating the sum of the area of each section of the material; and e, calculating the volume flow of the material according to the area of each section and the speed of the conveying belt.

2 citations


Cited by
More filters
Patent
22 Jan 2019
TL;DR: In this paper, a volume detection device arranged in a detection room field is used for detecting the volume in the detection room to obtain an instant on-site volume; a trigger control device is configured to receive the instant field volume and issue a capture trigger command when the volume is greater than or equal to a preset volume threshold value; MCU control equipment, for receiving a signal output image, segmenting from the output image to obtain a plurality of human body contours based on a person grey upper threshold and a person gray lower threshold, determining whether each human contour is an
Abstract: The invention relates to an image segmentation system based on computer processing, comprising: a volume detection device arranged in a detection room field, which is used for detecting the volume inthe detection room field to obtain an instant on-site volume; a trigger control device, configured to receive the instant field volume and issue a capture trigger command when the instant field volumeis greater than or equal to a preset volume threshold value; MCU control equipment, for receiving a signal output image, segmenting from the signal output image to obtain a plurality of human body contours based on a person gray upper threshold and a person gray lower threshold, determining whether each human contour is an animated human contour based on the image characteristics of the animatedcharacter, and issuing an animation identification signal when the number of animated human contours in the signal output image is more than twice the number of non-animated human contours in the signal output image. By the invention, the cartoon and the non-cartoon can be accurately distinguished.

1 citations

Patent
01 Mar 2019
TL;DR: In this article, a feature extraction unit of the slag slice spatial information is composed of a plurality of scanning lines generated by the laser three-dimensional camera; the properties of slag slices are judged comprehensively by comprehensive height gradient, height mean and height gradient mean, and the binary image of SLAs is established according to the properties.
Abstract: The invention provides a slag slice image segmentation method based on a laser three-dimensional camera. The method comprises the following steps: a feature extraction unit of the slag slice spatial information is composed of a plurality of scanning lines generated by the laser three-dimensional camera; the properties of slag slices are judged comprehensively by comprehensive height gradient, height mean and height gradient mean, and the binary image of slag slices is established according to the properties of slag slices. The binary images of slag slices are eroded and dilated respectively, and the non-slag slice regions are filtered based on the morphological characteristics of slag slices. The morphological features between the filtered connected domains are obtained, the blocked slag slices are filtered, and the segmented images of the unblocked surface slag slices are obtained. As that slag slice distribution spatial information obtain by the laser three-dimensional camera can avoid the influence of the uneven illumination on the image segmentation result, the slag slice image segmentation is realize by judging the slag slice shielding area based on the spatial height information, the slag slices shielded are eliminated, and the surface slag slices segmentation and the statistical accuracy of feature extraction are improved.

1 citations

Patent
09 Oct 2020
TL;DR: In this article, a coal flow detection method for accurately analyzing the coal carrying amount on a belt conveyor was proposed, where a laser radar ranging technology was applied to the field of coal mine automation.
Abstract: The invention relates to a coal flow detection method for accurately analyzing the coal carrying amount on a belt conveyor. A laser radar ranging technology is applied to the field of coal mine automation, the coal carrying amount on the belt conveyor can be accurately metered through the method, by means of laser beams emitted by a laser radar mirror surface column, belt shape data returned through the laser radar is calculated through a certain processing algorithm, then the average thickness of coal on a belt is obtained, and the coal flow is obtained through calculation according to a formula, so that the problems of being large in error, complex in construction and installation and prone to damage due to weighing adjustment in the conveying process of traditional coal conveying belt control intelligence are solved, the coal quantity is directly detected on the conveying belt, and the automation level of the coal mine industry is improved.

1 citations

Patent
30 Aug 2019
TL;DR: In this paper, the authors presented a blast furnace slag iron output state online detection method. But the method was not applied to the real-time operation and management of the blast furnace before-furnace.
Abstract: The invention provides a blast furnace slag iron output state online detection method. The blast furnace slag iron output state online detection method comprises the steps that an imaging device is installed, and original video images of the blast furnace before-furnace iron tapping state and deslagging state are collected; the original video images collected are transmitted to a collection station, datalization and data analyzing processing are conducted on the original video images, and analysis results are acquired; and the analysis results are displayed. The blast furnace slag iron outputstate online detection method is applied to blast furnace smelting production practice, the blast furnace before-furnace slag iron output condition is grasped in real time, and blast furnace before-furnace refined operation and management are achieved.

1 citations

Patent
14 Jun 2019
TL;DR: Zhang et al. as mentioned in this paper proposed an image accurate segmentation method fusing a deep learning network and a watershed algorithm, which is characterized by adopting a DeepLab recognition model to recognize the to-be-determined image to obtain an initial segmentation image, and adopting the watershed algorithm to segment the image to get a group of to be determined areas.
Abstract: The invention discloses an image accurate segmentation method fusing a deep learning network and a watershed algorithm. The method is characterized by adopting a DeepLab recognition model to recognizethe to-be-determined image to obtain an initial segmentation image, adopting the watershed algorithm to segment the to-be-determined image to obtain a group of to-be-determined areas, multiplying thenumber of the to-be-determined areas by the initial segmentation image points, dividing the to-be-determined areas into to-be-determined object areas, or else removing the to-be-determined areas in the to-be-determined object areas. The method comprehensively utilizes the distance between the to-be-determined point and the to-be-measured substance center and the gray difference between the to-be-determined point and the foreground and background to judge the attribute of the equal point, and achieves the precise segmentation of the image. The characteristic that adjacent pixels with similar gray levels are partitioned by the watershed is utilized, the core area of the to-be-detected object is established by adopting a deep learning method, and the detection precision is improved.