Wyniki wyszukiwania - BazTech

1

Ore extraction and analysis from RGB image and 3D Point Cloud

Jin Feng, Zhan Kai, Chen Shengjie, Huang Shuwei, Zhang Yuansheng

Gospodarka Surowcami Mineralnymi

|

2022

|

T. 38, z. 1

89--106

EN

Based on the theory of computer vision, a new method for extracting ore from underground mines is proposed. This is based on a combination of RGB images collected by a color industrial camera and a point cloud generated by a 3D ToF camera. Firstly, the mean-shift algorithm combined with the embedded confidence edge detection algorithm is used to segment the RGB ore image into different regions. Secondly, the effective ore regions are classified into large pieces of ore and ore piles consisting of a number of small pieces of ore. The method applied in the classification process is to embed the confidence into the edge detection algorithm which calculates edge distribution around ore regions. Finally, the RGB camera and the 3D ToF camera are calibrated and the camera matrix transformation of the two cameras is obtained. Point cloud fragments are then extracted according to the cross-calibration result. The geometric properties of the ore point cloud are then analysed in the subsequent procedure.

PL

W oparciu o teorię widzenia komputerowego zaproponowano nową metodę wydobycia rudy z podziemnych kopalń. Jest to połączenie obrazów RGB zebranych przez kolorową kamerę przemysłową oraz chmury punktów wygenerowanej przez kamerę 3D ToF. Po pierwsze, algorytm zmiany średniej w połączeniu z wbudowanym algorytmem wykrywania krawędzi ufności służy do segmentacji obrazu rudy RGB na różne regiony. Po drugie, efektywne regiony rud są podzielone na złoża rudy o dużych rozmiarach i zwałowiska składające się z małej ilości rudy. Metodą stosowaną w procesie klasyfikacji jest określenie ufności w algorytmie wykrywania krawędzi, który oblicza rozkład krawędzi wokół regionów rudnych. Wreszcie, kamera RGB i kamera 3D ToF są skalibrowane i uzyskuje się transformację matrycy obu kamer. Następnie, fragmenty chmury punktów są wyodrębniane zgodnie z wynikiem kalibracji krzyżowej. W kolejnej procedurze przeanalizowano właściwości geometryczne chmury punktów rudy.

2

Novel visual object descriptor using surf and clustering algorithms

Grycuk R.

Journal of Applied Mathematics and Computational Mechanics

|

2016

|

Vol. 15, nr 3

37--46

EN

In this paper we propose a method for object description based on two wellknown clustering algorithms (k-means and mean shift) and the SURF method for keypoints detection. We also perform a comparison of these clustering methods in object description area. Both of these algorithms require one input parameter; k-means (k, number of objects) and mean shift (h, window). Our approach is suitable for images with a non-homogeneous background thus, the algorithm can be used not only on trivial images. In the future we will try to remove non-important keypoints detected by the SURF algorithm. Our method is a part of a larger CBIR system and it is used as a preprocessing stage.

3

Detection of hard exudates using mean shift and normalized cut method

Banerjee S., Kayal D.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

679--685

EN

As diabetic retinopathy (DR) is one of the main causes of loss of vision among diabetic patients, an early detection using automated detection techniques can prevent blindness among diabetic patients. Hard exudates constitute one of the early symptoms of DR and this paper describes a method for its detection using fundus images of retina, employing a combination of morphological operations, mean shift (MS), normalized cut (NC) and Canny's operation. This combined technique avoids over segmentation and at the same time reduces the time complexity while clearly delineating the exudates. Output of the proposed method is evaluated using public databases and produces sensitivity, specificity and accuracy as 98.80%, 98.25% and 98.65%, respectively. The ROC curve gives 0.984 as area under curve. The sensitivity, specificity, accuracy and area under curve of ROC indicate the effectiveness of the method.

4

A coarse-to-fine kernel matching approach for mean-shift based visual tracking

Liangfu L., Zuren F., Weidong C., Ming J.

Opto-Electronics Review

|

2009

|

Vol. 17, No. 1

65-71

EN

Mean shift is an efficient pattern match algorithm. It is widely used in visual tracking fields since it need not perform whole search in the image space. It employs gradient optimization method to reduce the time of feature matching and realize rapid object localization, and uses Bhattacharyya coefficient as the similarity measure between object template and candidate template. This thesis presents a mean shift algorithm based on coarse-to-fine search for the best kernel matching. This paper researches for object tracking with large motion area based on mean shift. To realize efficient tracking of such an object, we present a kernel matching method from coarseness to fine. If the motion areas of the object between two frames are very large and they are not overlapped in image space, then the traditional mean shift method can only obtain local optimal value by iterative computing in the old object window area, so the real tracking position cannot be obtained and the object tracking will be disabled. Our proposed algorithm can efficiently use a similarity measure function to realize the rough location of motion object, then use mean shift method to obtain the accurate local optimal value by iterative computing, which successfully realizes object tracking with large motion. Experimental results show its good performance in accuracy and speed when compared with background-weighted histogram algorithm in the literature.