CC BY
17
При понижении давления раствор воздуха в воде становится пересыщенным и избыточное количество газа выделяется из раствора в виде мелкодисперсных пузырьков. При температуре 40 0С флотация практически прекращается из-за недостаточной растворимости компонентов воздуха и эффективность очистки значительно снижается. Для качественной работы установки необходимо или рассредоточить по времени сброс сточных вод с повышенной температурой или организовать предварительное охлаждение стоков [8, 295].
Сброс сточной воды с различной рН неравными интервалами времени создает проблему необходимости изменения рН путем подкисления или подщелачивания, так как коагулирующая способность зависит от реакционной среды. Образование крупнодисперсными частицами пленки, которая практически не содержит воду, попадание в промышленные сточные воды бытовых и ливневых стоков также осложняют процесс флотации. Собирающуюся на поверхности сточных вод пленку возможно удалить при помощи насоса, который будет выкачивать отстоявшиеся нефтепродукты в специальную емкость, тогда эффективность напорной флотации возрастет.
Попадания грунтовых вод, а вместе с ними глины, соединений железа необходимо избегать путем надлежащей проверки состояния и ремонта канализационных люков, коллекторов. При очистке воды, направляемой после промывания установок, на которых могут находиться поверхностно-активные вещества, мазут, масла, увеличивается стойкость образующихся эмульсий. Это приводит к ухудшению качества флотации. Устойчивость таких эмульсий находится в верхних пределах от месяцев до нескольких лет. Кислотная обработка вод, содержащих
стойкие эмульсии, до выброса этих вод к остальным потокам воды позволит обеспечить нормальную работу напорной флотационной установки.
Литература
1. Дерягин, Б.В. Основы и контроль процессов флотации [Текст] / Б.В. Дерягин, С.С. Духин, Н.Н. Рулев. - М.: Недра, 1980.
2. Классен, В.И. Введение в теорию флотации [Текст] / В.И. Классен, В.А. Мокроусов. - М.: Госгормехиз-дат, 1959.
3. Фрумкин, А.Н. Физико-химические основы теории флотации [Текст] /А.Н. Фрумкин. - М.: АН СССР, 1932.
4. Рулев, Н.Н. Теория флотации мелких частиц и флотационной водоочистки [Текст] : дис.... к.х.н. / Н.Н. Рулев. - Киев, 1977.
5. Каратаев О.Р., Новиков В.Ф., Шамсутдинова З.Р. /Моделирование процессов растворения химических реагентов в потоках воды// Вестник Казанского технологического университета. № 22, 2013г. с. 45-47
6. Стахов, Е.А. Очистка нефтесодержащих вод предприятий хранения и транспорта нефтепродуктов / Е.А. Стахов. - Л.: Недра, 1983. - 264 с.
7. Очистка и использование сточных вод в промышленном водоснабжении. - М.: Химия, 1983. - 288 с., ил
8. Валеев С.И., Булкин В.А. /Применение гидроциклонов для очистки сточных вод в системе оборотного водоснабжения// Вестник Казанского технологического университета. № 15, 2013г. с. 294-296
COMPARISON OF FEATURE DESCRIPTORS
Shimanskiy Nikolay Dmitrievich
Master of Kostanay State University named after Baitursynov, Kostanay
Zharlykasov Bakhtiyar Zhumalyevich Lecturer of Kostanay State University named after Baitursynov, Kostanay
Muslimova Agima Zeynagatdinovna
Ph.D. Kostanay State University named after Baitursynov, Kostanay
Introduction
Feature descriptors are commonly used in lots of computer vision algorithms - object recognition, tracking, image stitching camera calibration and etc. We used it in three different types of tasks - tracking for AR, object recognition and visual classification. Recently We conducted a detail analysis of the state-of-the-art detectors and descriptor-generators, since We are considering to try different algorithms in some of my undergoing research projects as well as for the purpose of our paper revision.
SIFT
SIFT descriptor is a classic approach, also the "original" inspiration for most of the descriptors proposed later. Up to date, it still outperforms most of the descriptors in the field. The drawback is that it is mathematically complicated and computationally heavy. Main issues it addresses are the scaling-invariance and orientation-invariance in describing the features.
Detector: The keypoint is selected based on the Difference of Gaussian - detecting locations that are invariant
to scale change of the image can be accomplished by searching for stable features across all possible scales, using a continuous function of scale known as scale space. To detect the keypoints, scale octave is generated and the local extrema is detected by comparing the centre pixel with the neighbors in space [1, p.5].
Descriptor: To describe the keypoints, SIFT make uses of the local gradient values and orientations of pixels around the keypoint. A keypoint describer is created by first computing the gradient magnitude and orientation at each image sample point in a region around the keypoint location, as shown on the left. These are weighted by a Gaussian window, indicated by the overlaid circle [2, p.130]. These samples are then accumulated into orientation histograms summarizing the contents over 4x4 subregions, as shown on the right, with the length of each arrow corresponding to the sum of the gradient magnitude near that direction within the region.
/ >
_ / t h
I N * ---
\' 4 -- / У
к
*
Picture 1. Difference of Gaussians
FAST
FAST is a standalone feature detector (not descriptor generator). It is designed to be very efficient and suitable for real-time applications of any complexity. The segment test criterion operates by considering a circle of sixteen pixels around the corner candidate p. The original detector classifies p as a corner if there exists a set of n contiguous pixels in the
Image gradients Keypoint descriptor
Picture 2. SIFT descriptor
circle which are all brighter than the intensity of the candidate pixel Ip plus a threshold t, or all darker than Ip - t, as illustrated below [3, p.13]. To speed up the detector, a machine learning approach is adopted, and a decision tree is generated. The detail discussion is in the paper. FAST is only a detector, but it is proven to be quite reliable and used in the upstream for lots of other descriptor generating process.
Picture 3. Corner detection
SURF
SURF detector is recognized as a more efficient substitution for SIFT. It has a Hessian-based detector and a distribution-based descriptor generator.
Detector: the detector is based on the Hessian matrix, defined as
H(x,a) = [
Lv
xy\
Lvv (x, o}
(1)
'-'xy
L is the convolution of the Gaussian second order derivative with the image I. In the implementation, they replace the Gaussian kernel with a simpler box filter. It is then interpolated in scale and image space to give itself the scale-invariance properties.
Descriptor: An orientation is first assigned to the keypoint. Then a square region is constructed around the keypoint and rotated according to the orientation. The region is split up regularly into smaller 4x4 square sub-regions. This keeps important spatial information in. For each sub-region, we compute a few simple features at 5x5 regularly spaced sample points. The horizontal and vertical Haar wavelet responses dx and dy are calculated and summed up over each sub-region and form a first set of entries to the feature vector. The absolute values of the responses |dx| and |dy| are also calculated, and together with the sum of vector to form a four-dimensional descriptor. And for all 4x4 sub-regions, it results in a vector of length 64 [4, p.4].
E dy
iwrt
Picture 4. SURF descriptor
BRIEF
BRIEF descriptor is a light-weight, easy-to-implement descriptor based on binary strings. Binary test is explored in FERN algorithm, which is a Naive-Bayesian classifier method for feature matching. BRIEF descriptor targeted to low-power devices, and compensate some of its robustness and accuracy to the efficiency. It is a standalone descriptor generator, an upstream detector, such as FAST is required.
The approach is to define a test pattern (experiment indicates Gaussian distribution gives a good result) and
applied to the detected keypoints. The lines indicates a test pair, an output of either 1 or 0 is provided based on the intensity difference of the two pixels [5, p.6]. A series of such test outputs a binary string, which is considered as the "descriptor". Matching of the descriptor is based on the Hamming distance. BRIEF descriptor is not scale and orientation invariant due to the nature of the its design, however it inspires a few most recent and advanced binary-test based descriptors, which are discussed below.
Picture 5. BRIEF - illustration of the five sampling pattern
ORB
ORB is an extension of BRIEF descriptor by introducing orientation invariance. It uses FAST detector with an orientation assignment by intensity centroid. To describe the feature, BRIEF pattern is rotated with orientation angles and a good pattern distribution is trained from the large rotated pattern database. A bit more detail about ORB is summarized here.
Detector: The detector first employ a Harris corner measure to order the FAST keypoints since FAST does not produce a measure of cornerness. The orientation for the detected points are calculated based on the intensity centroid. The centroid is defined as = Zx,yxpxqI(x,y) (2)
m.
pq
С = (^l0,^01) (3) m00 m00
A vector from the corner's center to centroid can be calculated, and the orientation simply is [6, p.2]
8 = atan2(m01,m10), (4)
Descriptor: The test pattern is steered according to the orientation of the keypoints. But the steered BRIEF lowers its variance because the oriented corner keypoints present a more uniform appearance to binary tests. To recover from the loss of variance in steered BRIEF, a learning method is developed to select a good subset from the binary test pool. The results BRIEF has a better diversity and lower correlation.
BRISK
BRISK is more recent method based on scale-space enabled FAST for testing and binary test patterns for describing.
Detector: a keypoint is identified at octave ci by analyzing the 8 neighboring saliency scores in ci as well as in the corresponding scores-patches in the immediately-neighboring layers above and below. In all three layers of interest, the local saliency maximum is sub-pixel refined before a 1D parabola is fitted along the scale-axis to determine the true scale of the keypoint [7, p.3].
k>{£,(f) r. icale
iiitta-dciavi d,
inrerpnLtcd ptrtirion Lilt ra-oc Da ve dl,
PAST ïco re 9
Picture 6. Scale-space interest point detection
Descriptors: BRISK is a 512 bit binary descriptor that computes the weighted Gaussian average over a selected pattern of points near the keypoint. The pattern is designed as that N locations are equally spaced on circles concentric with the keypoint. For the formation of the rotation- and scale-
normalized descriptor, BRISK applies the sampling pattern rotated by alpha around the keypoint k. The bit-vector descriptor is assembled by performing all the short-distance binary intensity comparisons of point pairs.
Picture 7. The BRISK sampling pattern with N = 60 point
FREAK
FREAK is a standalone descriptor. It improves upon the sampling pattern and method of pair selection that BRISK uses. FREAK evalues 43 weighted Gaussians at locations around the keypoint [8, p.4], but the pattern formed by these
Gaussians is biologically inspired by the retinal pattern in the eye. The pixels being averaged overlap, and are much more concentrated near the keypoint. The actual FREAK algorithm uses a cascade for comparing these pairs, and puts the 64 most important bits in front to speed up the matching process.
Human retina
Photoreceptors Cells Ganglion Cells
Computer Vision
Pixels
Action potentials
Linear Non-linear
X wt -
X w2 -
— X w3
X w4 -
— X w5 -
X w6 - I
_ — X w7 — _
1011001
Binary string
Picture 8. From human retina to computer vision: the biological pathways leading to action potentials is emulated by simple binary tests over pixel regions
Test cases
For this test we have written special test framework, which allows us to easily add the new kind of descriptors and test cases and generate report data. Five quality and one performance test was done for each kind of descriptor.
• Rotation test - this test shows how the feature descriptor depends on feature orientation.
• Scaling test - this test shows how the feature descriptor depends on feature size.
• Blur test - this test shows how the feature descriptor is robust against blur.
• Lighting test - this test shows how the feature descriptor is robust against lighting.
• Pattern detection test - this test performs detection of planar object (image) on the real video. In contrast to the synthetic tests, this test gives a real picture of the overall stability of the particular descriptor.
• Performance test is a measurement of description extraction time. All quality tests works in similar way. Using a given source image we generate a synthetic test data: transformed images corresponding feature points. The transformation algorithm depends on the particular test. For the rotation test case, it's the rotation of the source image around it's center for 360 degrees, for scaling - it's resizing of image from 0.25X to 2x size of original. Blur test uses gaussian blur with several steps and the lighting test changes the overall picture brightness. The pattern detection test deserves a special attention. This test is done on very complex and noisy video sequence. So it's challenging task for any feature descriptor algorithm to demonstrate a good results in this test. The metric for all quality tests is the percent of correct matches between the source image and the transformed one. Since we use planar object, we can easily select the inliers from all matches using the homography estimation. This metric gives very good and stable results. The matching of descriptors is done via brute-force matching.
Rotation test
Rotation invariaiTtiiess
* & W. ^ tf® fli г^•l' i® г'i■<1 ^ #
A/3£f/e in radians
Picture 9. Rotation test
In this test we obtain pretty expectable results, because calculation algorithm and descriptor nature. A detailed study all descriptors are rotation invariant expect the BRIEF. Slight of why the descriptor behaves exactly as it is, takes time and changes in stability can be explained by the feature orientation effort.
Scaling test
Scale iiivanaiitness
100
75
50
25
^ ^ ^ ^ ^ ^ ^ Scale
Picture 10. Scale test
SURF and SIFT descriptors demonstrate us very good stability in this test because they do expensive keypoint size calculation. Other descriptors uses fixed-size descriptor and you can see what it leads to. Currently for LAZY descriptor we do not have separate LAZY feature detector (we use ORB detector for tests) but We're thinking on lightweight feature detector with feature size calculation, because it's a must-have feature. Actually, scale invariance is much more important rather than precise orientation calculation.
Blur test
In this test we tried to simulate the motion blur which can occurs if camera moves suddenly. All descriptors demonstrate good results in this test. By "good" We mean that the more blur size is applied the less percent of correct matches is obtained. Which is expected behavior.
In lighting test the transformed images differs only in overall image brightness. All kinds of descriptors works well in this case. The major reason is that all descriptors extracted normalized, e.g the norm_2 of the descriptor vector equals 1. This normalization makes descriptor invariant to brightness changes.
Lighting test
л>ь
\1 ф i> ffi i®
Brightness shift
Picture 11. Blur test
Э 5 7 9 11 13 1E 17 19 Gaussian b/ur kernel size
Picture 12. Lighting test
Pattern detection on real video
Pattern detection
■ BRIEF
■ LAZY
V гъ V» -Л Ф ^ г^
Frame index
Picture 13. Pattern detection test
Detection of the object on real video is the most complex task since ground truth contains rotation, scaling and motion blur. Also other objects are also present. And finally, it's not HD quality. These conditions are dictated by the actual conditions of application of computer vision. As you can see on diagram, the SIFT and SURF descriptors gives the best results, nevertheless they are far away from ideal, it's quite enough for such challenging video. Unfortunately, scale-covariant descriptors show very bad results in this test because pattern image appears in 1:1 scale only at the beginning of the video (The "spike" near frame 20). On the rest of the video sequence target object moves from the camera back and scale-covariant descriptors can't handle this situation.
List of references:
1. David G. Lowe. "Distinctive Image Features from Scale-Invariant Keypoints". International Journal of Computer Vision archive, November 2004.
2. Peter Ian Hansen. "Wide-Baseline Keypoint Detection and Matching with Wide-Angle Images for Vision Based Localisation". Queensland University of Technology, Brisbane, 2010. - 382
3. Edward Rosten, Reid Porter, and Tom Drummond. "Faster and better: a machine learning approach to corner detection." IEEE Transactions on Pattern Analysis and Machine Intelligence archive, January 2010. 105-119
4. Bay, Herbert, Tinne Tuytelaars, and Luc Van Gool. "Surf: Speeded up robust features." Computer Vision and Image Understanding June, 2008.
5. Calonder, Michael, et al. "Brief: Binary robust independent elementary features." Computer Vision-ECCV 2010. Springer Berlin Heidelberg, 2010. 778792.
6. Rublee, Ethan, et al. "ORB: an efficient alternative to SIFT or SURF." Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.
7. Leutenegger, Stefan, Margarita Chli, and Roland Y. Siegwart. "BRISK: Binary robust invariant scalable keypoints." Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011.
8. Alahi, Alexandre, Raphael Ortiz, and Pierre Vandergheynst. "Freak: Fast retina keypoint." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
МАТЕМАТИЧЕСКАЯ МОДЕЛЬ ХОЛОДНОЙ ПРАВКИ СТАЛЬНОГО ЛИСТА НА ДЕВЯТИРОЛИКОВОЙ МАШИНЕ ФИРМЫ SMS SIEMAG МЕТАЛЛУРГИЧЕСКОГО КОМПЛЕКСА СТАН 5000
Шинкин Владимир Николаевич
доктор физ.-мат. наук, профессор Национального исследовательского технологического университета «МИСиС», г. Москва
THE MATHEMATICAL MODEL OF THE STEEL SHEET'S COLD STRAIGHTENING ON THE NINE-ROLLS MACHINE BY SMS SIEMAG AT THE METALLURGICAL COMPLEX MILL 5000
Vladimir N. Shinkin, Doctor of Science, Professor of the National Research Technological University «MISiS», Moscow АННОТАЦИЯ
Предложен математический метод определения оптимальных технологических параметров холодной правки стального листа на девятироликовой листоправильной машине немецкой фирмы SMS Siemag. Результаты исследований могут быть использованы на металлургических заводах по производству широкого толстого стального листа. ABSTRACT
The mathematical method for the determining of the optimal technological parameters of the cold straightening of a steel sheet on the 9-rolls sheet-straightening machine by German company SMS Siemag is proposed. The results of the research can be used at the metallurgical plants in the production of the broad thick steel sheet. Ключевые слова: толстый стальной лист, листоправильные машины. Keywords: a thick steel sheet, the sheet-straightening machines.
