一種空中多目標(biāo)的定位及識別快速算法
A Fast Arithmetic about Positioning and Identifying Multi-targets in Air
-
摘要: 針對空中多個(gè)目標(biāo)進(jìn)行精確定位及識別的特殊應(yīng)用場合，該文采用了先進(jìn)的改進(jìn)不變矩的算法來進(jìn)行目標(biāo)的識別。由于不變矩識別對目標(biāo)輪廓要求很高，該文提出了一種新的具有方向估計(jì)性質(zhì)的形態(tài)學(xué)梯度邊緣檢測算子，彌補(bǔ)了現(xiàn)行的同類算子無法估計(jì)邊緣方向的缺點(diǎn)；將模糊理論引入該算子，使其更好地抑制噪聲，成功分離目標(biāo)和背景；提出了一種新的斷點(diǎn)連接及孤點(diǎn)消除的算法，使目標(biāo)的輪廓更加清晰平滑，并用跟蹤法找到其單像素輪廓線。實(shí)驗(yàn)證明，這種新算法極大地提高了對空中多個(gè)目標(biāo)的識別率，并大大加強(qiáng)了系統(tǒng)的可靠性。
-
關(guān)鍵詞:
- 形態(tài)學(xué)梯度;模糊理論;方向估計(jì);閾值分割;邊緣檢測;不變矩
Abstract: Aiming at the special situation of positioning and identifying multi-targets in air, this paper has the advanced invariant moment arithmetic to carry out. Because the moments request good quality of identifying, so this paper provides a new morphological gradient image edge detection operator which can estimate orientation, and proves them in theory and practice. There are four element structures with different direction. In these operators, the blurring processing is added, it makes that the operators not only depress the noise in image, but also enhance edges definition. And then it changes the edge detection image into the binary image through the optimal threshold segmentation. It also shows a new simple arithmetic about jointing broken lines. It does not only make the targets contour smooth, but also can find the single pixel boundary with tracking. Through kinds of tests, the identifying rate has been improved, and the dependability has been strengthened. -
Dougherty E R, Astola J. An introduction to nonlinear image processing. SPIE, 1994, Tutorial Text Vol. TT16: 2-5 .[2]Lee J, Haralick R M, Dhapiro L G. Morphological edge detector. IEEE Trans. Robotics and Automation, 1987, RA-3(2): 142-153.[3]Mahdavieh Y, Gonzalez R C. Advance in Image Analysis, SPIE Optical Engineering Press, 1992: 432-437.[4]Sonka M, Hlavac V, Boyle R. Image Processing Analysis and Machine Vision(2ed), PWS Kent，1998: 4.3.2-4.3.3[5]Paplinkski A P. Directional filtering in edge detection. IEEE Tran.. on Image Processing, 1998: 7(4): 611-615.[6]楊枝靈，王開. Visual C++數(shù)字圖像獲取、處理及實(shí)踐應(yīng)用.北京: 人民郵電出版社, 2003: 535-537.[7]何斌, 馬天宇, 王運(yùn)堅(jiān), 朱紅蓮. Visual C++ 數(shù)字圖象處理. 北京: 人民郵電出版社, 2001: 435-437.[8]Sonka M, Hlavac V, Boyle R, 艾海舟，武勃. Image Processing Analysis and Machine Vision(2ed),北京: 人民郵電出版社，2003: 177-178.[9]Wong Y R . Scene matching with invariant moments CGIP, 1978, 8: 16-24.[10]周振環(huán). 圖像特征提取及應(yīng)用研究. [博士論文], 西安：西北工業(yè)大學(xué), 2001: 62-63. -
計(jì)量
- 文章訪問數(shù): 2443
- HTML全文瀏覽量: 114
- PDF下載量: 1077
- 被引次數(shù): 0
下載:
