本文選題：特征點(diǎn)匹配 + 實(shí)時(shí)　； 參考：《中國圖象圖形學(xué)報(bào)》2016年09期

【摘要】：目的針對(duì)傳統(tǒng)的圖像特征點(diǎn)匹配算法數(shù)據(jù)量大,計(jì)算耗時(shí)長的特點(diǎn),提出一種實(shí)時(shí)魯棒的特征點(diǎn)匹配算法(RRM)。方法通過微分操作確定圖像的邊緣區(qū)域,找出邊緣區(qū)域中很有可能成為特征點(diǎn)的錨點(diǎn),即梯度局部最大的點(diǎn)。對(duì)于每個(gè)檢測出來的特征點(diǎn),通過計(jì)算Intensity Centroid來確定特征點(diǎn)的方向,并且使用改進(jìn)的Brief來對(duì)特征點(diǎn)進(jìn)行描述,使之具有旋轉(zhuǎn)不變性。最后,結(jié)合Hamming距離和對(duì)稱匹配檢驗(yàn)對(duì)特征點(diǎn)進(jìn)行匹配。結(jié)果本文算法與多種算法進(jìn)行對(duì)比,在光照發(fā)生變化的情況下,RRM表現(xiàn)出明顯的優(yōu)越性和穩(wěn)定性,正確匹配率達(dá)到83%左右,而其他算法的準(zhǔn)確匹配率隨著光照的變暗明顯下降;在視角、尺度和旋轉(zhuǎn)變化條件下,RRM也具有較高的準(zhǔn)確匹配率。結(jié)論實(shí)驗(yàn)結(jié)果表明,RRM在保證匹配精度的前提下,有效地解決了傳統(tǒng)特征點(diǎn)匹配方法中的缺點(diǎn)。因此,本文算法能更好地應(yīng)用于圖像拼接、目標(biāo)跟蹤和對(duì)象識(shí)別等領(lǐng)域。
[Abstract]:Aim in view of the large amount of data and long computation time of traditional image feature point matching algorithm, a real-time robust feature point matching algorithm is proposed. Methods the edge region of the image is determined by differential operation, and the anchor point of the edge region which is likely to be the feature point is found, that is, the local maximum point of the gradient. For each detected feature point, the direction of the feature point is determined by calculating the Intensity Centroid, and the improved Brief is used to describe the feature point to make it rotation-invariant. Finally, the feature points are matched with Hamming distance and symmetry matching test. Results compared with other algorithms, RRM showed obvious superiority and stability in the case of light change, the correct matching rate was about 83%, while the accurate matching rate of other algorithms decreased obviously with the darkening of illumination. RRM also has a high accuracy matching rate under the condition of angle of view, scale and rotation. Conclusion the experimental results show that RRM can effectively solve the shortcomings of the traditional feature point matching method on the premise of ensuring the matching accuracy. Therefore, this algorithm can be applied to image mosaic, target tracking and object recognition.
【作者單位】： 廣東工業(yè)大學(xué)應(yīng)用數(shù)學(xué)學(xué)院;
【基金】：廣州市科學(xué)研究專項(xiàng)基金項(xiàng)目(201510010059)~~
【分類號(hào)】：TP391.41
，

本文編號(hào)：1976172