中国光学
中國光學
중국광학
Chinese Journal of Optics
2015年
5期
775-784
,共10页
激光主动成像%目标识别%最大稳定极值区域%快速轮廓转动力矩特征%支持向量机
激光主動成像%目標識彆%最大穩定極值區域%快速輪廓轉動力矩特徵%支持嚮量機
격광주동성상%목표식별%최대은정겁치구역%쾌속륜곽전동력구특정%지지향량궤
laser active imaging%target recognition%MaximallyStable Extremal Regions(MSER)%fast contour torque features%Suppor VectorMachine(SVM)
针对激光主动成像的图像特性,提出一种基于快速轮廓转动力矩的目标识别方法。将转动力矩的概念引入目标识别中,提出的快速轮廓转动力矩特征( FCTF)不仅包含了轮廓的尺寸、位置、规则度以及目标的亮暗等信息,同时对于旋转、尺度缩放等变换具有不变性。采用转动力矩的快速计算方法,提高了识别算法的计算效率。识别算法首先使用最大稳定极值区域( MSER)算法检测出目标特征区域,并将其变换为圆形区域,然后结合快速转动力矩特征算法提取出目标区域的局部不变特征,最后输入训练好的支持向量机分类器进行识别。实验结果表明相比于已有的激光主动成像目标识别方法,所提算法对于旋转、仿射变换均具有更高的识别率,同时单帧平均运算时间为9.68 ms,满足激光主动成像目标识别系统实时性的要求。
針對激光主動成像的圖像特性,提齣一種基于快速輪廓轉動力矩的目標識彆方法。將轉動力矩的概唸引入目標識彆中,提齣的快速輪廓轉動力矩特徵( FCTF)不僅包含瞭輪廓的呎吋、位置、規則度以及目標的亮暗等信息,同時對于鏇轉、呎度縮放等變換具有不變性。採用轉動力矩的快速計算方法,提高瞭識彆算法的計算效率。識彆算法首先使用最大穩定極值區域( MSER)算法檢測齣目標特徵區域,併將其變換為圓形區域,然後結閤快速轉動力矩特徵算法提取齣目標區域的跼部不變特徵,最後輸入訓練好的支持嚮量機分類器進行識彆。實驗結果錶明相比于已有的激光主動成像目標識彆方法,所提算法對于鏇轉、倣射變換均具有更高的識彆率,同時單幀平均運算時間為9.68 ms,滿足激光主動成像目標識彆繫統實時性的要求。
침대격광주동성상적도상특성,제출일충기우쾌속륜곽전동력구적목표식별방법。장전동력구적개념인입목표식별중,제출적쾌속륜곽전동력구특정( FCTF)불부포함료륜곽적척촌、위치、규칙도이급목표적량암등신식,동시대우선전、척도축방등변환구유불변성。채용전동력구적쾌속계산방법,제고료식별산법적계산효솔。식별산법수선사용최대은정겁치구역( MSER)산법검측출목표특정구역,병장기변환위원형구역,연후결합쾌속전동력구특정산법제취출목표구역적국부불변특정,최후수입훈련호적지지향량궤분류기진행식별。실험결과표명상비우이유적격광주동성상목표식별방법,소제산법대우선전、방사변환균구유경고적식별솔,동시단정평균운산시간위9.68 ms,만족격광주동성상목표식별계통실시성적요구。
Due to the characteristic of images in laser active imaging, a novel target recognition method based on fast contour torque features( FCTF) is proposed.The concept of torque is introduced into target recogni-tion.The proposed fast contour torque features contain abundant information such as the size, position, shape regularly of the contours and darkness of the target, which are as well invariant to rotation and scaling.Mean-while the fast calculation method greatly improves the computational efficiency.Firstly feature regions are de-tected using Maximally Stable Extremal Regions( MSER) algorithm, and transformed into circular areas.Then local invariant features of the feature regions are extracted by fast contour torque feature descriptor.At last the features are input into the trained Suppor Vector Machine( SVM) classifier for identification.The experimental results indicate that compared with the existing laser active imaging recognition algorithms, the proposed meth-od acquires higher recognition rate in rotation and affine transformation, and the average computing time of sin-gle frame is 9.68 ms, which meet the real-time requirement in laser active imaging.