Detection Algorithm of Chest Bitmap Based on Spatio-temporal Context Information
-
摘要:
为减小光照不均与随机抖动对胸环靶着弹检测精度的影响，该文提出一种融合时空上下文信息的胸环靶着弹检测算法。利用目标及其邻域的空间上下文信息进行光照均衡化，并提取胸环靶序列间时域运动上下文信息进行抖动校正。为提高胸环靶图像的稳定性，该算法提出多参数融合方法对抖动校正后的序列图像进行像素级融合。接着进行弹孔区域粗提取、能量筛选与重叠弹孔判别，获得弹孔位置分布。采用在部队靶场实地采集的图像进行实验，验证了该算法可以有效抑制光照不均与随机抖动带来的噪声影响，具有较好的弹孔提取能力。
Abstract:A detection algorithm based on spatio-temporal context information is proposed to reduce the influence of non-uniform illumination and random jitter on the accuracy of target hole detection. The light equalization is carried out by using the spatial context information of target and its neighborhood, and the temporal motion context information between chest bitmap sequences is extracted for dithering correction. In order to improve the stability of chest bitmaps, a multi-parameter fusion method is proposed to perform pixel-level fusion of jitter corrected sequence images. Then, rough extraction of bullet hole area, energy screening and overlapping bullet holes discrimination are carried out to obtain the location distribution of bullet holes. The experimental results show that the algorithm can effectively suppress the noise caused by non-uniform illumination and random jitter, and has great ability of bullet hole extraction.
-
表 1 IQA参数比较
${\mu _1}$(mean) ${\mu _2}$(std) ${\mu _3}$(grad) SSEQ 0.1 0.4 0.5 49.7565 0.2 0.3 0.5 50.7473 0.3 0.2 0.5 50.5672 0.4 0.1 0.5 49.4026 0.1 0.3 0.6 49.2834 0.2 0.2 0.6 50.0364 0.3 0.1 0.6 49.9368 0.1 0.2 0.7 49.2470 0.2 0.1 0.7 49.3499 0.1 0.1 0.8 48.9924 
下载: 导出CSV
表 3 弹孔中心坐标位置偏差与检测效率
序号 真值 检测结果 $(|\Delta x|,|\Delta y|)$ $\sqrt {\Delta {x^2} + \Delta {y^2}} $ 检测效率(s) 1 (206,725) (206.50,725.00) (0.50,0) 0.50 0.7413 2 (460,297) (459.63,297.50) (0.37,0.50) 0.62 0.7744 3 (267,541) (266.35,542.24) (0.65,1.24) 1.40 0.8000 4 (436,456) (436.77,457.13) (0.77,1.13) 1.37 0.7711 5 (733,626) (733.00,626.49) (0,0.49) 0.49 0.7656 6 (685,891) (686.50,888.50) (1.50,2.50) 2.92 0.7711 7 (797,915) (796.50,915.50) (0.50,0.50) 0.71 0.7586 8 (573,821) (573.00,819.50) (0,1.50) 1.50 0.7843 9 (700,758) (699.00,758.00) (1.00,0) 1.00 0.7946 10 (760,711) (760.13,710.32) (0.13,0.68) 0.69 0.8425
下载: 导出CSV
-
苑玮琦, 李梦祺. 基于视觉检测的胸环靶自动报靶系统研究[J]. 计算机技术与发展, 2019, 29(2): 147–151. doi: 10.3969/j.issn.1673-629X.2019.02.031YUAN Weiqi and LI Mengqi. Research on target of automatic scoring system based on visual inspection[J]. Computer Technology and Development, 2019, 29(2): 147–151. doi: 10.3969/j.issn.1673-629X.2019.02.031 罗杰, 张之明. 基于图像处理技术自动报靶系统综述[J]. 激光杂志, 2016, 37(7): 1–6. doi: 10.14016/j.cnki.jgzz.2016.07.001LUO Jie and ZHANG Zhiming. Survey on automatic target-scoring system based on image processing technology[J]. Laser Journal, 2016, 37(7): 1–6. doi: 10.14016/j.cnki.jgzz.2016.07.001 尹乾. 基于图像处理技术的自动报靶系统研究[D]. [硕士论文], 重庆大学, 2017: 37–45.YIN Qian. Study on automatic target scoring based on image processing technology[D]. [Master dissertation], Chongqing University, 2017: 37–45. WIDAYAKA P D, KUSUMA H, and ATTAMIMI M. Automatic shooting scoring system based on image processing[J]. Journal of Physics: Conference Series, 2019, 1201: 012047. doi: 10.1088/1742-6596/1201/1/012047 余梓. 基于图像处理技术的弹孔定位系统研究[D]. [硕士论文], 哈尔滨理工大学, 2016: 27–40.YU Zi. Study on bullet hole positioning system based on image processing technology[D]. [Master dissertation], Harbin University of Science and Technology, 2016: 27–40. 周友行, 周健, 邓渝波, 等. 基于边缘特征与HSI色彩特征的胸环靶弹孔识别[J]. 计算机工程与应用, 2015, 51(24): 190–194. doi: 10.3778/j.issn.1002-8331.1312-0221ZHOU Youhang, ZHOU Jian, DENG Yubo, et al. Chest bitmap bullet identification based on edge feature and HSI color feature[J]. Computer Engineering and Applications, 2015, 51(24): 190–194. doi: 10.3778/j.issn.1002-8331.1312-0221 徐建强, 陆耀. 一种基于加权时空上下文的鲁棒视觉跟踪算法[J]. 自动化学报, 2015, 41(11): 1901–1912. doi: 10.16383/j.aas.2015.c150073XU Jianqiang and LU Yao. Robust visual tracking via weighted spatio-temporal context learning[J]. Acta Automatica Sinica, 2015, 41(11): 1901–1912. doi: 10.16383/j.aas.2015.c150073 程新. 基于同态滤波的图像增强算法研究[D]. [硕士论文], 西安邮电大学, 2016: 33–40.CHENG Xin. Image enhancement algorithm based on homomorphic filtering[D]. [Master dissertation], Xi’an University of Posts & Telecommunications, 2016: 33–40. TIAN Qichong and COHEN L D. Global and local contrast adaptive enhancement for non-uniform illumination color images[C]. 2017 IEEE International Conference on Computer Vision Workshop (ICCVW), Venice, Italy, 2017: 3023–3030. doi: 10.1109/ICCVW.2017.357. 魏闪闪, 谢巍, 贺志强. 数字视频稳像技术综述[J]. 计算机研究与发展, 2017, 54(9): 2044–2058. doi: 10.7544/issn1000-1239.2017.20160078WEI Shanshan, XIE Wei, and HE Zhiqiang. Digital video stabilization techniques: A survey[J]. Journal of Computer Research and Development, 2017, 54(9): 2044–2058. doi: 10.7544/issn1000-1239.2017.20160078 胡瑞卿, 田杰荣. 基于光流法的运动目标检测算法研究[J]. 电子世界, 2019(5): 58–61. doi: 10.19353/j.cnki.dzsj.2019.05.031HU Ruiqing and TIAN Jierong. Research on moving target detection algorithm based on optical flow method[J]. Electronics World, 2019(5): 58–61. doi: 10.19353/j.cnki.dzsj.2019.05.031 田伟, 柏方超. 基于特征点的KLT实时目标跟踪算法实现[J]. 光电技术应用, 2019, 34(1): 31–34. doi: 10.3969/j.issn.1673-1255.2019.01.007TIAN Wei and BAI Fangchao. Implementation of KLT target tracking algorithm feature point-based[J]. Electro-Optic Technology Application, 2019, 34(1): 31–34. doi: 10.3969/j.issn.1673-1255.2019.01.007 王喆. 多聚焦图像像素级融合算法研究[D]. [硕士论文], 郑州大学, 2018: 15–30.WANG Zhe. Research on pixel-level fusion algorithms for multi-focus image[D]. [Master dissertation], Zhengzhou University, 2018: 15–30. GOH T Y, BASAH S N, YAZID H, et al. Performance analysis of image thresholding: Otsu technique[J]. Measurement, 2018, 114: 298–307. doi: 10.1016/j.measurement.2017.09.052 LIU Lixiong, LIU Bao, HUANG Hua, et al. No-reference image quality assessment based on spatial and spectral entropies[J]. Signal Processing: Image Communication, 2014, 29(8): 856–863. doi: 10.1016/j.image.2014.06.006 -
计量
- 文章访问数: 2563
- HTML全文浏览量: 1136
- PDF下载量: 47
- 被引次数: 0
下载:
