AIM： To determine the association between the binocular vision and an abnormal head posture（AHP）when watching television（TV） in children 7-14 y of age.·METHODS： Fifty normal children in the normal group and...AIM： To determine the association between the binocular vision and an abnormal head posture（AHP）when watching television（TV） in children 7-14 y of age.·METHODS： Fifty normal children in the normal group and 52 children with an AHP when watching TV in the AHP group were tested for spherical equivalents, far and near fusional convergence（FC） and fusional divergence（FD） amplitudes, near point of convergence, far and near heterophoria, accommodative convergence/accommodation ratio and stereoacuity. The values of these tests were compared between the two groups. The independent t test was applied at a confidence level of95%.·RESULTS： The far and near FC amplitudes and far FD amplitudes were lower in the AHP group（the far FC amplitudes： break point 13.6±5.4~△, recovery point 8.7±5.4~△.The near FC amplitudes： break point 14.5 ±7.3~△, recovery point 10. 3 ± 5. 1~△. The far FD amplitudes ： break point3.9±2.7~△, recovery point 2.6±2.3~△） compared with those in the normal group（the far FC amplitudes： break point19.1 ±6.2△, recovery point 12.4 ±4.5~△. The near FC amplitudes： break point 22.3 ±8.0~△, recovery point 16.1 ±5.7~△. The far FD amplitudes： break point 7.0 ±2.1~△,recovery point 4.6 ±1.9~△）. Other tests presented no statistically significant differences.·CONCLUSION： An association between the reduced FC and FD amplitudes and the AHP in children when watching TV is proposed in the study. This kind of AHP is considered to be an anomalous manifestation which appears in a part of puerile patients of fusional vergence dysfunction.展开更多
为防止驾驶员误判或忽视交通标志和车辆,提出一种通过线性加权方法融合Faster RCNN(faster regions with CNN features)和YOLOX-Tiny(you only look once X-Tiny)模型的路况检测算法,结合双目摄像头对检测目标物进行距离检测,以增强模...为防止驾驶员误判或忽视交通标志和车辆,提出一种通过线性加权方法融合Faster RCNN(faster regions with CNN features)和YOLOX-Tiny(you only look once X-Tiny)模型的路况检测算法,结合双目摄像头对检测目标物进行距离检测,以增强模型对道路远处目标的检测能力.实验结果表明,模型融合算法相较于Faster RCNN,每秒传输帧数提升了30.6帧,与YOLOX-Tiny相比,其目标检测结果的平均精度提升了21.9%.展开更多
除草是保证农作物高产的必要工作。针对机械化除草和智能喷药中存在的杂草识别问题,以2～5叶苗期玉米及杂草为研究对象,进行了融合高度特征与单目图像特征的杂草识别方法研究。首先从单目图像中提取16个形态特征和2个纹理特征;然后基于...除草是保证农作物高产的必要工作。针对机械化除草和智能喷药中存在的杂草识别问题,以2～5叶苗期玉米及杂草为研究对象,进行了融合高度特征与单目图像特征的杂草识别方法研究。首先从单目图像中提取16个形态特征和2个纹理特征;然后基于双目图像,提出了针对植株的高度特征提取方法,所得高度特征与实际测量值间误差在±12 mm以内;利用max-min ant system算法对形态特征进行优化选择,将形态特征减少到6个,有效减少数据量62.5%,并与纹理和高度特征进行融合;将2～5叶玉米幼苗的可除草期划分为3个阶段,分别构建融合高度特征与单目图像特征的SVM识别模型,并与相应不含高度特征模型进行对比。经测试,3个阶段模型的识别准确率分别为96.67%,100%,98.33%;平均识别准确率达98.33%。不含高度特征模型的识别准确率分别为93.33%,91.67%,95%;平均识别准确率为93.33%。结果表明,融合高度特征与单目图像特征的SVM识别模型优于不含高度特征模型,平均识别准确率提高了5百分点。该方法实现了高准确率的杂草识别,研究结果为农业精确除草的发展提供参考。展开更多
基金Supported by the Scientific and Technological Project of Henan Scientific Committee(No.112102310193No.122102310132+2 种基金No.132102310132)the Key Scientific Research Project of Education Department of HenanProvince(No.12A320068)the Medical Science Research Project of Henan Province(No.201003112)
文摘AIM： To determine the association between the binocular vision and an abnormal head posture（AHP）when watching television（TV） in children 7-14 y of age.·METHODS： Fifty normal children in the normal group and 52 children with an AHP when watching TV in the AHP group were tested for spherical equivalents, far and near fusional convergence（FC） and fusional divergence（FD） amplitudes, near point of convergence, far and near heterophoria, accommodative convergence/accommodation ratio and stereoacuity. The values of these tests were compared between the two groups. The independent t test was applied at a confidence level of95%.·RESULTS： The far and near FC amplitudes and far FD amplitudes were lower in the AHP group（the far FC amplitudes： break point 13.6±5.4~△, recovery point 8.7±5.4~△.The near FC amplitudes： break point 14.5 ±7.3~△, recovery point 10. 3 ± 5. 1~△. The far FD amplitudes ： break point3.9±2.7~△, recovery point 2.6±2.3~△） compared with those in the normal group（the far FC amplitudes： break point19.1 ±6.2△, recovery point 12.4 ±4.5~△. The near FC amplitudes： break point 22.3 ±8.0~△, recovery point 16.1 ±5.7~△. The far FD amplitudes： break point 7.0 ±2.1~△,recovery point 4.6 ±1.9~△）. Other tests presented no statistically significant differences.·CONCLUSION： An association between the reduced FC and FD amplitudes and the AHP in children when watching TV is proposed in the study. This kind of AHP is considered to be an anomalous manifestation which appears in a part of puerile patients of fusional vergence dysfunction.
文摘为防止驾驶员误判或忽视交通标志和车辆,提出一种通过线性加权方法融合Faster RCNN(faster regions with CNN features)和YOLOX-Tiny(you only look once X-Tiny)模型的路况检测算法,结合双目摄像头对检测目标物进行距离检测,以增强模型对道路远处目标的检测能力.实验结果表明,模型融合算法相较于Faster RCNN,每秒传输帧数提升了30.6帧,与YOLOX-Tiny相比,其目标检测结果的平均精度提升了21.9%.
文摘除草是保证农作物高产的必要工作。针对机械化除草和智能喷药中存在的杂草识别问题,以2～5叶苗期玉米及杂草为研究对象,进行了融合高度特征与单目图像特征的杂草识别方法研究。首先从单目图像中提取16个形态特征和2个纹理特征;然后基于双目图像,提出了针对植株的高度特征提取方法,所得高度特征与实际测量值间误差在±12 mm以内;利用max-min ant system算法对形态特征进行优化选择,将形态特征减少到6个,有效减少数据量62.5%,并与纹理和高度特征进行融合;将2～5叶玉米幼苗的可除草期划分为3个阶段,分别构建融合高度特征与单目图像特征的SVM识别模型,并与相应不含高度特征模型进行对比。经测试,3个阶段模型的识别准确率分别为96.67%,100%,98.33%;平均识别准确率达98.33%。不含高度特征模型的识别准确率分别为93.33%,91.67%,95%;平均识别准确率为93.33%。结果表明,融合高度特征与单目图像特征的SVM识别模型优于不含高度特征模型,平均识别准确率提高了5百分点。该方法实现了高准确率的杂草识别,研究结果为农业精确除草的发展提供参考。
