首页> 外文会议>International Scientific-Practical Conference Problems of Infocommunications Science and Technology >Parameter Definition of the Camera Settings and of Recognizable Object in the System of Automatic Video Recording
【24h】

Parameter Definition of the Camera Settings and of Recognizable Object in the System of Automatic Video Recording

机译:摄像机设置的参数定义和自动视频录制系统中的可识别对象

获取原文

摘要

A detailed analysis of the requirements for video surveillance systems and algorithms for character recognition is carried out. In order to obtain correct results, it is necessary that the entire measuring path (Camcorder-Cable-Monitor) be, as far as possible, of minimum length and maximum quality. The measuring table should be evenly illuminated. The shorter the focal length, the stronger the distortion. Therefore cameras with wide-angle lenses (less than 4mm) are undesirable to use. Maximum effect on the depth of field is provided by the lens aperture. The smaller the aperture opening - the greater the depth of field, the more - the smaller the depth of field. All the recommended cameras for recognizing numbers are able to adjust to changing lighting conditions by automatically changing the aperture. It is recommended to adjust the focus of such cameras with the maximum open aperture, when the depth of field is minimal. Most of the existing methods rely on the allocation of license plate boundaries. This fact can be used in additional image analysis. Consider all such problems - this is the task for serious number recognition systems.
机译:进行了对视频监控系统的要求和字符识别的算法的详细分析。为了获得正确的结果,必须尽可能最小的长度和最大质量的整个测量路径(摄像机电缆监控)。测量表应均匀照亮。焦距越短,失真越强。因此,具有广角镜片(小于4mm)的相机是不希望的。透镜孔提供对景深的最大影响。孔径开口越小 - 越越大,景深越多 - 较小的景深越小。用于识别数字的所有推荐相机都能够通过自动更改光圈来调整为改变照明条件。建议使用最大开口孔径调节这种相机的焦点,当前景深很小。大多数现有方法都依赖于牌照边界的分配。这一事实可用于额外的图像分析。考虑所有此类问题 - 这是严重数字识别系统的任务。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号