A No-Reference Image Quality Model for Object Detection on Embedded Cameras
A No-Reference Image Quality Model for Object Detection on Embedded Cameras
复制标题
DOI：
10.4018/ijmdem.2019010102
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Lingchao Kong;A. Ikusan;Rui Dai;Jingyi Zhu;Da Ros
中科院分区：
文献类型：
--
作者：
Lingchao Kong;A. Ikusan;Rui Dai;Jingyi Zhu;Da Ros
自动视频分析工具是成像应用中不可或缺的组成部分。目标检测是视频自动分析的第一步，也是最重要的一步，许多嵌入式摄像机都实现了目标检测。目标检测的准确性取决于所处理图像的质量。本文提出了一种新的图像质量模型，用于预测嵌入式摄像机的目标检测性能。构建视频数据集，其考虑成像过程中的质量劣化的不同因素，诸如降低的分辨率、噪声和模糊。常用的低复杂度的目标检测算法的性能得到的数据集。建立了一个基于回归树装袋集成的无参考回归模型，用于预测图像中可观察特征的目标检测精度。实验结果表明，该模型提供了更准确的预测图像质量的目标检测比通常已知的图像质量的措施。
Automatic video analysis tools are an indispensable component in imaging applications. Object detection, the first and the most important step for automatic video analysis, is implemented in many embedded cameras. The accuracy of object detection relies on the quality of images that are processed. This paper proposes a new image quality model for predicting the performance of object detection on embedded cameras. A video data set is constructed that considers different factors for quality degradation in the imaging process, such as reduced resolution, noise, and blur. The performances of commonly used low-complexity object detection algorithms are obtained for the data set. A no-reference regression model based on a bagging ensemble of regression trees is built to predict the accuracy of object detection using observable features in an image. Experimental results show that the proposed model provides more accurate predictions of image quality for object detection than commonly known image quality measures.