Blind Image Quality Prediction for Object Detection

Abstract

Automatic video data analysis tools have become indispensable components in today's imaging applications. The accuracy of automatic analysis methods relies on the quality of images or videos that are processed. It is therefore essential to introduce objective metrics for predicting the quality of images as evaluated by automatic analysis algorithms. Object detection is the first and the most important step in the process of automatic video analysis. This paper proposes a new image quality model for predicting the performance of object detection. A video data set is constructed that considers different factors related to quality degradation in the imaging process, such as reduced image 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 such as PSNR and SSIM.